BR102019001478A2 - METHOD FOR VERIFYING IDENTITY USING PRE-COLLECTED IMAGE / BIOMETRIC DATA - Google Patents

Abstract

The present invention relates to systems and methods for authenticating a user to an authentication system using a computing device configured to capture authentication biometric identification information. authentication biometric identification information is captured during an authentication session. authentication biometric identification information may comprise or be derived from one or more images of the user being authenticated. The authentication biometric identification information is compared to the root identification biometric information. Root identification biometric information is captured from a trusted source, such as from trusted devices located in trusted locations, such as a government entity, financial institution, or commerce. Identity verification can occur by comparing the trusted root identification biometric information with the biometric identification information captured during an authentication session. Proof of life determination can also occur to verify if the user is a living person. Proof-of-life determination may include comparing two user images, the two images being captured at different user distances.

Description

“METHOD FOR VERIFYING IDENTITY USING IMAGE / BIOMETRIC DATA PREVIOUSLY COLLECTED”.

FIELD [001] The modalities disclosed refer to biometric security. More specifically, the modalities disclosed refer to facial recognition authentication systems.

RELATED TECHNIQUE [002] With the advent of personal electronic devices that can be used to access many different user accounts, and the growing threat of identity theft and other security issues, there is an increasing need for ways to securely access accounts of users through electronic devices. Account holders are therefore often required to have longer passwords that meet various criteria, such as the use of a mixture of upper and lower case letters, numbers and other symbols. With smaller electronic devices, such as smartphones, smart watches, “Internet of things” (“IoT”) and other devices, it can be difficult to try to type these long passwords into the device each time access to the account is desired and, if another individual knows the user's password, the user can be represented without actually being present. In some cases, users may even decide to disable these annoying security measures due to the inconvenience of their devices. Thus, users of such devices may prefer other methods of secure access to their user accounts.

[003] Another of these methods can be through biometrics. For example, an electronic device may have a dedicated sensor that can scan a user's fingerprint to determine whether the person requesting access to a device or an account is authorized. However, such fingerprint systems are often prohibitively expensive to use on an electronic device

Petition 870190026446, of 03/20/2019, p. 6/137

2/113 small and are often considered unreliable and insecure.

[004] In addition, facial recognition is generally known and can be used in a variety of contexts. Two-dimensional facial recognition is commonly used to tag people in images on social networks or in photo editing software. The facial recognition software, however, was not widely implemented individually to securely authenticate users trying to gain access to an account because it is not considered to be secure enough. For example, two-dimensional facial recognition is considered unsafe because the faces can be photographed or recorded and then the resulting prints or videos showing images of the user can be used to trick the system. Thus, there is a need for a reliable, economical and convenient method to authenticate users who attempt to log in, for example, to a user account.

SUMMARY [005] The disclosed modalities were developed in light of the above, and aspects of the invention may include a method for registering and authenticating a user in an authentication system through a user's mobile computing device. The user device includes a camera and at least one motion detection sensor, such as an accelerometer, magnetometer and gyroscope.

[006] In one mode, the user can register in the system by providing registration images of the user's face. The registration images are obtained by the camera of the mobile device as the user moves the mobile device to different positions in relation to the user's head. The user can then obtain registration images showing the user's face from different angles and distances. The system can also use one or more motion sensors from a mobile device to determine a register movement path that the

Petition 870190026446, of 03/20/2019, p. 7/137

3/113 phone did during image generation. At least one image is processed to detect the user's face within the image, and to obtain biometric information from the user's face in the image. Image processing can be done on the user's mobile device or on a remote device, such as an authentication server or a user account server. Registration information (biometrics, movement and other registration information) can be stored on the mobile device or remote device, or both.

[007] The system can then authenticate a user by providing, by the user, at least one authentication image through the camera of the mobile device while the user moves the mobile device to different positions in relation to the user's head. The authentication images are processed by information from facial biometrics and facial detection. Path parameters can also be obtained during the image generation of the authentication images (authentication movement). The authentication information (biometrics, movement and other authentication information) is then compared with the registration information to determine whether the user should be authenticated or denied. Image processing and comparison can be conducted on the user's mobile device or can be conducted remotely.

[008] In some modalities, several registration profiles can be created by a user to provide greater security. For example, a user can create a register using accessories, such as a hat or glasses, or by making a funny face. In other ways, the user's registration information can be linked to a user's email address, phone number, or other unique identifier.

[009] The authentication system can include comments displayed on the mobile device to assist a user in learning and authenticating with the system. For example, a precision meter can provide feedback on a

Petition 870190026446, of 03/20/2019, p. 8/137

4/113 movement correspondence rate or authentication biometrics. A motion meter can provide feedback on the movement detected by the mobile device.

[010] In some modalities, the system can reward users who correctly use the authentication system or who otherwise take fraud prevention measures. Such rewards may include leaderboards, status levels, reward points, coupons or other offers, and the like. In some embodiments, the authentication system can be used to log into multiple accounts.

[011] In addition to biometric and motion matching, some modalities may also use band detection, glare detection and edge detection on the screen to make the system more secure. In other modalities, other user attributes can be detected and combined including the user's gender, age and ethnicity, and the like.

[012] The system can also provide gradual access to the user account (s) when the user first configures the authentication system. As the user correctly implements the system, the authorization can be expanded. For example, for a period of time as the user gets used to the authentication system, lower transaction limits may apply.

[013] In some modalities, the mobile device may present video comments of what the user is photographing to assist the user in photographing his face during registration or authentication. Video comments can be displayed on only part of the display screen of the mobile device. For example, video comments can be displayed in an upper portion of the display screen. The display of video comments can be positioned on a portion of the display screen that corresponds to a location on a front camera of the mobile device.

Petition 870190026446, of 03/20/2019, p. 9/137

5/113 [014] To facilitate low-light imaging, portions of the screen, other than video comments, can be displayed in a bright color, such as white. In some embodiments, LED or infrared light can be used, and near-infrared thermal imaging can be done with an infrared camera. The mobile device used for imaging can then have multiple cameras for capturing infrared and visible light images. The mobile device can also have multiple cameras (two or more) forming images in a single spectrum or multiple spectrum to provide stereoscopic three-dimensional images. In this mode, close-up frames (with zoom) can create the greatest differentiation compared to images captured from a distance. In this mode, frames captured at a distance may be unnecessary.

[015] In some modalities, to provide greater security, the mobile device can emit objects, colors or patterns on the display screen to be detected during the image generation. The predetermined object or pattern can be a single one-dimensional or two-dimensional barcode. For example, a QR code (two-dimensional barcode) can be displayed on the screen and reflected from the user's eye. If the QR code is detected in the image, then the person can be authenticated. In other modalities, an object can move on the screen and the system can detect whether the user's eye follows the movement.

[016] In some modalities, the system can provide instructions in a display of video comments to assist the user in moving the device in relation to the user's head during registration and / or authentication. Instructions can include ovals or frames displayed on the display screen where the user must place his face by moving the mobile device until his face is inside the oval or frame. The instructions can preferably be of different sizes and can also be centered at different positions on the screen. When

Petition 870190026446, of 03/20/2019, p. 10/137

6/113 a real three-dimensional person captures his image from near and far, it turns out that the biometric results are different due to the barrel-type distortion effect of the lenses at different distances. In this way, a three-dimensional person can be validated when the biometric results are different in the near and far images. This also allows the user to have multiple biometric profiles for each of the distances.

[017] In other modalities, the biometrics of images obtained between near and far images can be analyzed for incrementally different biometric results. In this way, the transformation of the face from a distant angle to the next deformed one is captured and tracked. Incremental frames during authentication can then be combined with frames captured at similar locations during registration along the movement path and compared to ensure that expected similarities and differences are found. This results in a movement path and captured image and biometric data that can prove that a three-dimensional person is currently being photographed. Thus, not only do we compare the near and far biometric data, but also the biometric data obtained between them. The biometric data obtained between them must also correspond to a correct transformation speed along the movement path, greatly increasing the security of the system.

[018] The touch screen can be used in some modes. For example, the user may need to enter or swipe (slide) a code or pattern in addition to the authentication system described here. The touch screen can also detect the size and orientation of the user's finger and whether the right or left hand is used on the touch screen. Voice parameters can also be used as an additional layer of security. The system can detect edge sharpness or other indicators to ensure that the images obtained are of sufficient quality for the

Petition 870190026446, of 03/20/2019, p. 11/137

7/113 authentication system.

[019] When a camera has an autofocus, the autofocus can be controlled by the system to validate the presence of the real three-dimensional person. Autofocus can verify that different characteristics of the user or the environment are focused at different focal lengths. In other modalities, the authentication images can be saved to evaluate the person who tried to authenticate with the system.

[020] In some modalities, the necessary correspondence limits can be adapted over time. The system can therefore consider changes in biometrics due to age, weight gain / loss, environment, user experience, security level or other factors. In other modalities, the system can use image distortion before obtaining biometric information to further protect against fraudulent access.

[021] A method for verifying biometric authentication comprising receiving a user's root biometric identification information from a trusted biometric information source to establish the root biometric identification information as being trusted and verified is also disclosed. Store the root biometric identification information in a database and, later, during an authentication process, capture a first image with an authentication camera. The first image is captured when the user is at a first distance from the authentication camera. Capture a second image with the authentication camera, so that the second image is captured when the user is a second distance from the authentication camera. The first distance is different from the second distance. The method of operation also includes processing the first image to create the first biometric authentication information and processing the second image to create the second biometric authentication information. The method also compares the first

Petition 870190026446, of 03/20/2019, p. 12/137

8/113 biometric authentication information with the second biometric authentication information and compares the root biometric identification information with the first biometric authentication information, the second biometric authentication information, or both. The method will authenticate the user when the comparison determines that the first biometric authentication information corresponds to the second biometric authentication information within a limit, but is not identical, and the comparison determines that the root biometric identification information corresponds to the first biometric information of second biometric authentication information, or both, within a limit.

[022] In one embodiment, the authentication camera is one of the following types of cameras: camera on a user's mobile device, camera on a user's computer, camera at an ATM, camera at a point of sale and camera at a financial institution. The source of reliable biometric information is a first camera in a trusted source. The first camera can be located in a financial institution or in a government agency office. In one configuration, an authentication server receives the root biometric identification information, the first biometric authentication information and the second biometric authentication information, and the authentication server performs the comparison and authentication.

[023] In an arrangement, the first image and the second image are of the user's face. As part of a proof of life determination, one of the first image and the second image is distorted due to barrel-type distortion. The method may also include performing one or more additional life proof tests on the first image or the second image to verify that the user is a living person during the authentication process.

[024] A method for verifying a user's biometric authentication including storing identification information is also disclosed.

Petition 870190026446, of 03/20/2019, p. 13/137

9/113 user's root biometric obtained from a trusted biometric detection device that is located in a trusted location to establish the root biometric identification information as trusted and verified. Then, during an authentication session, receiving biometric identification information from the root, receiving biometric identification information from the user of a computing device during an authentication session and comparing the biometric identification information with the biometric identification information from authentication. Authenticate the user when the root biometric identification information matches the authentication biometric identification information within a predetermined limit.

[025] In one embodiment, the reliable biometric detection device is in one of the following locations: financial institution, commercial point of sale or government entity. The computing device used during an authentication session is located at a financial institution, ATM, business point of sale or is the user's mobile device or the user's personal computer. In one embodiment, the trusted biometric detection device includes a camera, and the computing device used during an authentication session includes a camera. The root biometric identification information and the authentication biometric identification information are based on a facial image of the user and at least one other item of biometric information.

[026] In one embodiment, this method also comprises capturing supplementary authentication biometric identification information from the user during the authentication session and comparing supplementary authentication biometric identification information with authentication biometric identification information. The method also compares the supplementary authentication biometric identification information with the root biometric identification information. The user is authenticated when the comparison determines that the biometric information

Petition 870190026446, of 03/20/2019, p. 14/137

10/113 authentication corresponds to supplementary authentication biometric information within a first limit, but is not identical, and the comparison determines that the root biometric identification information corresponds to supplementary authentication biometric information within the predetermined limit.

[027] An identity authentication system comprising the following elements is also disclosed. A first computing device configured to request and receive root biometric identification information, for a user, from a trusted source, so that the trusted source is a government affiliated entity or a financial institution. A second computing device configured to, during an authentication session, create biometric authentication information captured from the user during the authentication session, compare the biometric authentication information with the root biometric identification information and perform a proof of life determination on the user during the authentication session using the biometric authentication information. In response to the comparison and execution, authenticate the user if the comparison determines that the biometric authentication information matches the root biometric identification information within a limit and the proof of life determination determines that the user is a living person.

[028] The root biometric identification information can be derived from an image. In a configuration, a user image cannot be recreated from the root biometric identification information. The first computing device and the second computing device can be the same computing device. It is also contemplated that the biometric authentication information is derived from at least a first image and a second image, which are captured by a camera associated with the second computing device. Thus, the first image is captured by the camera located at a first distance from the user and the second image is captured by the camera located at a second

Petition 870190026446, of 03/20/2019, p. 15/137

11/113 user distance, the second distance being less than the first distance. The proof of life determination comprises determining whether the second image has barrel-type distortion compared to the first image.

[029] Also disclosed here is a method for establishing a reliable biometric profile comprising capturing a user's biometric information when the user makes a financial payment to third parties, the financial payment to third parties creating financial payment data. Then, store the user's biometric information with the financial payment data and create a biometric trust profile associated with the user with the user's biometric information with the financial payment data to establish trust in the biometric profile.

[030] In one mode, capturing biometric information comprises capturing at least a first image at a first distance from the user, processing the first image to create the first biometric information, and capturing at least a second image at a second distance from the user, such that the second distance is different from the first distance. This modality also processes the second image to create second biometric information, and compares the first biometric information with the second biometric information to determine whether the first biometric information corresponds to the second biometric information within a limit. This method may also include performing a life proof test as part of the comparison, comparing the first biometric information with the second biometric information to verify that the first biometric information is not very similar to the second biometric information.

[031] In an arrangement, financial payment to the third party is not accepted when the first biometric information does not match the second biometric information within a limit or the proof of life test determines that the biometric information is not from a living person. It is also contemplated that this method may

Petition 870190026446, of 03/20/2019, p. 16/137

12/113 understand capturing additional biometric information from a user, in addition to prior biometric information, when the user makes additional financial payment to a third party. Then, compare a user's additional biometric information with the previous biometric information, and in response to a match between the additional biometric information and the previous biometric information, update the biometric trust profile to increase the confidence associated with the trust profile biometric. However, in response to a mismatch between the additional biometric information and the previous biometric information, update the biometric confidence profile with an indicator of a frustrated comparison.

[032] The method may further comprise generating a confidence score for the user's biometric confidence profile, the confidence score being determined by at least one of the following: amount of financial payment, number of financial payments, and age of the profile of biometric confidence. The biometric trust profile can be shared or used by other entities to verify a person's identity based on the biometric trust profile.

[033] Also disclosed is a method for establishing a reliable biometric profile of a user comprising capturing a user's first biometric information when the user performs a first confidence building action and processing the first biometric information to generate a biometric information profile. Capture the user's second biometric information when the user performs a second trust-building action and process the second biometric information to compare the first biometric information with the second biometric information. If the processing determines that the first biometric information matches the second biometric information within a limit, then update the reliable biometric profile to reflect the match, but if the processing determines that the first biometric information does not match the second biometric information within the limit then update the profile

Petition 870190026446, of 03/20/2019, p. 17/137

13/113 reliable biometric to reflect the mismatch.

[034] In one embodiment, the confidence building action is one or more of the following: financial payment, attendance at the workplace, payments to a guarantee account and medical consultation. The biometric information profile can include a confidence score that is based on the matches of the biometric information, the number of trust building actions and the nature of the trust building actions.

[035] In one embodiment, the capture of biometric information comprises capturing at least a first image at a first distance from the user, and processing at least a first image to create the first biometric information. Capture at least a second image at a second distance from the user, such that the second distance is different from the first distance, and process at least a second image to create the second biometric information. Then, compare the first biometric information with the second biometric information to determine whether the first biometric information corresponds to the second biometric information within a limit.

[036] This method may also include performing a life proof test as part of the comparison, comparing the first biometric information with the second biometric information to verify that the first biometric information is different from the second biometric information due to the change in distance the images are captured. In one embodiment, financial payment to the third party is not accepted when the first biometric information does not match the second biometric information within a limit and the proof of life test determines that the biometric information is from a living person. The biometric trust profile can be shared or used by other entities to verify the user's identity. It is contemplated that the biometric information is derived from an image of the user's face.

Petition 870190026446, of 03/20/2019, p. 18/137

14/113 [037] Also disclosed is a system for developing a biometric trust profile based on user action and biometric user information. In one embodiment, this system comprises a first computing device having a camera configured to capture a first set of images of the user when the user is making a first financial transaction, processing the first set of images to create the first biometric information, and storing the first biometric information as part of a biometric trust profile for the user. A second computing device is also provided which has a camera configured for, or the first computing device is further configured to capture a second set of images of the user when the user is making a second financial transaction, to process the second set of images to create second biometric information, and store the second biometric information as part of a biometric trust profile for the user. A third computing device is configured to compare the first biometric information with the second biometric information, in response to the correspondence between the first biometric information and the second biometric information within a predetermined limit, to update the biometric confidence profile to a confidence level high and, in response to the mismatch between the first biometric information and the second biometric information within a predetermined limit, update the biometric confidence profile to reduce the confidence level.

[038] In one embodiment, the first set of images and the second set of images comprise at least one near image and one distant image, the next image captured when the camera is closer to the user than the distant image. The first computing device or the second computing device can be further configured to perform a proof of life determination on the second set of images to verify that the

Petition 870190026446, of 03/20/2019, p. 19/137

15/113 user in the second set of images is a living person. In one embodiment, an image of the user cannot be recreated from biometric information. The first computing device and the second computing device can be the same computing device. It is contemplated that the biometric confidence profile may include a confidence score representing a confidence level for the biometric confidence profile, such that the confidence score is based on one or more of the following: amount of the financial transaction, number of financial transactions, and how long ago the creation of the first biometric information occurred. In an arrangement, the financial transaction is payment of money to a third party.

[039] Also disclosed is a method for capturing and storing biometric information comprising capturing a user's first biometric information with a computing device, and converting the first biometric information into a first biometric model. Create a first data block that is part of a block chain, such that the first data block includes the first biometric model and the first authentication information. The first block of data is added to the block chain, such that the block chain exists in several places in several different data memories.

[040] In one embodiment, this method further comprises capturing a second biometric information with a computing device and converting the second biometric information into a second biometric model, then comparing the second biometric model with the first biometric model and, in response to an authentication match between the second biometric model and the first biometric model, creating a second data block, the second data block including the second biometric model, the second authentication information, and the results of the comparison. Then add the second block of data to the block chain. It is contemplated that the first biometric information can be at least

Petition 870190026446, of 03/20/2019, p. 20/137

16/113 minus one user image captured with a camera and the second biometric information comprises at least one user image captured with the camera. In one embodiment, the second biometric information can comprise a first image captured at a first distance from the user and a second image captured at a second distance from the user, the converter can convert the first image into a first biometric image model and convert the second image in a second biometric image model, and the comparison can compare the first biometric image model with the second biometric image model. The authentication match can comprise the first biometric image model corresponding to the second biometric image model within a first boundary and the first biometric image model being different from the second biometric image model within a second boundary.

[041] In one embodiment, the authentication information comprises one or more of the following: device ID, a unique user ID, user identification information, the type of algorithm, encryption type, biometric sensor version, registration of date and time, GPS information. This method may further comprise encrypting a block of data when a block of data is added to the block chain. The method can occur on a user's computing device, an authentication server, or both. In an arrangement, a data block is downloaded to a user's computing device in the block chain and a private key is kept by the user to decrypt the downloaded data block. The data block can also include financial transaction information associated with authentication correspondence. Authentication comparison and matching can take place on a block chain edge server. In one embodiment, a user's image cannot be recreated from the root biometric identification information.

Petition 870190026446, of 03/20/2019, p. 21/137

17/113 [042] The system can use any number or combination of security features as security layers, as described in this document. When authentication fails, the system can be configured so that it is not clear which security layer triggered the failure to preserve the integrity of the security system.

[043] Other systems, methods, characteristics and advantages of the invention will or will become apparent to one skilled in the art when examining the Figures and detailed description below. It is intended that all systems, methods, characteristics and advantages are included in this description, are within the scope of the invention, and are protected by the attached claims.

BRIEF DESCRIPTION OF THE DRAWINGS [044] The components in the Figures are not necessarily to scale, emphasizing the principles of the invention. In the figures, the reference numbers designate corresponding parts across the different views.

[045] Figure 1 illustrates an example of an environment for using the facial recognition authentication system, according to an exemplary modality.

[046] Figure 2 illustrates an example of a mobile device.

[047] Figure 3 illustrates exemplary software modules that are part of the mobile device and server.

[048] Figure 4 presents a method to perform authentication by facial recognition according to a modality.

[049] Figure 5 presents a method for registering a user in a facial recognition authentication system, according to an exemplary modality.

[050] Figures 6A and 6B show an example of movement of a

Petition 870190026446, of 03/20/2019, p. 22/137

11/183

mobile device about one face of user according with an modality exemplary. [051] The Figures 7A and 7B show an example of movement of a mobile device about one face of user according with an modality

exemplary.

[052] Figure 8 presents a method of providing authentication information in a face recognition authentication system, according to an exemplary modality.

[053] Figure 9 presents a method for verifying authentication credentials in a facial recognition authentication system, according to an exemplary modality.

[054] Figure 10 illustrates an exemplary display showing graphical and numerical commentary on a facial recognition authentication system.

[055] Figures 11A, 11B and 11C illustrate displays of exemplary video comments corresponding to front camera positions in a face recognition authentication system.

[056] Figure 12 presents an example video display commentary of a facial recognition authentication system in which border pixels on the sides of the display are horizontally extended.

[057] Figures 13A and 13B illustrate exemplary screen displays with facial alignment indicators shown as an oval to serve as a guide as the user moves the mobile device closer to or away from his face.

[058] Figure 14 illustrates an example mobile device screen showing a graphic code entry interface with an image formation area.

[059] Figure 15 illustrates an example mobile device screen

Petition 870190026446, of 03/20/2019, p. 23/137

19/113 showing a graphic and numeric code entry interface with an image formation area.

[060] Figure 16 presents a system for biometric identification using root identification information, according to an exemplary modality.

[061] Figure 17 presents a method for authentication using a root identification system, according to an exemplary modality.

[062] Figure 18 presents a method of remote establishment of a biometric identity, according to an exemplary modality.

[063] Figure 19 shows a biometric authentication system using a block chain, according to an exemplary modality.

[064] Figure 20 is a schematic view of a mobile or computing device, such as one of the devices described above, according to an exemplary embodiment.

DETAILED DESCRIPTION OF MODALITIES [065] A system and method for providing secure and convenient face recognition authentication will be described below. The system and method can be achieved without the need for additional expensive biometric systems or readers while offering greater security over conventional facial recognition systems.

Facial Recognition Authentication Environment [066] Figure 1 illustrates an exemplary environment for using the facial recognition authentication system described in this document. This is a possible usage and system environment. It is contemplated that, after reading the specification provided below in connection with the Figures, a person ordinarily versed in the technique can reach different usage environments and configurations.

[067] In this environment, a user 108 can have a mobile device 112 that can be used to access one or more user accounts through

Petition 870190026446, of 03/20/2019, p. 24/137

11/203 authentication. A user 108 can have a mobile device 112 that can capture a photo of user 108, such as an image of the user's face. The user can use a camera 114 in or connected to the mobile device 112 to capture an image or multiple images or video of him / her. The mobile device 112 can comprise any type of mobile device capable of capturing an image, be it static or video, and perform image processing or communication over a network.

[068] In this mode, user 108 can load and hold mobile device 112 to capture the image. The user can also wear or hold any number of other devices. For example, the user can use a watch 130 containing one or more cameras 134 or biosensors arranged on the watch. Camera 134 can be configured to create an image of visible light as well as infrared light. Camera 134 may additionally or alternatively employ image intensification, active lighting or thermal vision to obtain images in dark environments.

[069] When pointed at a user 108, camera 134 can capture an image of the user's face. Camera 134 may be part of a module that may include communication capability that communicates with a mobile device 112, such as via Bluetooth®, NFC, or another format, or communication directly with a network 116 over a cable link or wireless 154. Watch 130 may include a screen on its face to allow the user to view information. If camera module 134 communicates with mobile device 112, mobile device 134 can transmit communications to network 116. Mobile device 134 can be configured with more than one front camera 114 to provide a 3D or stereoscopic view, or to obtain images in different spectral bands, such as visible light or near infrared.

[070] The mobile device 112 is configured to communicate without

Petition 870190026446, of 03/20/2019, p. 25/137

21/113 wire over a network 116 with a remote server 120. Server 120 can communicate with one or more databases 124. Network 116 can be any type of network capable of communicating with and from the mobile device , including, but not limited to, a LAN, WAN, PAN or the Internet. The mobile device 112 can communicate with the network via a cable or wireless connection, such as via Ethernet, Wi-Fi, NFC and the like. Server 120 can include any type of computing device capable of communicating with mobile device 112. Server 120 and mobile device 112 are configured with a processor and memory and are configured to execute machine or machine-readable code instructions stored in memory.

[071] Database 124, stored on the mobile device or remote location as shown, can contain facial biometric information and user authentication information 108 to identify users 108 to allow access to associated user data based on one or more images or biometric information received from the mobile device 112 or clock 134. The data can be, for example, information related to a user account or instruction to allow access to a separate account information server 120B. The term “biometric data” can include, among other information, biometric information regarding facial features and path parameters. Examples of route parameters may include acceleration and speed of the mobile device, angle of the mobile device during image capture, distance from the mobile device to the user, direction of travel in relation to the user's face position in relation to the user, or any another type of parameter associated with the movement of the mobile device or the user's face in relation to a camera. Other data can also be included, such as GPS data, device identification information, and the like.

[072] In this mode, server 120 processes requests for

Petition 870190026446, of 03/20/2019, p. 26/137

22/113 identification of the mobile device 112 or user 108. In one configuration, the image captured by the mobile device 112, using facial detection, comprises one or more images of the user's face 108 during the movement of the mobile device in relation to the user's face , such as in a tiled or horizontal line or arc, vertical line or arc, forwards and backwards from the user's face, or any other direction of movement. In another configuration, the mobile device 112 calculates biometric information from the images obtained, and sends the biometric information to the server 120. In yet another modality, the mobile device 112 compares the biometric information with the biometric information stored on the mobile device 112, and sends a comparison authentication result to server 120.

[073] Data including image (s), biometric information or both are sent over network 116 to server 120. Using image processing and image recognition algorithms, server 120 processes the person's biometric information, such as facial data, and compares biometric information with the biometric data stored in database 124 to determine the similarity of a match. In other embodiments, image processing and comparison are done on the mobile device 112, and the data sent to the server indicates a result of the comparison. In other embodiments, image processing and comparison are done on the mobile device 112 without accessing the server, for example, to gain access to the mobile device 112 itself.

[074] Using facial recognition processing, an accurate identity match can be established. Based on this and, optionally, on one or more other factors, access may be granted, or an unauthorized user may be rejected. Facial recognition processing is known in the art (or is an established process) and, as a result,

Petition 870190026446, of 03/20/2019, p. 27/137

11/23 is described in detail here.

[075] A second server 120B with a second associated database 124B is also shown, and a third server 120C with a third associated database 124C. The second and third databases can be provided to contain additional information that is not available on server 120 and database 124. For example, one of the additional servers can only be accessed based on user authentication 108 performed by server 120 .

[076] One or more software applications are executed on the 112 mobile device. This software is defined here as an identification app (ID App). The ID App can be configured with one or both of facial detection and facial recognition and one or more software modules that monitor path parameters and / or biometric data. Facial detection, as used here, refers to a process that detects a face in an image. Facial recognition, as used here, refers to a process that can analyze a face using an algorithm, map its facial features, and convert them into biometric data, such as numerical data. Biometric data can be compared with those derived from one or more different images for similarities or non-similarities. If a high percentage of similarity is found in the biometric data, the individual shown in the images can be considered a match.

[077] With the ultimate goal of combining a user's face with an identity or image stored in a database 124, to authenticate the user, the ID App can first process the image captured by camera 114, 134 to identify and locate the face that is in the image. As shown in Figure 1, it can be face 108. Authentication can be used to log in to an online account or for several other access control functions.

[078] The part of the photo that contains the detected face can then be cropped,

Petition 870190026446, of 03/20/2019, p. 28/137

24/113 removed and stored for processing by one or more facial recognition algorithms. When first detecting the face in the image and cutting only that part of the face, the facial recognition algorithm does not need to process the entire image. In addition, in modalities where facial recognition processing occurs remotely from the mobile device 112, such as on a server 120, it is necessary to send much less image data over the network to the remote location. It is contemplated that the entire image, a cut face or just biometric data can be sent to remote server 120 for processing.

[079] Facial detection software can detect a face from a variety of angles. However, facial recognition algorithms are more accurate in direct images in well-lit situations. In one embodiment, the highest quality facial image for captured facial recognition is processed first, then images of the face that are of inferior quality or at different angles from those that are straight towards the face are processed. Processing can take place on the mobile device or on a remote server that has access to large databases of image data or facial identification data.

[080] Facial detection occurs, preferably, on the mobile device and is performed by the software of the mobile device, such as the ID App. This reduces the number or size of the images (data) that are sent to the server for processing where the faces are not found and minimizes the total amount of data that must be sent over the network. This reduces bandwidth requirements, and network speed requirements are reduced.

[081] In another preferred mode, facial detection, facial recognition and biometric comparison all take place on the mobile device. However, it is contemplated that the facial recognition processing can take place on the mobile device, on the remote server or both.

Petition 870190026446, of 03/20/2019, p. 29/137

25/113 [082] Figure 2 illustrates an example of a mobile device. This is only a possible mobile device configuration and, therefore, it is contemplated that one skilled in the art can configure the mobile device differently. The mobile device 200 can comprise any type of mobile communication device capable of execution as described below. The mobile device may comprise a PDA, cell phone, smartphone, tablet, wireless electronic pad, an IoT device, a “wearable” electronic device or any other computing device.

[083] In this exemplary embodiment, the mobile device 200 is configured with an external compartment 204 configured to protect and contain the components described below. Inside compartment 204 is a processor 208 and a first and a second bus 212A, 212B (collectively 212). Processor 208 communicates via buses 212 with the other components of the mobile device 200. Processor 208 can comprise any type of processor or controller capable of functioning as described herein. Processor 208 may comprise a general purpose processor, ASIC, ARM, DSP, controller or any other type of processing device. Processor 208 and other elements of mobile device 200 receive power from a battery 220 or other power source. An electrical interface 224 provides one or more electrical ports for electrically interfacing with the mobile device, such as with a second electronic device, computer, medical device or an energy supply / charging device. Interface 224 can comprise any type of electrical interface or connector shape.

[084] One or more memories 210 are part of the mobile device 200 for storing machine-readable code to run on processor 208 and for storing data, such as image data, audio data, user data, medical data, data location, accelerometer data, or

Petition 870190026446, of 03/20/2019, p. 30/137

26/113 any other types of data. Memory 210 may comprise RAM, ROM, flash memory, optical memory or micro-drive memory. The machine-readable code, as described here, is non-transitory.

[085] As part of this modality, processor 208 connects to a user interface 216. User interface 216 can comprise any system or device configured to accept user input to control the mobile device. The 216 user interface can comprise one or more of the following: keyboard, roller ball, buttons, discs, pointer key, touch pad and touch screen. A touch screen controller 230 is also provided, which interfaces via bus 212 and connects to a display 228.

[086] The display comprises any type of display screen configured to display visual information to the user. The screen can include an LED, LCD, thin film transistor screen, OEL CSTN (color super twisted nematic), TFT (thin film transistor), TFD (thin film diode), OLED (organic light-emitting diode), AMOLED display (active matrix organic light-emitting diode), capacitive touch screen, resistive touch screen or any combination of these technologies. The display 228 receives signals from processor 208 and these signals are translated by the display into text and images as is understood in the art. The display 228 may further comprise a display processor (not shown) or controller that interfaces with the processor 208. The touch screen controller 230 may comprise a module configured to receive signals from a touch screen that is superimposed on the display 228 .

[087] Also part of this exemplary mobile device is a speaker 234 and a microphone 238. Speaker 234 and microphone 238 can be controlled by processor 208. Microphone 238 is configured to receive and convert audio signals into signals based on the control of processor 208. Likewise, processor 208 can activate speaker 234 to generate audio signals. These devices operate as is understood in the art and thus are not here

Petition 870190026446, of 03/20/2019, p. 31/137

27/113 described in detail.

[088] A first wireless transceiver 240 and a second wireless transceiver 244 are also connected to one or more of buses 212, each of which connects to respective antennas 248, 252. The first and second transceivers 240, 244 are configured to receive input signals from a remote transmitter and perform analog front-end processing on the signals to generate baseband analog signals. The input signal can also be processed by conversion to a digital format, such as an analog to digital converter, for subsequent processing by processor 208. Likewise, the first and second transceivers 240, 244 are configured to receive signals from output from processor 208 or another component of the mobile device 208, and convert those baseline signals to the RF frequency for transmission through the respective antenna 248, 252. Although it is shown with a first wireless transceiver 240 and a second transceiver without wire 244, it is contemplated that the mobile device 200 may have only one of these systems or two or more transceivers. For example, some devices have triple or quadruple band capability, or have Bluetooth®, NFC or other communication capabilities.

[089] It is contemplated that the mobile device and therefore the first wireless transceiver 240 and a second wireless transceiver 244 can be configured to operate in accordance with any wireless standards currently existing or developed in the future, including, but not limited to , Bluetooth, WI-FI, such as IEEE 802.11 a, b, g, n, wireless LAN, WMAN, fixed broadband access, WiMAX, any cellular technology including CDMA, GSM, EDGE, 3G, 4G, 5G, TDMA , AMPS, FRS, GMRS, citizen band radio, VHF, AM, FM and wireless USB.

[090] Also part of the mobile device are one or more systems connected to the second bus 212B, which also interface with the processor 208. These devices include a system module of

Petition 870190026446, of 03/20/2019, p. 32/137

28/113 global positioning (GPS) 260 with associated antenna 262. The GPS 260 module can receive and process signals from satellites or other transponders to generate location data in relation to the location, route direction and speed of the GPS 260 module. GPS is generally understood in the art and therefore will not be described in detail here. A gyroscope 264 connects to bus 212B to generate and provide guidance data in relation to the orientation of mobile device 204. A magnetometer 268 is provided to provide directional information to mobile device 204. An accelerometer 272 connects to bus 212B to provide information or data relating to shocks or forces experienced by the mobile device. In one configuration, accelerometer 272 and gyroscope 264 generate and provide data to processor 208 to indicate a movement path and orientation of the mobile device.

[091] One or more cameras (photo, video or both) 276 are provided to capture image data for storage in memory 210 and / or for possible transmission via a cable or wireless link or for later viewing. The one or more 276 cameras can be configured to detect an image using visible light and / or near infrared light. 276 cameras can also be configured to use image intensification, active lighting or thermal vision to obtain images in dark environments. Processor 208 can process image data to perform image recognition, such as in the case of facial detection, item detection, facial recognition, item recognition or bar / box code reading.

[092] A flasher and / or flashlight 280, as well as an LED light, are provided and are controllable by the processor. The 280 flasher or flashlight can serve as a traditional strobe or flashlight. The 280 flasher or flashlight can also be configured to emit near-infrared light. A 284 power management module interfaces with or monitors battery 220 to manage consumption

Petition 870190026446, of 03/20/2019, p. 33/137

29/113 power, control battery charging and supply power voltages to various devices that may require different power requirements.

[093] Figure 3 illustrates exemplary software modules that are part of the mobile device and the server. Other software modules can be provided to provide the functionality described below. It is expected that, for the functionality described here, there is compatible software (non-transitory machine-readable code, instructions or machine-executable code) configured to execute the functionality. The software would be stored in memory and executable by a processor.

[094] In this confirmation example, mobile device 304 includes a receiving module 320 and a transmission module 322. These software modules are configured to receive and transmit data to remote devices, such as cameras, glasses, servers, video towers. phone or WI-FI system, such as router or access points.

[095] Also part of the mobile device 304 is a location detection module 324 configured to determine the location of the mobile device, such as with triangulation or GPS. An account configuration module 326 is provided to establish, store and allow a user to adjust account settings. A 328 login module is also provided to allow a user to log in, such as with password protection, to the 304 mobile device. A 308 facial detection module is provided to run facial detection algorithms, while a 321 facial recognition module includes software code that recognizes a user's facial features, such as to create numeric values that represent one or more facial features (facial biometric information) unique to the user.

[096] An information display module 314 controls the display of information to the user of the mobile device. The display can take place on the

Petition 870190026446, of 03/20/2019, p. 34/137

11/30 mobile device or watch. A 316 user input / output module is configured to accept data and display data to the user. A local 318 interface is configured to interface with other local devices, such as using Bluetooth® or other communication with a shorter range, or cable links using connectors for connected cameras, batteries, data storage elements. All software (with associated hardware) shown on the 304 mobile device works to provide the functionality described here.

[097] The server software module 350 is also shown in Figure 3. These modules are located remotely to the mobile device, but can be located on any server or remote processing element. As is understood in the art, networks and network data use a distributed processing approach with multiple servers and databases operating together to provide a unified server. As a result, it is contemplated that the module shown in server block 350 may not be all located on the same server or the same physical location.

[098] As shown in Figure 3, server 350 includes a reception module 352 and a transmission module 354. These software modules are configured to receive and transmit data to remote devices, such as cameras, watches, glasses, servers, cell towers or WIFI systems, such as a router or access points.

[099] A 356 information display module controls an information display on the 350 server. A 358 user input / output module controls a user interface in connection with the local 360 interface module. Also located on the server side of the system is a facial recognition module 366 that is configured to process the image data from the mobile device. The facial recognition module 366 can process the image data to generate facial data (biometric information) and perform a

Petition 870190026446, of 03/20/2019, p. 35/137

11/31 comparison with other facial data to determine a facial match as part of an identification determination.

[0100] A 368 database interface allows communication with one or more databases that contain information used by the server modules. A location detection module 370 can use location data from mobile device 304 for processing and to increase accuracy. Likewise, an account configuration module 372 controls user accounts and can interface with the account configuration module 326 of the mobile device 304. A secondary server interface 374 is provided for interfacing and communicating with one or more other servers .

[0101] One or more databases or database interfaces are provided to facilitate communication and database searching. In this exemplary modality, the system includes an image database that contains images or image data for one or more people. This database interface 362 can be used to access users of image data as part of the identity matching process. Also included in this modality is a personal data database interface 376 and a privacy settings data module 364. These two modules 376, 364 work to establish the privacy setting for individuals and to access a database that can contain privacy settings.

Authentication System [0102] An authentication system with path parameters that is operable in the environment and system described above will now be described as shown in Figure 4. Figure 4 presents a method for performing facial recognition authentication with path parameters according with one embodiment of the invention. As will be described in more detail below, the system uses the mobile device 112 and server 120 resources defined above to generate a

Petition 870190026446, of 03/20/2019, p. 36/137

32/113 secure and convenient login system as an example of an authentication system. This reduces the user's burden of having to enter complex passwords on a small screen on a mobile device, prevents fraud through means such as key registration or screenshots, and increases security by combining various route parameters and / or device parameters that must be met before the user is authenticated.

[0103] In step 410, the system registers a user in the face recognition authentication system. In one embodiment, an authentication server, such as server 120 (Figure 1), can be configured to authenticate a user to allow access to the user account, such as a bank or other account, via the mobile device 112. The server Authentication 120 may be included as part of an institution or entity server that provides user accounts (hereinafter “account server”), or the authentication server may be provided separately. For example, in the environment shown in Figure 1, Servers 120B and 120C can represent account servers. In other embodiments, the account server and the authentication server are one in the same. In one embodiment, authentication server 120 can provide a user authentication application for installation on mobile device 112.

[0104] A registration process according to a modality will be described with reference to Figure 5. In this modality, a user, through a mobile device 112, establishes a connection between the mobile device 112 and the account server 120B in step 510 Just as an example, the user can establish a connection to a server of a financial institution, such as a bank, or that connection can occur later in the process after authentication. The user then provides typical login information to authenticate the user, such as a username and password for a financial account in step 512. In step 514, the user can receive a reminder on the mobile device 112 to

Petition 870190026446, of 03/20/2019, p. 37/137

33/113 register in the face recognition authentication system. The user then, through the user interface, indicates that he would like to configure the authentication system in response to the reminder.

[0105] Then, in step 516, the mobile device 112 can send device information to the authentication server 120. The device information can include, among other information, a device identifier that uniquely identifies the user's mobile device. Such information may include information about the device manufacturer, model number, serial number and mobile network. In step 518, when authentication server 120 is incorporated into account server 120B, authentication server 120 associates and stores device information with user account information. When authentication server 120 is separated from account server 120B, account server 120B can generate a unique identifier related to account information and send the unique identifier to authentication server 120. Authentication server 120 can associate information of the device and the unique identifier between them and can store the information in a database 124.

[0106] Next, the user is asked to provide a plurality of images of his face using a camera 114 on the mobile device 112 (hereinafter, “registration images”) in step 510. The registration images of the user's face are taken as the user holds the mobile device and moves the mobile device to different positions in relation to its head and face. Thus, the registration images of the user's face are taken from many different angles or positions. In addition, the mobile device's path parameters are monitored and recorded for future comparison in step 522. Some non-limiting examples of how a user can hold a mobile device and take a plurality of images of their face are shown in Figures 6A-7B .

Petition 870190026446, of 03/20/2019, p. 38/137

34/113 [0107] In Figure 6A and 6B, the user holds the mobile device 112 on one side of his face, and moves the mobile device 112 in an arc-like course horizontally around his face until the mobile device 112 be on the other side of your face. In Figures 7A and 7B, the user keeps the mobile device 112 away from his face and then brings the mobile device 112 closer to his face. Of course, any number of other paths can be used in addition to those shown in Figures 6A-7B. In addition, the user can move the head while the camera is kept fixed. The user can also hold the camera steadily and move his head in relation to the camera. This method, therefore, can be implemented with a webcam on a laptop or desktop or any other device, such as an IoT device in which a camera is mounted on a similarly stationary location or object.

[0108] The registration images can be obtained as follows. The user holds and guides a mobile device 112 with a camera 114 so that camera 114 is positioned to photograph the user's face. For example, the user can use a front camera 114 on a mobile device 112 with a display screen and can confirm on the display screen that his face is in a position to be photographed by camera 114.

[0109] Once the user has guided the device, the device can start to obtain the user's registration images. In one mode, the user can press a button on device 112, such as on a touch screen or another button on the device, to start obtaining the registration images. The user then moves the mobile device to different positions in relation to his head as the device photographs the user's face from a plurality of angles or positions, as described above. When the front camera mentioned above is used, the user can continuously confirm that his face is being photographed by viewing the image on the display screen. The user can press

Petition 870190026446, of 03/20/2019, p. 39/137

35/113 the button again to indicate that the imaging is complete. Alternatively, the user can hold the button during imaging and then release the button to indicate that imaging is complete.

[0110] As described above, the mobile device 112 may include facial detection. In this modality in step 524, the mobile device can detect the user's face in each of the registration images, cut the images to include only the user's face and send, through a network, the images to the authentication server 120. In step 526, upon receiving the registration images, the authentication server 120 performs facial recognition on the images to determine the biometric information (“registration biometrics”) for the user. The authentication server 120 can then associate the registration biometrics with the device information and the unique identifier (or account information) and store the biometric information in database 124 in step 528. For greater security, in step 530, the mobile device 112 and the authentication server 120 can be configured to delete the registration images after the user registration biometry is obtained.

[0111] In another embodiment, the mobile device 112 can send the images to the authentication server 120 without performing facial detection. Authentication server 120 can then perform facial detection, facial recognition and processing of biometric information. In another embodiment, the mobile device 112 can be configured to perform facial detection, facial recognition and biometric processing and then send the results or data resulting from the processing to the authentication server 120 to be associated with the unique identifier or account. user. This prevents sensitive personal data (images) from leaving the user's device. In yet another embodiment, the mobile device 112 can perform each of the steps mentioned above, and the mobile device 112 can store the registration information without sending any of the registration images or biometrics to the server.

Petition 870190026446, of 03/20/2019, p. 40/137

36/113 [0112] In one mode, the gyroscope, magnetometer and accelerometer of the mobile device are configured to generate and store data while the user moves the mobile device over his head to obtain the registration images (path parameters). The mobile device can process this data in step 532 to determine a path or arc in which the mobile device moved while the user was photographing his face (“registration movement”). Using data from the accelerometer, magnetometer and gyroscope, the system can check when a user is ready to start scanning their face, as well as determine the scan path. The data is used to determine when to start and stop the scan interval. The data can additionally include the time elapsed during the scan. This time can be measured from the moment the user presses the button to start and stop and image formation, or it can be measured from the time the button is pressed during image formation, or during more movement or to complete the scan.

[0113] The registration movement of the mobile device 112 (which is data that defined the movement of the mobile device during image capture) can be sent to authentication server 120. Authentication server 120 associates and stores the registration movement , registration biometrics, device information and unique identifier or account information. Alternatively, the data generated by the gyroscope, magnetometer and accelerometer can be sent to server 120, and server 120 can process the data to determine the registration movement.

[0114] Thus, in the modality described above, the registration information can then understand the device information, the registration biometrics and the registration movement (based on the movement of the mobile device 112).

[0115] Returning to Figure 4, once registration is complete, authentication server 120 can later receive credentials from a user trying to log in.

Petition 870190026446, of 03/20/2019, p. 41/137

37/113 authenticate to the system, as shown in step 420. For example, a user can try to log in to a user account. When a user tries to log in, instead of or in addition to providing typical account credentials, such as username and password, the user can again produce a series of images or videos of his face while the mobile device 112 is held in hand and moved to different positions in relation to the head (“authentication images”) in the same way as it was done during registration (as shown in Figures 6A-7B). In this way, the user can provide the necessary images (the term images includes video, since video is a succession of images) from many different angles and / or positions, and can provide parameters of the device's path while obtaining the images (“ authentication movement ”) to confirm both the identity of the user, as well as proof of the individual's life and reality to ensure that it is not a video, a screenshot or other representation of the person.

[0116] In a mode described in Figure 8, the user, through the mobile device 112, obtains several authentication images in step 810 while moving the mobile device 112 to different positions in relation to the user's head. Using facial detection in step 812, the mobile device 112 detects the user's face in each of the authentication images, cuts the images and sends the images to the authentication server 120. In another embodiment, the mobile device 112 sends the images for server 124, and server 124 performs facial detection. In step 814, authentication routing 120 can perform facial recognition on authentication images to obtain biometric information ("authentication biometrics"). In another embodiment, mobile device 112 performs facial recognition to obtain authentication biometrics and sends authentication biometrics to server 120.

[0117] In step 816, the mobile device 112 sends the device information identifying the device and sends route parameters, such as

Petition 870190026446, of 03/20/2019, p. 42/137

38/113 gyroscope, magnetometer and accelerometer information, defining the path of the mobile device obtained during the formation of images, as well as the time elapsed during the formation of images (“authentication movement”) for server 120. The credentials received by the authentication server 120 for a login in the facial recognition system can thus understand the device information, the authentication images or the authentication biometrics and the authentication movement (path parameters).

[0118] Returning to Figure 4, in step 430, the authentication server 120 verifies that the credentials received from the mobile device 112 correspond sufficiently to the information obtained during the registration. For example, as shown in step 910 in Figure 9, using algorithms to process the characteristics of the face and light hitting the face between the different images, the authentication server 120 can determine that the face in the authentication images is three-dimensional, that is, it is not a representation on a printed image or video screen. When the mobile device 120 sends only the authentication biometrics 120 to the server, the server 120 can validate the real or three-dimensional aspects of the user's image by comparing the biometric results of the different images.

[0119] In step 920, authentication server 120 can then compare the login credentials with the information stored from the registration process. In step 920, server 120 compares the device identification obtained during the login process with that stored during registration. In step 930, the authentication biometrics can be compared with the registration biometrics to determine whether it corresponds sufficiently with the registration biometrics. In step 940, the authentication movement can be compared with the registration movement to determine whether it corresponds sufficiently to the registration movement.

[0120] In some modalities, a copy of the registration information can be stored on the mobile device 112, and the mobile device 112 can

Petition 870190026446, of 03/20/2019, p. 43/137

39/113 verify that the credentials received on the mobile device 112 correspond sufficiently to the registration information. This would allow a user to protect documents, files or applications on the mobile device 112 itself, in addition to protecting the user account hosted on a remote device, such as authentication server 120, even when a connection to authentication server 120 might be temporarily unavailable, such as when a user does not have access to the Internet. In addition, this would allow the user to protect access to the 112 mobile device itself. Or the registration information can be stored on the server.

[0121] Thus, in step 950, if the authentication server 120 or the mobile device 112 determines that the registration information corresponds sufficiently to the received credentials, then the server or mobile device can verify that the identification of the user it is trying to make the login corresponds to the account owner. This avoids the user's cumbersome process of having to manually enter a complex password using the small screen of the mobile device. Many passwords today require capital letters, special characters, lower case letters and numbers.

[0122] The level of correspondence necessary to determine that the registration information corresponds sufficiently to the authentication information in the attempt to login can be defined in advance. For example, the match level can be a 99.9% match rate between registration biometrics and authentication biometrics and a 90% match rate between the registration move and the authentication move. The required level of correspondence can be static or elastic based on the established limits.

[0123] For example, the required level of matching can be based on GPS information from the mobile device 112. In one embodiment, the

Petition 870190026446, of 03/20/2019, p. 44/137

40/113 authentication 120 may require a 99.9% match rate as the match level when the GPS information on the mobile device matches the user's home location or other authorized location (s). On the other hand, if the GPS information shows that the device is in a foreign country far from the user's home, the authentication server may require a 99.99% match rate as the match level or may be denied entirely. Therefore, the necessary correspondence between pre-stored authentication data (registration information) and currently received authentication data (authentication information) is elastic, as the required percentage correspondence between images or path parameters can be changed depending on several factors, such as time of day, location, frequency of attempted login, date, or any other factor.

[0124] The required level of correspondence may additionally depend on the time. For example, if a second authentication attempt is made just after a first authentication attempt at a location far from the first authentication location based on the GPS information of the mobile device 112, the match limit level can be set higher. For example, a user cannot travel from Seattle to New York in an hour. Likewise, midnight login attempts at three in the morning can be a sign of fraud for some users based on users' usage patterns.

[0125] The level of correspondence between the registration information and the authentication information may be the result of the composition of the various parameters of the registration information and the authentication information. For example, when the button press time in the authentication information is within 5% of the registration information button press time, the button press time correspondence may constitute 20% of the overall correspondence. Likewise, when the trajectory

Petition 870190026446, of 03/20/2019, p. 45/137

41/113 of the movement path of the authentication information is within 10% of the registration information, the movement path of the movement can constitute 20% of the general correspondence. Other parameter matching rates, such as matching face size and facial recognition in authentication information compared to registration information, may constitute the remaining 10% and 50% of the overall level of correspondence. In this way, the overall total match level can be adjusted (the total of all parameters is greater than 75%, for example), or the match rate for individual parameters can be adjusted. For example, in a second login attempt, the threshold match rate for one parameter can be increased or the overall match level for all parameters can be increased. Limit match rates can also be adjusted based on the account being authenticated or other desired security levels.

[0126] Returning to Figure 4, in step 440, authentication server 120 can grant or deny access based on the verification in step 430. For example, if authentication server 120 verifies that the credentials match the registration information, then , server 120 can authenticate the user to allow access to the user's account. In the case where authentication server 120 is separate from account server 120B (such as a bank server), authentication server 120 can transmit the unique identifier to the account server, along with an indication that the identity of the user associated with the unique identifier has been verified. The 120B account server can then authorize the user's mobile device 112 to transmit and receive data from the 120B account server. Obviously, all of this can occur only on the account server 120B or on the mobile device 112 itself.

[0127] Alternatively, if the credentials provided by the user are not verified, the authentication server can transmit a message to display on the

Petition 870190026446, of 03/20/2019, p. 46/137

42/113 mobile device 112 screen, indicating that the login attempt failed. Authentication server 120 can then allow the user to try again to log in via the face recognition login system, or authentication server 120 can require the user to enter typical account credentials, such as a username and password.

[0128] In one mode, server 120 can allow three consecutive failed login attempts before requiring a username and password. If, in one of the attempts, the required level of correspondence is met, the user can be verified and access can be granted. According to one embodiment, authentication server 120 can retain information from each successive authentication attempt and combine data from multiple authentication attempts to obtain more accurate facial biometric information from the person attempting authentication. In addition, the level of correspondence can be increased with each successive authentication attempt. In addition, by averaging the route data (authentication movement) and / or image data (images / authentication biometrics) of various login attempts, the login data (registration information) is improved and improved.

[0129] Therefore, the authentication system described above allows authentication to a remote server 120 or to the mobile device 112 itself. This can be done as described above by the mobile device 112 by capturing the authentication credentials, and the authentication server 120 processing and analyzing credentials against registration information (cloud processing and analysis); mobile device 112 capturing authentication credentials and processing credentials, and authentication server 120 analyzing credentials against registration information (mobile device processing, cloud analysis); or the mobile device 112 capturing authentication credentials and processing and analyzing the

Petition 870190026446, of 03/20/2019, p. 47/137

43/113 credentials compared to registration information (mobile device processing and analysis).

Advantages and Characteristics of the Modalities [0130] The system described above provides several advantages. As an advantage, the face recognition authentication system provides a secure login. For example, if during a login attempt, the camera on the mobile device photographed a digital screen showing a person turning his head while the phone was not moving, the accelerometer, magnetometer and gyroscope data would not detect any movement. Thus, the registration movement and the authentication movement would not correspond, and the login attempt would be denied.

[0131] In addition, as a plurality of images is used as registration images and authentication images, histograms or other photo manipulation techniques can be used to determine whether a digital screen is present in place of a human face in the images. For example, the system can check for changes in light frequency in captured images, or bands in an image that indicate that an electronic viewfinder generated the image, backlight, suspicious changes in lighting, or other analysis of the images by comparing the images to determine that the actual active user is actually alive, present and requesting authorization to log in.

[0132] As yet another advantage, as explained above, not only must the registration biometry correspond sufficiently to the authentication biometry, but also the registration movement must correspond to the authentication movement, and the device information must match the information of the registration device. For example, an application can be downloaded on a mobile device that has a digital camera. The application can be a login application or it can be an application of a financial institution or other entity with which the user has an account. The user can then log in to the application

Petition 870190026446, of 03/20/2019, p. 48/137

44/113 using a typical login credential, such as a website username and password. In addition, the user can have a device code to log into another device, or he can use the camera to scan the QR code or another code to pair the device with his user account.

[0133] The user then holds the mobile device to move the mobile phone to different positions in relation to his head, while keeping his face visible to the camera as he moves. As the mobile device moves, the camera obtains face registration images. During imaging, the speed and angle of movement of the current user's mobile device are measured using the accelerometer, magnetometer and gyroscope to generate the registration movement. The formation of continuous images and the detection of the face throughout the process have been shown to prevent fraud. This is because a fraud attempt cannot be made by rotating the images forward and out of the front of the camera.

[0134] For example, a user can initiate movement from right to left or from left to right, as shown in Figures 6A and 6B. The movement can also be in the front and rear direction, as shown in Figures 7A and 7B. Any other movement can be used, such as starting at the center, then going to the right and then returning to the center. Vertical and diagonal movements can also be used to further increase the complexity of the registration movement. When the user tries to log in later, the user must repeat the movement pattern in the authentication movement to match the registration movement, in addition to matching device information and biometric data. Thus, system security is greatly improved.

[0135] The system therefore provides enhanced security to authenticate a user who has a mobile device. As explained above, the system can use

Petition 870190026446, of 03/20/2019, p. 49/137

45/113 at least one or more of the following in any number of combinations to securely authenticate the user: physical device verification, mobile network verification, facial recognition including face size in the image, one face detected in each frame during motion, accelerometer information, gyroscope information, magnetometer information, pixels per square inch, color bits per pixel, type of image, code or pattern entered by the user and GPS information.

[0136] As another advantage, the facial recognition login system provides a convenient way for a user to log into an account with a mobile device. For example, once registered, a user does not need to enter a username and password on the small mobile device whenever the user wants to access the account. Instead, the user simply needs to photograph themselves while imitating the registration movement with the mobile device. This is especially beneficial with smaller mobile devices, such as cell phones, smart watches and the like.

[0137] The system can also be configured to allow a user to log in securely on multiple devices or to allow users to share devices securely. In one embodiment, the registration information can be stored on an authentication server (or in the “cloud”) and, therefore, is not associated only with the user's original device. This allows the user to use any number of suitable devices to authenticate to the authentication server. In this way, a user can use a friend's phone (third-party device) or another device to access their information, such as account information, calendar information, email or other messages, etc. performing the authentication operation on any device.

[0138] For example, the user can provide an email address, username code or similar identifier on the friend's phone, so that

Petition 870190026446, of 03/20/2019, p. 50/137

46/113 the authentication server compares the login information with the user account registration information. This would tell the authentication server which authentication profile to use, but without allowing access to user data, accounts or tasks. When you log out of the friend's phone, access to user information on the friend's phone is terminated. The feature provides the benefit of allowing a user to securely access the account or other information or tasks accessible by authentication using any device without having to enter the user's password on the third party device, where it could be logged in or copied. In a sense, the user is the password.

[0139] Through cloud-based registration information, a single user can also transfer data securely between authenticated devices. In one embodiment, a user can own a first device, such as a mobile phone, and be authenticated on the first device through the authentication system. The user can then purchase a new device, such as a new phone, tablet or other device. Using the cloud-based authentication system, the user can authenticate to the new device and transfer data from the first device to the new device. Data transfer can be completed via the Internet, a LAN connection, a Bluetooth connection, a wired connection or near field communication. The authentication process can also be part of a security check to resend or restore a system after the phone is lost or stolen. Thus, the authentication system can be used to activate or authenticate a new device, with the authentication used to verify the user of the new device.

[0140] Likewise, the system can facilitate secure access to a single device shared by several people to control content or other resources on the device. In many cases, passwords can be viewed, copied, guessed or detected, particularly when a device is

Petition 870190026446, of 03/20/2019, p. 51/137

47/113 shared by several users. Users can be, for example, family members, including parents and children, co-workers or have other relationships, such as students. The authentication system can allow each member of the family to log in based on their own unique registration information associated with a user account.

[0141] The device can restrict access to certain content or resources from one or more user accounts, such as children's user accounts, allowing access to content and resources for other people, such as parents' accounts. When using the authentication system for the shared device, child users cannot use a password to try to gain access to restricted content, because the authentication system requires the presence of the person responsible for authentication, as explained above. Thus, sharing devices between users with different privileges is more secure and improved. Likewise, in a classroom environment, a single device can be safely shared among multiple people for tests, research and grade reports.

Adaptations and Modifications [0142] Various modifications can be made to the above system and method without departing from the scope of the invention. For example, images can be processed by a facial recognition algorithm on the device and can also be converted to biometric data on the device, which are then compared with the biometric data created previously for an authorized user. Alternatively, images from a device can be sent over a wired or wireless network, where facial recognition algorithms running on a separate server can process the images, create biometric data and compare that data with the previously stored data assigned to that device.

Multiple Profiles for a Single User

Petition 870190026446, of 03/20/2019, p. 52/137

48/113 [0143] In addition, the photo registration process can be done multiple times for a user to create multiple user profiles. For example, the user can register with profiles with and without glasses, with and without other portable devices, in different lighting conditions, wearing hats, with different hair styles, with or without facial or ear jewelry, or making different faces and unique, such as closed eyes, blinking or speaking out to establish another level of exclusivity for each user profile. These “faces” made by the user will not be available on the user's Social Media Pages and therefore will not be available for copying, manipulation and use during a fraud attempt. Each set of registration images, registration biometrics or both can be saved together with the separate registration movement. In one mode, at least three images are captured when the mobile device completes the route. Contemplate that any number of images can be captured.

Linking Registration Information [0144] It is also contemplated that the registration process may be linked to an e-mail address, telephone number or other identifier. For example, a user can sign up with an email address, fill in one or more entries as described above, and confirm entries via the same email address. The e-mail address can then further increase the security of the system. For example, if a user unsuccessfully tries to log in through the authentication system a predetermined number of times, such as three times, for example, then the authentication system locks the account and sends an email to the email address -mail informing the user of unsuccessful login attempts. The email may also include one or more photos of the person who was unable to log in and GPS data or other data from the login attempt. The user can then confirm that this was a valid login attempt and reset the system, or the user can report the login attempt as fraudulent. If a

Petition 870190026446, of 03/20/2019, p. 53/137

49/113 fraudulent login or if there are many blocks, the system can delete the account associated with the email address to protect the user's security. Thus, future fraudulent attempts would not be possible.

Return Meters [0145] To make imaging even easier, the mobile device can include several return meters, such as a motion meter or precision meter, as shown in Figure 10. In one embodiment, the 1012 mobile device it can display a 1024 motion meter that indicates the amount of movement the mobile device 1012 does as the user moves the mobile device 1012 to different positions in relation to his head. For example, the 1024 motion meter can be represented as a line that slides from one side of the screen. In this way, the registration process may require a certain movement limit of the device to register a user with the multidimensional authentication system. For example, the system may require the 1012 mobile device to be moved in an arc or straight line and rotated at least 45 degrees to create the registration information. In another example, the system may require an acceleration of the device exceeding a threshold value. The motion meter can also assist the user in learning how to photograph themselves using the authentication system.

[0146] The 1012 mobile device can also display a 1026 precision meter or any other visual representation of authenticated frames to assist the user in authenticating using the authentication system and learning how to improve authentication. The precision meter 1026 can show the user a match rate (graphical, alpha or numeric) of a predetermined number of images obtained during the authentication process. The precision meter can be represented on the display in several ways, including numerical percentages, color representation, graphs and the like. A combination of representations

Petition 870190026446, of 03/20/2019, p. 54/137

50/113 can also be used.

[0147] For example, as shown in Figure 10, the match rates for a predetermined number of images obtained during authentication are represented on the precision meter. In the modality shown in Figure 10, each image can be represented by a column in a graph and the precision can be shown for each image in each column. For example, the column with a larger bar represents greater precision, and a column with a smaller bar represents less precision. In addition to the match rates for images, match rates for the route parameter can also be displayed. Over time, the user can improve.

[0148] In another modality, each image can be represented in a table as a color that corresponds to the correspondence rate. Dark green may represent a very high match rate, light green may represent a good match rate, yellow may represent a satisfactory match rate, red may represent a mediocre match rate, and gray may represent a low match rate. Other color schemes can also be used.

[0149] The height of the bars or the colors used can correspond to predetermined match rates. For example, a full or dark green bar can have a match rate greater than 99.9%, a three-quarter or light green bar can have a match rate between 90% and 99.9%, half a bar or yellow can have a match rate of 50-90%, red can have a match rate of 20% -50% and a single-quarter or gray bar can have a match rate of 0-20%. A pie chart, line graph or any other type of representation can also be used or any other numeric or graphical display. An overall score can be displayed or a score per image.

Petition 870190026446, of 03/20/2019, p. 55/137

51/113 [0150] The accuracy meter can also include a 1028 message indicating an overall match score. For example, the accuracy meter can indicate an overall average match score or the number of images that have reached a 99.9% match rate and display the message to a user. With the 1024 motion meter and the 1026 precision meter as described above, the user can quickly learn to use the authentication system due to the feedback presented by the 1024, 1026 meters.

Gamification and Rewards [0151] The 1024, 1026 motion and precision meters can also be configured to incorporate game features, aspects or techniques into the authentication system to encourage a user to try to get the best match possible (such as a high or high score percentage of frames), increasing the user's ability to use the authentication system. This also creates user adoption rates for the technology.

[0152] For example, the user can compete with themselves to imitate or improve previous authentication scores to encourage or train the user to achieve a high score. Other modifications to the authentication meter can also be incorporated, such as the ability to share precision match results with others to demonstrate the ability to use the system or compete with others. In other cases, the user may receive a reward, such as a gift or coupon, for highly accurate scores. While this may slightly increase costs, the reduction in loss from fraud would far outweigh the additional cost.

[0153] Other game techniques can be incorporated into the authentication system to encourage users to take actions that prevent unauthorized or fraudulent authentication. In one embodiment, the authentication system can

Petition 870190026446, of 03/20/2019, p. 56/137

52/113 reward users who engage in fraud prevention activities. One of these activities is the use of the facial recognition authentication system described here. For example, based on the accuracy meter described above, the system can reward a user who is successfully authenticated to the system above a certain match rate. The system can award reward points, cash or other prizes based on successful authentication or a predetermined number of successful authentications. When reward points are used, points can be discounted for predetermined prizes.

[0154] Other gaming features may involve reward levels for users who gain a predetermined amount of experience using the authentication feature. For example, different reward levels can be based on users being successfully authenticated 100 times, 500 times, 1000 times etc. Since each case of loss due to fraud can be significant and harm the clientele of the company or organization, the benefits for fraud prevention are significant.

[0155] In one modality, the user can be notified that he or she has reached various levels of competence, such as a “silver level” upon reaching 100 successful authentications, a “gold level” upon reaching 500 successful authentications, or a “Platinum level” when reaching 1000 successful authentications. An amount of points awarded for each authentication above a certain match rate can increase based on the level of user experience. Of course, the names of the levels and the number of authentications for each level, as described above, are only exemplary and may vary as desired.

[0156] In one mode, authentication only counts for reward levels when the deal is transacted on the website, while in others

Petition 870190026446, of 03/20/2019, p. 57/137

53/113 modalities, repeated attempts can be made, all of which count towards rewards. Another feature may incorporate a classification framework in which a user can be notified of a user's classification, comparing his proficiency or willingness to use the authentication system with other users.

[0157] The successful use of the authentication system benefits companies and organizations that use the system by reducing costs for fraudulent activities and the costs of preventing fraudulent activities. These cost savings can be used to fund the gaming resources described above in the authentication system.

[0158] Other activities that correspond to the authentication system and contribute to the reduction of fraud can also be incorporated to allow a user to earn points or receive prizes. Such activities may include the creation, by the user, of a sufficiently long and strong password that uses a certain number and a combination of characters. This encourages and rewards users to set passwords that are not easily compromised. Other examples may include rewarding users for taking time to perform verification steps in addition to an initial authentication, such as cell phone verification or authentication email, answering one or more personal questions, or other secondary checks known or developed later. This rewards users for spending time and the inconvenience to reduce the risk of fraud for a company or organization.

[0159] As another example, if the authentication service is used to access websites or applications that provide affiliate programs, then the prize or gift can be subsidized by affiliate commissions on purchases made on those sites. For example, if a commerce site (product or service) uses the method and device disclosed here to prevent fraud and thereby increase profits, then a percentage of each purchase made by a user using the service

Petition 870190026446, of 03/20/2019, p. 58/137

54/113 authentication will be provided to the authentication service. By reducing fraud, consumer purchases are more likely and additional users will be willing to enter financial and personal information. A link, code or reference source or affiliate identifier can be used to credit the authentication system with directing the consumer to the commerce site (product or service).

Multiple Account Login [0160] It is also contemplated that the authentication system can be configured to allow a user to access several different websites using a single authentication. As the authentication process and result are unique to the user, the user can first designate which participating sites the user chooses to log in to and, after selecting which one or more sites to log in to, the user performs the authentication described here . If secure authentication is successful, the user will be connected to the selected sites. In this way, the authentication process is a universal access control for several different sites and prevents the user from having to remember several different usernames and passwords, in addition to reducing fraud and password overhead for each user.

Automatic Image Start / Stop [0161] It is also contemplated that the system can be configured to have the video camera running on the phone. The mobile device would capture frames and path parameter data when the phone moved (using the camera, gyroscope, magnetometer and accelerometer), but would only process biometric data on the device or send the frames to the server if they had a face on them. In this mode, the application running on the mobile device can trigger the software application to start saving frames when the phone is in motion and then, if the phone continues to move in the correct path (a semicircle, for example) and the system detects a face in the frame, the mobile device would start sending images, part of the image or biometric data to the server

Petition 870190026446, of 03/20/2019, p. 59/137

55/113 for processing. When the system detects movement, it can trigger image capture at certain intervals. The application can then process the frames to determine whether the images contain a face. If the images include a face, then the application will cut it and then check whether the movement path of the mobile device is similar to that used during registration. If the movement path is similar enough, the application can send the frames, one at a time, to the server to be checked or processed, as described above.

Edge and Band Detection [0162] When a fraudulent attempt is made using a display screen, such as LED, LCD or other screen, the system can detect the fraudulent login attempt based on the expected attributes of the screen. In one mode, the authentication system will perform checks for tracks produced by digital screens. When tracks are detected, the system can recognize a fraudulent login attempt. In another mode, the system will perform checks to detect the edges of digital screens. As the mobile device is moved to obtain the authentication movement during a login attempt, the system checks the captured images so that the edges of a screen recognize a fraudulent login attempt. The system can also check other image artifacts resulting from a screen, such as the detection of reflections. Any algorithm known or further developed to detect bands and edges of the screen can be used. After fraud detection, it will prevent authentication and access to the website or prevent transaction or account access.

Estimation of Other Attributes [0163] The authentication system can also conduct an analysis on the registration images to estimate at least one of gender, approximate age and ethnicity. In an alternative mode, the user can manually enter one or more

Petition 870190026446, of 03/20/2019, p. 60/137

56/113 more of your gender, an approximate age and an ethnicity, or this information can be captured or obtained from existing records that are known to be accurate. The authentication system can then store a user's estimated gender, age and ethnicity as registration credentials or user data. Thus, when the user tries to authenticate later on the system, the system will compare gender, age and ethnicity derived from the authentication images (using biometric analysis to determine such data or estimates based on processing) with gender, age, and ethnicity to determine whether to authenticate the user. For example, if the derived data for gender, age and ethnicity matches the stored registration credentials, authentication will be successful or that aspect of authentication will be successful.

[0164] The authentication system can make estimates of gender, age and ethnicity based on a single image during the authentication process or based on multiple images. For example, the authentication system can use an image of the plurality of images that has an ideal viewing angle of the user's face for analysis. In other modalities, a different image can be used for each analysis of age, gender and ethnicity, when different images reveal the best data for the analysis. Authentication can also estimate gender, age and ethnicity in a plurality of images and average the results to obtain overall scores for a gender, age and ethnicity.

[0165] As an alternative to obtaining gender, age and ethnicity as registration information, estimates of gender, age and ethnicity as authentication credentials can be defined over a course of repeated use of the authentication system. For example, if, in successful previous authentications using biometric and motion information, the authentication system always estimates that a user's age is between 40 and 50, authentication can define credentials for that user that require later login information to

Petition 870190026446, of 03/20/2019, p. 61/137

57/113 include images of a face estimated to be between 40 and 50 years old. Alternatively, gender, age and ethnicity estimates can be implemented as one of the many factors that contribute to an overall authentication score to determine whether or not to authenticate a user.

[0166] For example, if the authentication process has a gender estimate of + or - 0.2 with a male rating of 1.9, then if the actual results are not within this range, the system may deny access to the user . Likewise, if the user's age range is always between 40 and 50 years old during previous authentication or registration attempts, and an authentication attempt is outside that range, the system may deny access or use the result as a compositional factor. to deny access.

[0167] In an additional modality, when a bracelet or watch capable of obtaining an EKG signature is used, a certain EKG signature may be required at login. The EKG signature can also be paired with face recognition rotation to provide multi-stage login for critical security and identification applications. In addition, credentials may also include GPS information, where login is only allowed in certain geographic locations, as defined during registration. In a configuration, the GPS coordinates of the mobile device are recorded and recorded for an actual login or login attempt. This is additional information about the user's location. For example, if the GPS coordinates are in a foreign country known for fraud, then the attempt would likely be fraudulent, but if the GPS coordinate indicates that the attempt or login was made at the user's home, there is less likely to be fraud. In addition, some applications can only allow a user to log in when they are in a specific location, such as a secure government facility or hospital.

[0168] Registration information may also include information on

Petition 870190026446, of 03/20/2019, p. 62/137

58/113 distance. Since the range of motion (speed, angle, duration ...) is unique to each user, the facial detection software on the device can process the images and determine whether the device is too close or too far from the individual. Or, in other words, the registration information may consider the size of the face in the images. Thus, potential registration information may also vary based on the length of the user's arm, the size of the head and face and the optics of the camera on the user's specific mobile device. The user can also be positioned on a computer or fixed camera, such as a laptop, desktop or ATM. The user can then move the face back and forth, from side to side or up and down (or a combination) to create the images. Therefore, this method of operation is not limited to a mobile device. In one embodiment, the camera is arranged in a car, such as in a mirror, and the person moves his head or face for authentication.

Access by Gradual Authentication [0169] In one mode, the system is defined to limit what the user can do when enrolled and authenticated for the first time. Then, after further authentications or after a predetermined period of time and a number of authentications, additional resources can be granted. For example, during the first 20 authentications during the first 3 months, a maximum transaction of $ 100 may be allowed. This creates a database of known authentication data related to unobjected transactions by the user. Then, during the next 20 authentications, a transaction limit of $ 3000 can be set. This limits total loss in the event of fraud when authentication data is limited and the user is new to the system. For example, if an unauthorized user is able to fraudulently register with the authentication system.

Video Display for Image Formation

Petition 870190026446, of 03/20/2019, p. 63/137

59/113 [0170] When the user photographs himself using a front camera, the user can confirm that his face is being photographed by viewing the image in the viewfinder, as described above. The image shown on the display can be configured to have a smaller area than the entire display, and can be positioned at the top of the display towards the top of the device. When the user's image is displayed only at the top of the user's display screen, the user's eyes tend to look more closely at the front camera. When the user's eyes are approaching, the accuracy of facial recognition can be improved. In addition, tracking eye movement from one frame to another can allow the system to confirm that the images are of a living person and not a photograph or video recording of the person.

[0171] The image shown on the display can also be positioned to match the location of a camera on the user's device, as shown in Figures 11A-11C. The mobile devices currently available may include front-facing cameras arranged in several different positions. For example, a mobile device 1112a, 1112b may have a front camera 1114a, 1114b that is arranged above the viewfinder and decentralized to one side or the other, as shown in Figures 11A and 11B. Consequently, the user's return image 1116a, 1116b shown on the display can be positioned to match the location of camera 1114a, 1114b, as shown. In Figure 11A, when a camera 1114a is above the viewfinder and is off center in a position to the left of the center, then the image 1116a can be shown in an upper left corner of the viewfinder. In Figure 11B, when a camera 1114b is above the viewfinder and is off center in a position to the right of the center, then the 1116b image can be shown in an upper right corner of the viewfinder. As shown in Figure 11C, a mobile device 1112c can have a camera 1114c that is centrally arranged directly above the viewfinder. There, the 1116c image can be displayed

Petition 870190026446, of 03/20/2019, p. 64/137

60/113 centered at the top of the display. In this way, the user's eyes are directed close and / or follow as close as possible to the camera, assisting in eye tracking and movement verification. The user can also better see the feedback image and other comments or information on the screen, while moving the mobile device.

[0172] The image displayed on the display by the user can still be modified in such a way that the border pixels on the sides are horizontally extended as shown in Figure 12. That is, a predetermined area 1206, 1208 on the right and left sides is deformed to extend to the right and left edges, respectively, of the screen. This allows a larger vertical portion of the displayed image to be shown on the display. Simultaneously, this trains the user to use the system correctly, keeping the face in the center of the screen, as his face is deformed on the screen if it is decentralized and part of the face enters one of the deformed areas.

Authentication in Low Light Environments [0173] To facilitate the creation of images, the screen of the mobile device can be additionally displayed with a white background, and the brightness of the screen can be increased to illuminate the user's face in a dark environment. For example, a portion of the display may provide video feedback for the user to ensure that he or she is photographing himself, while the remaining portion of the display is configured to display a bright white color. Referring to the example shown in Figure 11C, this can be done by showing the video feedback 1116c in the center of the display, with the surrounding areas being displayed as bright white bars around the video feedback 1116c. In very dark situations, an LED flash can be used on the back of the mobile device and the rear camera. Alternatively, the camera can be configured to create an image using infrared light or other night vision techniques.

[0174] When infrared imaging is used as

Petition 870190026446, of 03/20/2019, p. 65/137

61/113 thermal image, other security improvements are possible. In particular, the thermal image can be analyzed to indicate whether the images obtained are from a real user or if they are fraudulent images from a screen or other device. When a person is in front of an infrared thermal imaging camera, the heat radiation detected must have a very oval shape, designating the person's head. In contrast, the heat that radiates from a screen is typically rectangular. In addition, the heat patterns detected on the face of the real person, as well as the movement of the heat patterns in the images, can be compared to the heat patterns expected from a human face to distinguish the images from fraudulent authorization attempts using a screen.

Mobile Device Detection Output [0175] The display or other light source on the mobile device can also be used to provide additional security measures. During the authentication process described above, the light from the display or other light source is projected onto the user's face and eyes. This projected light can then be detected by the camera of the mobile device during imaging. For example, the color tone detected on the skin or a reflection of the light from the cornea of a user's eye can be picked up by the camera on the mobile phone. Because of this, random light patterns, colors and designs can be used to provide additional security and ensure that there is a person alive trying to authenticate and not just a picture or video of a person being photographed by a fraudster.

[0176] As an example, when a user initiates authentication, the authentication server can generate and send instructions to the user's device to display a random sequence of colors at random intervals. The authentication server stores the randomly generated string for later comparison with the authentication information received from the mobile device. During the formation of authentication images, the colors displayed by the device are projected on the face

Petition 870190026446, of 03/20/2019, p. 66/137

62/113 of the user and reflected in the user's eyes (the cornea of the eyes) or any other surface that receives and reflects the light from the screen. The camera on the user's mobile device detects the colors reflected in the user's skin or eyes (or other surface) and generates color data indicating the colors detected based on the projection of the screen. This data can be returned to the authentication server to determine whether the sequence or color pattern sent to the mobile device matches that known pattern or sequence projected by the user's device screen. Based on this comparison on the authentication server, authentication is authorized or denied. The comparison with the random color sequence in the instructions may alternatively occur exclusively on the user's device to determine whether an active user is being authenticated.

[0177] As another example, when a user begins authentication, the authentication server can send instructions to the user's device to display a randomly generated pattern that is then stored on the authentication server. This pattern can include graphics, text, lines or bars, flashing light patterns, colors, a QR code or the like. The randomly generated pattern is displayed during the formation of authentication images and the pattern is reflected in the user's eyes (cornea). The user device's camera detects the pattern reflected in the user's eye and processes the mirror image reflected from the displayed pattern. The processed pattern (such as converted to a numeric value) is transmitted to the authentication server and compared to the pattern that was randomly generated and stored on the authentication server to verify that the pattern displayed on the screen and created after reflection on the user's face establishes a pattern match.

[0178] If a match occurs, it establishes or increases the likelihood that a living person is being photographed by the device. If the pattern is not a match or does not meet a threshold level

Petition 870190026446, of 03/20/2019, p. 67/137

63/113 correspondence, the authentication process may fail (access denied) or access to the account or the transaction amount may be limited. Note that this example can also be incorporated into the desktop computer with a webcam that does not incorporate the registration movement and the authentication movement described above. In addition, this example can not only be incorporated with facial recognition, but can also serve as an additional layer of security for iris recognition or any other type of ocular blood vessel recognition, or any facial feature that is unique to a user .

[0179] When the above example is implemented on a desktop computer, eye tracking can also be used to further demonstrate the presence of a live user. For example, the screen may show a ball or other random object or symbol moving in a random pattern that the user observes with his or her eyes. The camera can detect this movement in real time to verify that the user is alive, and is not an image or display, and to verify that the movements of the eye or head match and coincide with the expected movement of the object or words on the screen, which are known to the authentication system. Eye tracking can also be done by establishing an anchor point, such as by clicking the mouse at a location on the screen (if the user is looking at the location where the mouse click occurs) and then estimating for where the user is looking on the screen in relation to the anchoring position.

[0180] The use of a moving object on the screen can also be beneficial when registering on a mobile or stationary device. For example, when capturing registration images, the device can display a moving digital object (such as a circle or word (s)) that moves across the screen so that the user is encouraged to follow it with his head and with the eyes. This movement can be

Petition 870190026446, of 03/20/2019, p. 68/137

64/113 user's device or the device can be configured to instruct the user to follow the object. This results in movement of the head and / or eyes, creating small changes in the orientation of the user's head and face with the device's camera, providing more complete registration information. With more complete registration information, the system can better ensure that the user is authenticated later, even at slightly different angles, during future authentication attempts.

Intuitive User Training and Enhanced Security by "Zoom" [0181] In one mode, the system is configured to assist the user in easily learning how to authenticate with the system. As shown in Figure 13A, once registration or authentication has started, as described above, the system causes the user's mobile device 1310 to display a small oval 1320 on screen 1315 while the mobile device 1310 is photographing the user. Instructions 1325 displayed on screen 1315 instruct the user to hold the 1310 mobile device so that their face or head appears on the 1320 oval. Since the 1320 oval is small, the user is required to keep the 1310 mobile device away from his body, for example, stretching your arm while holding your 1310 mobile device. The maximum arm length and face size are unique to the user. In another embodiment, the arm may not be fully extended to accommodate operation when space is not available, such as in an automobile or in a crowded location. Note that while the small oval 1320 is shown centered on the display, it can be positioned anywhere on the 1315 screen.

[0182] Then, as shown in Figure 13B, the system causes the user's mobile device 1310 to display a larger oval 1330 on the display 1315. The display 1315 can also show corresponding instructions 1335 directing the user to “magnify” his face to fill the 1330 oval with your face. The user does this by bringing the 1310 mobile device closer to his face in a generally straight line with

Petition 870190026446, of 03/20/2019, p. 69/137

65/113 the user's face (as shown in Figures 7A and 7B) until the user's face fills the 1330 oval or exceeds the oval. In other embodiments, the large oval 1330 may simply be a request for the user to bring the mobile device 1310 closer to their face.

[0183] Thus, the system provides and teaches the user a simple method to provide registration and authentication images together with the registration and authentication movement, as explained above. The system can also teach variable registration and authentication movement by varying the location of the small oval 1320 on screen 1315, and changing the order and size of the displayed ovals. For example, the user can zoom in / out, then take out, then zoom out completely by moving the mobile device. The system can be configured to monitor whether the camera's zoom function (when equipped) is not in use, which normally requires the user to touch the screen.

[0184] In one mode, the registration movement can be omitted, and the authentication movement can be compared to the expected movement based on the on-screen reminders. For example, the device or the authentication server generates a series of ovals of different sizes within which the user must position his face by moving the mobile device contained in the user's hand. In this way, the authentication movement can be different during each login, depending on the order, size and placement of the ovals shown on the screen.

[0185] The system can also incorporate other security features when the “zoom” movement is used as shown in Figures 13A and 13B. Typical cameras on a mobile device or any other device include a curved lens. This results in a barrel-type distortion effect on the resulting images obtained by the camera. In some cases, this curvature may not be visible to the human eye or can be noticed only at certain focal lengths. Barrel curvature or distortion effect can vary with focal length or

Petition 870190026446, of 03/20/2019, p. 70/137

66/113 the distance between the user and the lens. The degree of the barrel-type distortion effect is therefore dependent on the type of optics used in the camera lens and other factors.

[0186] The barrel-type distortion effect becomes more pronounced in an image of a person's face when the person photographs their face close to the lens. The effect makes the relative dimensions of the person's face look different than when the image is taken with the person's face farthest from the lens. For example, a person's nose may appear up to 30% wider and 15% higher than a person's face when the image is taken in close proximity when compared to when the image is taken from a distance. Differences in relative dimensions are caused by the relatively greater differences between the camera and the various facial features when the person is photographed close to the lens compared to relatively equal distances when the person is photographed at a distance further from the lens.

[0187] These differences were found to be significant in many facial recognition algorithms. That is, a facial recognition algorithm may not recognize a living person photographed from near and far as the same person. In contrast, if a two-dimensional photograph of a person is taken by the camera from both near and far, the relative focal lengths between the lens and the two-dimensional image do not change as significantly. Thus, a facial recognition algorithm would recognize two-dimensional photography as the same person when photographed up close and at distances further from the lens.

[0188] This effect can be used to increase the security of the authentication system. For example, during registration, registration images can be provided by the user both near and far from the lens, in addition to other positions during movement. Later, during authentication, authentication images can be obtained at distances near and away from the lens to determine whether they match the registration information obtained from the images.

Petition 870190026446, of 03/20/2019, p. 71/137

67/113 of registration. In addition, as the barrel-type distortion effect is expected when a real three-dimensional person is present, an absence of the relative change in the dimensions of facial features alerts the system to a fraudulent authentication attempt. This effect cannot be easily recreated with a two-dimensional image (photograph or printed screen) and, therefore, this step can serve as a safe test to prevent a two-dimensional image (instead of a live face) being used for authentication.

[0189] In other words, using this “zoom” movement on the user's face, two or more biometric profiles can be created for the same person. One of the various profiles for the person can have an image further from the camera, and one of the various profiles can be for the person photographed closest to the camera. For the system to authenticate the person, the images and authentication biometrics must match the two or more profiles in the images and registration biometrics.

[0190] In addition, the system can detect the presence of a real person, compared to a fraudulent photograph of a person, by comparing the background of the images obtained in proximity and at a distance. When the mobile device 1310 is held in such a way that the person's face fits within the oval 1320, objects at the bottom that are almost directly behind the person may be visible. However, when the 1310 mobile device is held in such a way that the person's face fits inside the larger 1330 oval, the person's face blocks the cameras' ability to see the same objects that are almost directly behind the person. Thus, the system can compare the backgrounds of the images obtained in proximity and distance to determine if the real person is trying to authenticate with the system.

[0191] Of course, in Figures 13A and 13B, shapes or guides other than ovals 1320 and 1330 can be used to guide the user to hold the mobile device 1310 at the appropriate distance from his face. For example, the 1310 mobile device may show a full or partial square or

Petition 870190026446, of 03/20/2019, p. 72/137

68/113 rectangular. In addition, the system can vary the size and location of the frame, such as ovals 1320, 1330 to add more security. For example, the system may require a medium-sized frame, a small frame, and then a large frame. As another example, the system may require a small frame in a first location and a second location and then a large frame. This can be done randomly to teach different users the registration and authentication movements.

[0192] The number of frame sizes presented to the user may also vary for a single user based on the results of other security features described here. For example, if the GPS coordinates of the mobile device show that the device is in an unexpected location, more frames at different distances may be required for authentication. One or more indicators, such as lights, words or symbols, can be displayed on the screen to be visible to the user to direct the user to the desired distance that the mobile device must be from the user.

[0193] In Figures 13A and 13B, the system can predict the barrel-type distortion expected from the images based on the mobile device used for registration and authentication, and based on known and reliable registration data. In addition, or as an alternative, the known specifications of a mobile phone camera for a given model can be used to predict the expected distortion of the person's facial features at different distances from the lens. Thus, authentication can be device dependent. In addition, user registration information is not required at all possible distances from the camera.

[0194] For example, as described above, images and registration biometrics can be obtained for a user at two distances from the user. During authentication, several images are captured, in addition to images corresponding to distances near and far from biometrics and registration images. Based on

Petition 870190026446, of 03/20/2019, p. 73/137

69/113 expected distortion of these intermediate images, according to the distance covered by the device, the system can validate that the change in distortion of the images is occurring at the correct rate, even if only two registration profiles are obtained.

[0195] The capture of these images can be still images or video, in such a way that frames or images are extracted from the video that is captured during the movement from the first position far from the user and from the second position close to the user. Thus, it is contemplated that the operation can capture multiple frames during the zoom movement and ensure that the distortion is occurring at the correct rate for the size of the head and the distance movement of the mobile device based on data from accelerometers, magnetometers and the like.

[0196] Over time based on accumulated data or calculated data during the design phase, the system will have data indicating that if a phone is moved a certain distance towards a user's face, then the distortion effect it must be within a known percentage of the final distortion level or initial distortion level. So, in order to deceive or deceive the authentication system disclosed here, the attempted fraud would not only need to distort the fraudulent two-dimensional image, but it would also need to cut the background and then make a video of the face, distortion and background incrementally and in the correct speed, all without having any video screen strips or visible screen edges, which is very unlikely.

[0197] Many currently known facial recognition and facial detection algorithms are configured to look for a small face within an image. Thus, to ensure that the facial detection and recognition algorithms detect and recognize the user's face in the enlarged image (Figure 13B), the system can add a large security zone around the image taken in proximity. This creates a larger overall picture and allows current algorithms

Petition 870190026446, of 03/20/2019, p. 74/137

70/113 facial detection and recognition detect and recognize the face, even when the user's face is large in the original image.

[0198] When the registration and authentication movement resulting from the process described with Figures 13A and 13B is used, the security features of eye tracking described above can also be improved. For example, when the user is instructed to bring the 1310 mobile device closer to their face to fill in the 1330 oval, the QR code, a random shape, a barcode, color, text, numbers or any other visual indicator can be displayed on the screen. At this close distance, the reflection of the indicator displayed in the user's eye or face can be more easily captured by the camera. In addition, eye movement, blinking and the like to determine the “proof of life” of the person being photographed can also be more easily obtained in close proximity.

[0199] In one mode, at least one blink is required to prove presence for authentication. In another mode, blinks can be counted and the number of blinks can be calculated over time during authentications. This allows an additional factor in authentication to be the number of blinks observed during the movement. If a pattern of when the user blinks during movement is observed, the system can check whether the user blinks at the expected time and at the location of the device during the movement during future authentication attempts.

[0200] In other modalities, the size or location of the oval or frame may change to sizes or locations other than those shown in Figures 13A, 13B, such that the user must position and / or tilt the phone to position his face inside the oval. This establishes yet another method for ensuring the user's presence.

[0201] In an exemplary method, the mobile device is positioned at a first distance from the user and a first image is captured for

Petition 870190026446, of 03/20/2019, p. 75/137

71/113 processing. This distance can be linearly removed from the user and, in this mode, it may not be in an arc or orbit. This can occur by moving the mobile device by the user, manually or with the mobile device on a movable device or rail system. Or the lens system can be adjusted if, in a fixed system, to change the size of the user's face in relation to the size of the frame. Alternatively, the user can stand still, multiple cameras can be used, or the camera can move without the user moving. Once some form of movement (from a device, camera, lens or user) has occurred to establish the camera at a second distance, a second image is captured for processing. The movement from the first position to the second position can be direct to the user. Processing takes place on both images.

[0202] Processing may include calculations to verify a difference between the two images, or a difference in the biometrics obtained from the two images, which indicates that a real person is being photographed. Processing can take place to compare the first authentication image with a first registration image (corresponding to the first distance) to determine whether a match is present and then comparing the second authentication image to a second registration image (corresponding to the second distance) to determine whether a match is present. If a match occurs, authentication can continue.

[0203] Variations of these methods are also possible with the system that requires a match at the first distance, but a mismatch at the second distance, thus indicating that the second image is not a two-dimensional image. The resulting processing in a match or mismatch can be any type of image processing or facial recognition algorithm. As with the other processing described here, the

Petition 870190026446, of 03/20/2019, p. 76/137

72/113 processing can take place on the mobile device, on one or more remote servers or any combination of such devices.

[0204] All processing described here can take place only on the mobile device, only on a remote server or a combination of these. Biometric data can be stored on the mobile device or on the server, or it can be divided between the two for security purposes. For example, images can be processed on the mobile device, but compared to registration data in the cloud or on a remote server. Or the images can be sent to the cloud (remote server) for processing and comparison.

Touch Screen Enhancements [0205] Additional security modifications added may include information about a user's finger. Many mobile devices with touch screens can detect the location and approximate size of a user's touch on the screen. Thus, an approximate size of a user's finger or thumb can be measured by the system. In addition to the size of a finger, it is possible to detect an angle of orientation of the finger or whether the fingers or thumbs of the right or left hand are used.

[0206] In one mode, a user selects an account to open, initiates the formation of registration images or initiates the formation of authentication images by touching the touch screen of the user's device. The authentication system can thus detect whether a user's touch during authentication matches previously stored registration information, including the size of the user's finger or thumb, the amount of pressure applied to the screen and whether the user is right-handed or left-handed. This adds an additional layer of security to the authentication system.

[0207] In addition, the authentication system may require the user to initiate authentication by touching a fingerprint reader or the touch screen of a

Petition 870190026446, of 03/20/2019, p. 77/137

73/113 or more predetermined ways. In one embodiment, as shown in Figure 14, a touch screen 1410 can be divided into predetermined regions 1420. For example, there may be nine equal, circular, square or other 1420 regions on the touch screen 1410 of the mobile device. During registration, the user selects one of the 1420 regions of the 1410 screen to touch to initiate authentication. During authentication, if the pre-selected region 1420 is not touched to initiate authentication or during the entire authentication process, authentication is denied. This is only a possible design possibility and other design options are contemplated.

[0208] 1420 regions on the touch screen can be visually represented by a grid, or they may not be displayed on the 1410 touch screen. As shown in Figure 15, in addition to or in place of 1420 regions, 1520 buttons can be displayed on a 1510 touch screen. Here, the user can initiate authentication by pressing one or more of the 1520 buttons in a predetermined pattern. The user can also initiate authentication using a predetermined sliding pattern. The position to be touched by the user can change with each authentication attempt and can be transmitted to the user through any instruction from the authentication server, such as code, number, letter, color, captcha or other indicator.

Voice Parameters [0209] It is also contemplated that the user can record his voice speaking a phrase while recording his images during the registration process when using the system for the first time. Then, to authenticate, the user would also have to speak the phrase when moving the mobile device to capture the image of his face. Thus, an additional path parameter can be the user's spoken voice and the use of voice recognition as another layer or element of the authentication process.

Petition 870190026446, of 03/20/2019, p. 78/137

74/113

Image Quality Assurance [0210] The authentication system can also process images received from the mobile device to determine whether the images are of sufficient quality. For example, the system can check if the images are blurry due to blurred images or if the camera lens is being obscured by fingerprints, oils, etc. The system can alert the user that the quality of the images is insufficient (either too light or too dark) and direct the user to adjust a focus, exposure or other parameter, or to clean the camera lens.

Autofocus [0211] The authentication system can also use an autofocus feature when the mobile device's camera is equipped with that feature. For example, when a real three-dimensional person is being photographed, the system checks whether the sharpness of the image changes as the camera performs autofocus. In another mode, the system can control autofocus so that the camera focuses on a first location or distance to check the sharpness (in focus) of a part of the image that contains a face. The system then controls the camera to focus on a second location or distance where the presence of a face is not detected and to check the sharpness (in focus) of a part of the image. If a three-dimensional person in a real environment is being photographed, it is expected that the focal length settings will be different in the first and second locations, which suggests that a real person is currently being photographed. However, if the focal lengths of both locations are the same, it indicates that a photograph or two-dimensional screen is being photographed, indicating a fraudulent login attempt.

[0212] The system can also control the device's autofocus to check different focal lengths of different features in the image. For example, when a person's face is photographed from the front, it is expected that the

Petition 870190026446, of 03/20/2019, p. 79/137

75/113 person has a different focal length (more distant) than the tip of the person's nose.

Login Attempted Images [0213] The authentication server can also be configured to store authentication images for a predetermined period of time. Images can provide additional security benefits as proof that a person is trying to sign in to a user's account. For example, the system can store a predetermined number of previous login attempts, such as twenty login attempts, or store images of login attempts for a predetermined period of time, such as during the last seven days or weeks. Any fraud or attempted fraud will result in pictures of the person trying to log in being stored or sent to the account server's authentication server.

[0214] The mere knowledge that photos will be taken and sent is a significant impediment for any potentially dishonest person, because he knows that his photo will be taken and stored, and is a guarantee of security for the user. Likewise, any attempt or unsuccessful attempt may have the photo stored and the indication of who is trying to access the account. It is also contemplated that an email or text message together with the image of the person who is trying to log in unsuccessfully can be sent to the authorized user, so that they know who is trying to access their account. This establishes the first security line for the account, since the user with the photo or image is also in possession of the authentication server.

Adaptive Correspondence Limits [0215] In addition, the level or percentage of correspondence between registration information and authentication information to authenticate the user may change over time. In other words, the system can understand a limit

Petition 870190026446, of 03/20/2019, p. 80/137

76/113 adaptive.

[0216] After a user regularly uses the authentication system described above, the user will have logged into the system by moving the mobile device along the predetermined path in relation to his head many times. Thus, it can be expected that, as the user gains experience using the authentication system, the user gradually establishes a comfortable and standardized movement path. In contrast, a user's initial registration movement is likely to be the most awkward and awkward since the user has little experience with the authentication system.

[0217] To make the authentication system more convenient for the user without losing security, the adaptive limit system allows the registration movement to adapt so that the user is not trapped by the awkward and awkward initial movement like the registration movement . To facilitate this, with each successful authorization, the successful authorization movement is stored, and the movement path is added to a list of acceptable movement paths. The list of acceptable movement paths can be limited to a predetermined number of paths. When a new successful authorization is completed and the list of acceptable movement paths is full, the oldest registration movement path will be deleted and the most recent one will be stored in its place. Alternatively, the movement path that is less similar to the other movement paths stored in the list can be deleted. Thus, when storing the most similar or most recent movement paths, the registration movement can adapt slowly over time, as the user is familiar with the system and settles in a comfortable movement path for authentication.

[0218] In addition, other registration information can be adaptively changed in a similar way to user information. Per

Petition 870190026446, of 03/20/2019, p. 81/137

77/113 example, biometric information or photos of successful authentications can be stored as part of the registration information, and old registration information can be discarded over time. In this way, the authentication system can be convenient for a user, even over a long period of time, as the user experiences aging, facial hair growth, different makeup styles, new glasses or other subtle facial changes.

[0219] The determination of how much variation is allowed over time in the movement path or in the biometric information, or both, can be defined by the entity that requires authentication to meet the entity's security requirements. The time or number of scans after the initial registration can be used to modify the adaptive limit. For example, during the first few days after registration, the limit may be lower while a security threat is low and the differences in routes are likely to be greater. After several authentications or several days, the limit may increase. The limit can still be defined based on the trend data of the movement path or biometric information. For example, the limit may be softer in the trend direction of the data, while having a tighter tolerance for the data in relation to the trend.

[0220] A temporal aspect can also be added along with the location information. For example, if the user conducts and authenticates a transaction close to his home and then, an hour later, another transaction is attempted in a foreign country, the transaction can be denied. Or it can be denied if the distance between the previous authentication location and the next authentication location cannot be traveled or is unlikely to be traveled in the time interval between login or authentication attempts. For example, if the user authenticates in Denver, but an hour later an attempt is made in New York, Russia or Africa, the first or second attempt will be fraudulent because the user

Petition 870190026446, of 03/20/2019, p. 82/137

78/113 will probably not be able to travel between these locations in an hour.

[0221] In addition, if the next transaction is attempted at a more reasonable time and distance from the first transaction, the match limit level can be increased to provide additional security, without automatically denying the transaction. Likewise, an altimeter can be used in such a way that, if the altitude determined by the mobile device is different from the altitude of the city in which the user is located, this may indicate an attempted fraud. Thus, the altitude or barometric readings of the mobile device can be used to verify the location and can be referenced in relation to GPS data, IP address or location data of the router, or location identified by the user.

Random Image Distortion [0222] To provide an additional layer of security to the face recognition authentication system, the system can use random image distortion. For example, a user may receive a random distortion algorithm after registering with the system. The distortion algorithm can include such distortions in the image as enlarging or narrowing the person's face by a predetermined amount, adding or overlapping a predetermined shape at a predetermined position on the user's face. As an example of this, the distortion can be an overlapping circle 100 pixels above the user's left eye.

[0223] With the distortion attributed only to the user's images, the biometric data for that user will be exclusive for the account or device used by the user. In other words, the registration biometrics stored on the authentication server or on the mobile device will not only reflect the user's facial characteristics, but will also reflect the image distortion attributed exclusively. Thus, even if an accurate and fraudulent representation of a person was used on a different device or through a different account, the authentication biometrics offered would not correspond sufficiently due to a distortion

Petition 870190026446, of 03/20/2019, p. 83/137

79/113 single different or an absence of single distortion. Thus, overall security can be improved.

Security Layers [0224] It is noted that each of the above modalities, modifications and improvements can be combined in any combination as needed to create multiple layers of security for authentication. For example, facial recognition can be combined with motion detection or path detection, or it can operate independently of these features for authentication. In addition, when more than one of the improvements or modifications described above are combined, the authentication system can be configured so as not to provide any feedback or indication as to which layer failed authentication.

[0225] For example, when a predetermined ring pattern to initiate authentication is combined with the authentication and facial authentication movement, the system does not indicate whether a ring pattern was incorrect or if the authentication movement or authentication images are not correspond to the registration information. Instead, the system provides an identical authentication denial, regardless of the failure. This is the case when any number of the security features described above are combined. In this way, it is difficult for a fraudster to detect which aspect of the fraudulent credentials should be corrected, further increasing the security of the system.

[0226] All the above resources can be incorporated together, or only some resources can be used and others, omitted. For example, when the device asks the user to move the device so that the user positions their head within a first small frame (such as an oval) and then in a second large frame (as in Figures 7A, 7B, 13A and 13B ), the system can be configured so that facial recognition does not need to be performed on the image (s) in the first frame (frames captured far away). The security

Petition 870190026446, of 03/20/2019, p. 84/137

80/113 of the system is maintained by performing facial recognition across the image at some point between the first and second frames and in the second frame. This can be especially true when it also integrates another layer of security, such as checking eye tracking following a moving object on the screen, or reading a reflection of a QR code or a random shape in the user's eye. In another modality, when two or more cameras are used to create three-dimensional stereoscopic images, facial recognition may not be performed in the first distant frame, but instead the person's proof of life can be validated in the nearest frame only after the movement of the person. device. In yet other modalities, other layers of security can be used and the motion parameters can be omitted. Such combinations can be beneficial for larger or stationary devices, such as gaming laptops, personal desktop computers, a stationary kiosk or the like.

Application Examples [0227] Likewise, although described here as financial account authentication, authentication using path parameters and image data can be implemented in any environment that requires verification of the user's identity before allowing access, such as access automatic, access to rooms, access to computer, access to website or data, use of telephone, use of computer, receipt of packages, access to events, ticketing, access to courts, airport security, retail sales transactions, access to IoT or any other type of situation.

[0228] For example, a modality will be described where the above authentication system is used to safely conduct a retail sales transaction. In this modality, a user is registered on the authentication server or an authentication application on the mobile device, as described above, and

Petition 870190026446, of 03/20/2019, p. 85/137

81/113 generated registration information, including images and / or registration biometrics, and registration movement. In this example, the user initiates or attempts to complete a transaction at a retail outlet with a credit card, smart card, or using a smartphone with NFC capabilities.

[0229] The user initiates the transaction by swiping a credit card, smart card or using an application on a smartphone with NFC features to pay for goods or services. The retailer would then authorize the card or have the relevant network of the financial institution (“Gateway”). For example, the retail establishment, through a Gateway, such as one operated by VISA or AMERICAN EXPRESS, would determine whether the account is available and has sufficient funds available.

[0230] The Gateway would then communicate with the authorization server to authorize the transaction, verifying the user's identity. For example, the Gateway can send an authorization request to the authentication server, and the authentication server sends a notification, such as a push notification, to the user's mobile device to request the user to authenticate the transaction.

[0231] After receiving notification from the authentication server, such as through a vibration, beep or other sound on the mobile device, the user can authenticate his identification with the mobile device. The authentication server can also send the transaction information to the user for verification by the user. For example, the authentication server can send information that causes the mobile device to display the seller, the location of the seller and the total purchases of the transaction.

[0232] Then, as before, the user can hold the mobile device and obtain a plurality of authentication images as the user moves the mobile device to different positions in relation to the user's head. When moving the mobile device to obtain the authentication images, the mobile phone tracks

Petition 870190026446, of 03/20/2019, p. 86/137

82/113 also the parameters of the path (authentication movement) of the mobile device through the gyroscope, magnetometer and accelerometer to obtain the authentication movement of the device. The mobile device can then send the device information, authentication images and authentication movement to the authentication server. In other modalities, the mobile device can process the images to obtain biometric data and send the biometric data to the server. In still other modalities, the mobile device can process the images, obtain authentication information, compare the authentication information with the registration information stored on the mobile device and send the results of approval / disapproval of the comparison to the authentication server.

[0233] The authentication server can then authenticate the user's identity and confirm that the user wants to authorize the transaction on his account if the device information, images and / or authentication biometrics and authentication movement match the device information registration, images and / or registration biometrics and the registration movement. The authentication server then transmits an authorization message to the Gateway. After the gateway has received confirmation of authorization, the Gateway then communicates with the retail outlet to allow the retail transaction.

[0234] Several advantages can be obtained when a retail transaction is authorized using the system and method above. Since the user's identity verification and transaction confirmation are completed through the authentication system and the mobile device, there is no longer a need for a user to provide their credit card or subscription or enter a PIN number in the point system retailer's selling point. In addition, the retail establishment does not need to verify a user's photo ID. The above method and system also has the advantage of providing secure transactions that can work with transactions

Petition 870190026446, of 03/20/2019, p. 87/137

83/113 mobile and online that do not have cameras, such as security cameras, on site.

[0235] In the secure retail transaction described above, the user obtains the total amount due on his mobile device from the retail establishment through the authentication server and Gateway. However, in one embodiment, the mobile phone can use the camera as a barcode, QR code or similar scanner to identify the items and the prices of the items to be purchased. The mobile device can then total the amount due and act as the checkout to complete the transaction with the retail outlet.

[0236] In another modality, a user of the application may wish to pay an individual or a merchant anonymously. In this case, the user would designate an amount to be paid in an application and the application would create a unique identifying transaction number. This number can then be shown to the second user, so that the second user can enter the identification transaction number in an application on a separate device. The unique identification transaction number can also be sent from the user to the second user via NFC, Bluetooth, QR code or other suitable methods. The second user can also enter the amount and request payment.

[0237] Upon receiving the payment request and the unique identification transaction number, the authentication server can send a notification to the first user's mobile device to authenticate the transaction. The user then verifies his identity using the facial recognition authentication system described above. The user can, alternatively or additionally, verify his identity using other biometric data, such as fingerprint or retinal scan, movement and route-based images, or the user can enter a password. After authentication, the user's device sends a request to the user's payment provider to request and authorize payment to the second user.

Petition 870190026446, of 03/20/2019, p. 88/137

84/113

In this way, payment can be made securely, while the users of the transaction are anonymous.

[0238] According to one modality, as an additional security measure, the GPS information of the mobile device can also be sent to the authentication server to authenticate and allow the retail transaction. For example, the GPS coordinates of the mobile device can be compared with the coordinates of the retail establishment to confirm that the user is actually present at the retail establishment. In this way, a criminal who has stolen a credit card and tries to use the card from a distant location (compared to the retail location) cannot complete a transaction because the user's phone is not at the retail location. IP addresses can also be used to determine the location.

[0239] As explained above, the level or percentage of correspondence between registration information and authentication information to authenticate the user can also be adjusted based on the GPS coordinates of the mobile device. For example, if the retail store and the GPS coordinates of the mobile device are close to a user's home, then the match level can be set at a lower limit, such as a 99% match rate. Alternatively, if the location is too far from the user's home and is in a foreign country, for example, the match level can be set at a higher limit, such as a 99.999% match rate.

Biometric Identification using Root Identification Information [0240] Most biometric identification systems in recent years have used devices such as smartphones to capture biometric data (for example, a digital photograph or scanning a fingerprint). These biometric data correspond to pre-existing biometric data on the device (in

Petition 870190026446, of 03/20/2019, p. 89/137

85/113 compliance with FIDO Alliance standards) or in the cloud (a remote computing device) where biometric data is sent to servers and compared to pre-existing data.

[0241] However, with the ability to convert images or other biometric data into biometric models on the device without sending the raw data files to a server, an additional option is available. Existing raw biometric data, such as facial images, fingerprint scans, etc. or converted biometric models can be downloaded to the device.

[0242] The downloaded biometric data can then be converted and / or compared to a biometric model that was created from the data captured on that device and previously sent to the cloud or captured and sent to the cloud from a different device .

[0243] This allows a third party to provide an existing root identification profile for comparison with the biometric information obtained on the device for authentication. For example, the root identification profile may comprise an image or other biometric reading of a customer that has been captured and verified at a bank branch, from a DMV file or from another authorized and trusted source. The bank branch, government entity (such as DMV) or other trusted source may have a secure camera, fingerprint reader or other type of biometric capture device that reliably captures the user's biometric information to create the root identification profile . The root identification profile can, alternatively or additionally, comprise biometric models created from the verified image or biometric reading. In this way, the identification match on the device has a higher level of confidence based on the verified root identification profile of third parties. The biometric model is defined as data derived from the biometric identity profile. For example, if a user's trusted image is captured, that trusted image can be

Petition 870190026446, of 03/20/2019, p. 90/137

86/113 or be part of the root identification profile. This reliable image can be processed to create a biometric model or be part of a biometric model. Processing can transform the image into data (the biometric model) that can be used in the authentication process, but the original image cannot be recreated from the biometric model.

[0244] Figure 16 presents a system for biometric identification using root identification information, according to an exemplary modality. The system includes a 1612 user device, such as a smartphone or a tablet-like computing device that comprises one or more biometric sensors, such as a 1614 camera and 1615 fingerprint scanner. The 1612 device communicates with a 116 network , such as the Internet.

[0245] A 1630 root identification server is also connected to the 116 network. The 1630 root identification server can be a bank server, a government server or another “trusted” server that stores root identification information including biometric information and / or biometric model (s). The 1630 root identification server is connected to biometric detection devices, such as a 1632 camera or 1634 fingerprint scanner. It is contemplated that the 1632 camera can be part of a computer, standalone device or a mobile device, all of which are reliable. The camera can be fixed or the distance between the user and the 1632 camera can vary during the capture of reliable images, such as an image captured at a distance from an image captured closely. The distance can be similar to the distance a user can establish while holding their mobile device to self-photograph. A 1620 authentication server that provides an application, such as facial recognition algorithms and the like, is also connected to network 116. Also part of the embodiment of Figure 16 is a third party server 1640, which can be a root identification server or a third-party server, just like for a company

Petition 870190026446, of 03/20/2019, p. 91/137

87/113 or any other type of entity. As described above, a 1650 authentication server can also be part of the system. The 1650 authentication server can be configured to perform authentication processing, for example, by running one or more authentication algorithms on biometric data to evaluate and authenticate a user. In one embodiment, authentication servers 1650 can be configured as one or more of servers 120, as shown and described above in Figure 1. Figure 20 illustrates exemplary server hardware. Any means of communication between the elements in Figure 16 can occur, including cable and wireless connections.

[0246] Figure 17 presents a method for authentication using a root identification system, according to an exemplary modality. Authentication using facial recognition as the biometric information analyzed for a root identification profile can work as explained in the following exemplary modality. First, in step 1701, biometric information is captured using a reliable device (camera 1632 or scanner 1634 in Figure 16). The device is considered reliable because the biometric information collected on the device is verified by a trusted institution, such as a bank or government agency. This captured data can be defined as a root identification profile. They can be stored on a 1630 server or in any secure database. In one embodiment, the root identification profile can include DMV (Department of Motor Vehicle) images, or any reliable biometric information collected or based on the government. A root identification profile is established in step 1703 that comprises the biometric information of the trusted device and links the biometric information to a user identity, such as name, CPF number, another identification number, driver's license number, account number account name or any other type of information. This root identification profile is stored in the

Petition 870190026446, of 03/20/2019, p. 92/137

88/113 server, such as the 1630, 1640, 1650 server or any other database. The trusted source can be a commercial or governmental entity.

[0247] In step 1705, biometric information, such as an image containing data about an individual's face from the root identification profile, is sent from the 1630 server to the 1612 smart device upon an authentication request from the 1612 smart device The term smart device (which is used as an authentication device) can be any type of computing device, such as a computer, mobile device (tablet, cell phone), ATM, kiosk or any other device used to conduct an authentication session. for identity verification. The smart device (authentication device) can belong to the user, company, government entity or any other entity that intends to use the authentication system to verify the identity. For example, a car dealership may wish to check the identification before releasing the new car for purchase. If the authentication device is an ATM, authentication may be required before a cash withdrawal occurs. If a point of sale, a jewelry store, for example, may want to verify the identification before providing the diamond ring. At a government agency, the government agency may wish to verify identification before releasing the pension, retirement benefit, medical services or tax return.

[0248] The 1612 smart device can be referred to as the authentication device because it is the device that is used for authentication. The user of the smart device 1612 then articulates camera 1614 so that the user's face can be captured by the device's camera 1614, in step 1707. As described above, one or more images can be captured. Images can be captured with the camera at different distances from the user or the user at different distances from the camera. Biometric data (profile or model)

Petition 870190026446, of 03/20/2019, p. 93/137

89/113 transferred from the 1630 server to the authentication device can now be compared in step 1709. In one embodiment, the trusted model or trusted image can be downloaded to the smart device (authentication device). For example, each reliable image is converted into a biometric model by a facial recognition algorithm for comparison. In comparison, if the models are similar enough based on the limits defined, for example, by a publisher or application entity that requests authentication, the image captured by the smart device (device ID) and the image previously captured (root ID) they can be considered correspondents in step 1711. Thus, the person is who he claims to be and the identity is verified. Access can then be granted or the business transaction completed, the travel authorized or any other authorized activity, or the registration process can be completed based on the corresponding images or modeled in step 1713. If there is no match in step 1711, access is denied in step 1715.

[0249] As described above, trusted biometric information (profile or model) is sent from a remote server to the authentication device. In other modalities, other data exchange schemes are possible. In one embodiment, the trusted biometric information stored on a 1630 root identification server and the biometric authentication information (captured during an authentication session) is loaded on the 1630 root identification server. The 1630 root identification server is equipped with a memory (storage software - machine-readable code) and a processor is configured to perform authentication algorithms. The authentication algorithms can be for identity verification, proof of life or both. The results of the authentication request are the return to the authentication device, which can be any of the servers or devices shown in Figure 16.

Petition 870190026446, of 03/20/2019, p. 94/137

90/113 [0250] In another embodiment, a 1612 authentication device (or server) initiates an authentication session. Biometric authentication data is captured and processed. The resulting biometric authentication information is uploaded to a 1650 authentication server. The 1650 authentication server is configured with memory, machine-readable code and a processor, and configured to process / compare biometric information as part of an authentication session. The 1650 authentication server, after the authentication session starts, obtains the biometric identification information corresponding to the user, the authentication retrieves the biometric identification information for the user. The biometric root identification information can be stored on the 1650 authentication server or requested and received from the root identification server. In some cases, such as in the case of government-controlled identity data, the biometric root identification information can be stored on a secure government server that functions as the root identification server. Upon receipt of the root biometric identification information from the root identification server 1630, the authentication server 1650 performs identification verification by comparing the root biometric identification information with the biometric authentication information (profile or model information) by comparing the root biometric identification information with the biometric authentication information.

[0251] In another mode, authentication (includes proof of life termination, identity verification or both) occurs on the authentication device and on a remote server, such as the authentication server or the root identification server. In this configuration, the smart device will receive the biometric information from the user's captured authentication session as well as the trusted root identification information from the root identification server, and then make a comparison to determine if there is a match. If

Petition 870190026446, of 03/20/2019, p. 95/137

91/113 there is a match, then the biometric information captured by the smart device (biometric information capture device from the authentication session) will be sent to the 1650 authentication server of the 1630 root identification server and the processing and comparison will be repeated there. This provides a dual verification process and would prevent the smart device from accurately or fraudulently reporting successful authentication.

[0252] It is also contemplated that the determination of proof of life can occur in all these modalities as part of the authentication. While identity verification against trusted root identification information is a valuable part of the process, it is also the proof of life determination. Thus, it is contemplated that identity verification can occur independently, the proof of life determination can occur independently or both can occur as part of a verification session. In one embodiment and as discussed above, proof of life detection is a comparison of two user images captured at different distances between the user and the camera (due to a change in the distance between the camera and the user from any camera movement) , user movement, or both). In one embodiment, the proof of life detection occurs before the identification verification. It can serve as a prerequisite that must occur successfully before identification verification is attempted. In an exemplary embodiment, proof of life detection occurs as described herein. If the process determines that someone else is attempting the authentication, then the authentication session is ended and no additional biometric information is collected, and the trusted root identification information is not downloaded and compared, or the biometric information captured by the device are not loaded on the authentication server or the root identification server. Alternatively, if the proof of life determination determines that the person

Petition 870190026446, of 03/20/2019, p. 96/137

92/113 leads the authentication session is a living person, so the root biometric information is retrieved from the root biometric server or the biometric information collected during authentication is sent to the authentication server or root identification server for identity verification. Using proof of life termination as a prerequisite before identity verification provides several benefits. The benefit is the elimination of personal biometric information over the network, reduced bandwidth usage, faster completion of the authentication session and less overhead on the processing resources of the authentication server or the root identification server, which saves costs by requiring less network and server resources.

[0253] The benefits of this system include, but are not limited to, the ability to match biometric data previously captured from a different device with a new device, while no biometric data leaves the new device during matching. This is important in some regulatory environments and sectors.

[0254] For facial recognition systems with a server component, the same facial recognition algorithm can be loaded on the server as it is running in an application on the smart device. This allows only the model to be transferred to the device instead of the biometric reading itself (for example, facial images, fingerprint scans, etc.). For example, in step 1705, the biometric information can be the biometric model instead of an image of the root identification profile. The algorithms located on different devices / servers must be configured so that the models created are homogeneous and can be compared. That is, if the algorithms output data in different formats, the resulting biometric data / model format is incompatible, and no match can occur because similar facial features would not be represented by standards

Petition 870190026446, of 03/20/2019, p. 97/137

93/113 of similar biometric model data. The term model is defined here as biometric data points represented by a sequence of numbers or other data formed in a consistently formatted pattern, so that similarities and differences can be determined through various methods of comparison.

[0255] In a modality in which no model is transferred to the device, the root identification established in step 1703 may include a biometric model created from a biometric algorithm, such as a facial recognition algorithm. For example, an image that includes the face of an individual captured with a trusted device (1632 camera at a bank branch, DMV etc.) is sent to the 1630 server, where it is converted into a biometric model with a facial recognition algorithm. As mentioned above, the biometric model of the root identification profile is sent to the smart device 1612 upon an authentication request in step 1705. This can be referred to as the biometric model of root identification. The method proceeds as explained previously with reference to Figure 17, where the biometric models are compared in step 1709.

[0256] In another example, two or more biometric modalities could be used together, such as fingerprints, face and voice. Another example of the method in Figure 17 using two or more biometric modalities can work as follows. First, images of a user's face, scans of the user's fingerprints, as well as a recording of the user's voice are captured with trusted devices in step 1701 (for example, devices 1632, 1634 at a bank branch, a DMV etc. at that the identity of the captured data is verified) to establish a root identification in step 1703. Images, scans and records can be considered biometric root identification data, as this information is captured from a reliable source. At

Petition 870190026446, of 03/20/2019, p. 98/137

94/113 step 1707, the user of the smart device (1) presses one or more of his fingers on a fingerprint sensor and / or takes a picture of his fingers; (2) articulates the camera so that the user's face can be captured by the device's camera; and / or (3) speaks words into the device's microphone to be recorded. The data recorded by the device can be considered biometric device identity data.

[0257] Biometric data of root identification and biometric data of device identity are converted into biometric models (biometric models of root identification and biometric models of device identity) by fingerprint recognition, facial recognition and / or recognition algorithms of voice. In some cases, biometric root identification data can be converted to biometric root identification models on the server, and the models can be sent to the device. The biometric root identification models and the biometric device identity models are compared in step 1709, and if the models are similar enough based on the limits defined, for example, by an application publisher, the root identification models and the device identity templates can be considered a match. Based on correspondence, access can be granted or a registration process can be completed in step 1713.

[0258] In another mode, in step 1709, the images and / or the biometric model (s) of the user device can be transferred to the server, where they can be stored and / or compared with the models and / or biometric images of root identification. Then, if the user wishes to replace the original device or add a second user device to the account, both the root image (s) and / or model (s) and the image (s) and / or device identity model (s) captured on the first device can be sent to the second device during setup or registration for comparison and matching.

Petition 870190026446, of 03/20/2019, p. 99/137

95/113

This links the server's root ID to the device's first identity and again to the device's second identity. If no image and / or root identification model has been previously captured and stored on the server, the image and / or model that is loaded from the first device can still provide additional security. If the user chooses to add a second device to an account, the image (s) and / or model (s) of the first device can be sent to the second device, and the comparison described above can occur again by the user using the second device to authenticate. Authentication compares the biometric information sent from the first device to the second device with the user's biometric data captured using the second device to verify that it is the same user. This allows the user to add a second device with greater security, since the identities of the users on both devices have been found to match.

[0259] In addition, when the image (s) and / or model (s) are loaded on the server, comparisons on the server between the image (s) and / or model (s) can be performed regardless of a comparison made directly on the device. This offers a significant increase in security because, even if a hacker could manipulate the user's device to send a “matching” result back to the server, the server would also compare the same image (s) and / or biometric model (s). Therefore, authentication can take place on two or more devices or servers to make the system more secure. If less than all or a predetermined number of devices / servers do not authenticate, then a match is not declared. Thus, the server would also need to determine whether the image (s) and / or the biometric model (s) were matched using the same limits. Therefore, the hacker not only needs to compromise the user's device, but also one or more servers to defeat security.

Petition 870190026446, of 03/20/2019, p. 100/137

96/113 [0260] In addition to biometric correspondence, proof of life checks can be included in the device part of the correspondence, as well as in the server part, as described in detail above. For example, additional information, such as device movement, skin texture, three-dimensional depth information, can be used to help determine whether the biometric data presented to the camera is from a living human being and not a photo, video or fake mask. .

Remote Image Collection / Biometric Models [0261] To verify biometric data, it is usually necessary for an individual to enter a bank branch, a government office, such as a DMV or police station, or another “trusted” location to have their biometric data collected. For example, a bank may require a photograph, a fingerprint or a voice recording to open certain types of accounts. The biometric data obtained is then linked to the person and the account. This face-to-face biometric data collection has usually been required because there was no other way to trust that an individual was in fact who he claimed to be. Through face-to-face collection, identification is verified, for example, by the person providing the documents with the name and photograph issued by a governing body.

[0262] However, according to an exemplary modality disclosed here, an individual can provide his own biometric data using any smart device with a biometric sensor or camera to be verified without face-to-face verification. In fact, according to the disclosed modalities, companies, organizations, government entities, accountability institutions or financial institutions can be more confident than ever that the biometric data provided is from the correct individual and not from an imposter, hacker or bad actor.

[0263] Figure 18 presents a method for remotely establishing a

Petition 870190026446, of 03/20/2019, p. 101/137

97/113 biometric identity, according to an exemplary modality. In this modality, an individual first downloads an application to his smart device from an institution with which he has an account, or with which he wants to open an account in step 1801. When opening the application and when asked, the person presents his face, fingerprint etc. camera or sensor. The biometric data is captured and stored on the device as “registration data” in step 1803. This process is described above in detail as the registration process or the storage of the baseline biometric information. In some modalities, the registration data is sent to a server and stored in a server or database.

[0264] The user then makes a payment or deposit to the institution in step 1805. For example, if a credit institution provided the user with a mortgage, the user would enter their payment account information into the application so that the institution could collect payment. When payment information and authorization are transmitted to the credit institution, some or all of the user's biometric registration data is collected and transferred to the credit institution's server with the same. Since payment is made by the user for the user's debt, which causes the money to leave the user's account and therefore not occur by a possible hacker or person committing fraud, the resulting biometric data collected as part of the transaction is considered reliable. This step can be defined as the execution of an action that is a loss for the user or an action that the user does not benefit from. Although this action may involve cash payments to third parties, it can also be an action such as performing a service or task, filing taxes, doing a medical check-up, donating blood, a DNA test or sample or any other event that a person with intent to commit fraud probably would not do repeatedly.

Petition 870190026446, of 03/20/2019, p. 102/137

98/113 [0265] Subsequently, when the user opens the application again to carry out another transaction (such as payment or other action), the user is again asked, as part of the payment, to present his biometric information to the camera or sensor, and new biometric models can be created in step 1807. The new biometric models are compared with the previous “registration data” on the device and / or the new models can be sent to the server for comparison in step 1809. In some modalities, the device you can compare the models by downloading the registration data models from the server to the device for correspondence. Or the newly acquired model can be sent to an authentication server for comparison with the registration models (biometric information) or previously recorded models (biometric information).

[0266] When it is determined that the new information and / or biometric models do not match the registration data, then the transaction can be denied, as shown in step 1811, and the root identification will not have the unmatched biometric information added to it . Either the transaction can be completed, but the new unmatched biometric information is not added to the database, or the account can be flagged for an attempt and failure to match the biometric information. However, when the new biometric information corresponds sufficiently to the registration data, the transaction can be authorized as shown in step 1813. In addition, when there is a match, the confidence level of the biometric data attached to the user profile is increased .

[0267] Since, in this modality, the user is sending funds to the account, for example, to pay a debt or to make a deposit, he / she (the user) has an incentive to be able to access the account containing later those funds or has a reduced debt. So, over time, as

Petition 870190026446, of 03/20/2019, p. 103/137

99/113 that multiple deposits and / or payments are made with corresponding biometric models, confidence in the identity of the user performing the transactions increases, as shown in the cycle of steps 1807, 1809 and 1813. Trust is high because it is not likely that a person who is attempting to commit fraud or identity theft, now or in the future, will pay other people's debts (invoices) or take other actions that do not benefit them or that cause them harm (such as a payment). This also provides repeated links or association between the user and the account to create confidence that the user is who he or she claims to be the person associated with that account.

[0268] The resulting biometric information can later be used in environments and applications other than that account after it becomes reliable. For example, since trust is built with a biometric profile for a user, that same biometric profile can be considered reliable and used for shopping or access control.

[0269] In one way, to limit liability to third parties or other entities, access to withdrawals even for a reliable biometric profile can be limited to the same amount or less than what was deposited or paid in full by the user. For example, if a user makes a mortgage payment, loan payments or bank deposits worth $ 3,000 every month for three months using their smart device and using their face to identify themselves at all times, the financial institution may be willing to allow that person to transfer up to $ 9,000 (or some other amount related to reliable payments made) from a different account that the bank has for the user, such as a checking account. Likewise, if a trusted biometric profile is established, it can receive a confidence score, which designates the amount or degree of confidence associated with that trusted biometric profile. Based on the confidence score, third parties, such as companies, suppliers,

Petition 870190026446, of 03/20/2019, p. 104/137

100/113 government agencies can make decisions on how to do business with that user or how much to lend or sell based on this confidence score. For example, a different threshold for the confidence score can be established and the confidence score must meet these limits (based on a comparison) before money is loaned, a credit card is issued or a product is sold / provided to the user before an identification card is issued or before access is granted to a secure location.

[0270] As banks and other credit institutions report on outstanding balances, credit limits and payment terms to credit bureaus, the bank is also expected to provide the biometric model (possibly in encrypted format) to a credit bureau, an entity governmental or other entity, for storage as part of the identifying information in the user's credit file. So, if the user wishes to apply for credit from a different institution, that institution may require the user to access their version of the application with the same biometric data collection system (and / or confidence score) used to create and maintain the model. Biometric models can be sent to credit bureau servers and compared to archived models for that individual. With this process, the user can positively identify himself and grant access to the financial institution to view his credit information without providing or transmitting his social security number, date of birth or other confidential information.

[0271] If a user does not have a debt to pay to the account issuer or the issuer is not a financial institution, it is possible to simply offer a temporary deposit service (or other process to build trust) to provide assurance that the data biometrics provided are true and correct for the claimed user. For example, a user could provide a credit card number with his name and address, the card could be charged at $ 100 and the user

Petition 870190026446, of 03/20/2019, p. 105/137

101/113 would provide your biometric data to the application on your smart device. The user would then correctly answer a series of knowledge-based authentication questions based on their credit report, insurance information, medical information or other potential confidential information, and provide their biometric data again to the application to retrieve the funds or correspondence with biometrics stored in a reliable database or other means. The result is a biometric identity that can be trusted in future transactions up to the amount that was previously deposited and successfully recovered. In this way, the credit can be offered up to the deposit amount or some amount based on the value of the guarantee account.

[0272] Although described in financial terms, it is also contemplated that other actions can be used to build confidence that the biometric information captured when the action occurs and the resulting reliable biometric profile, developed over time, is accurate and reliable. For example, in one embodiment, the authentication system can be used as an access control system or a shift at a person's workplace. Every time the user enters work or enters the building using the access control system, their biometric information is captured and used to build confidence in their identity. It is assumed that the person who comes to work is the real person and not a person who tries to commit fraud or establish a false identity. Likewise, this process can take place in a doctor's office as part of a medical examination, dental office, donation of money, obtaining or renewing a driver's license or passport, attending school or any other activity that would not be performed by a person trying to commit fraud. GPS data can be combined with this process to verify that a person who is hitting the spot is at work.

Decentralized Biometric Identity Ledger

Petition 870190026446, of 03/20/2019, p. 106/137

102/113 [0273] There are numerous security and privacy benefits for a biometric, anonymous and decentralized identity network, compared to biometric authentication conducted in a centralized database or only on a user device. As explained earlier, biometric identity information can comprise images with biometric data, such as digital photographs of a face or fingerprint, and / or biometric models that are sequences of numbers representing data that have been captured by a sensor and converted into a sequence by a biometric recognition algorithm.

[0274] Decentralized Ledgers, such as Blockchains, Tangles, HashGraphs etc., referred to below in Blockchains, can be used to create public or private records that provide an immutable transaction history. The blocks can store various data and, in this modality, the blocks can store biometric data in the form of an image or a biometric model created from a biometric sensor (camera, fingerprint scanner etc.) and / or an algorithm that analyzes an output from the biometric sensor (photography, fingerprint scanning, etc.). Figure 19 shows a biometric authentication system using a chain of blocks, according to an exemplary modality.

[0275] In an exemplary biometric authentication method, a 1912 smart device would run an application allowing a 1916 sensor or 1914 camera to capture biometric data and optionally convert the biometric data into one or more biometric models. The biometric data and / or models would be added to an encrypted block along with additional information, such as a device ID, a unique user ID, user identity information, algorithm / sensor type / version information, date and time , GPS information and / or other data.

Petition 870190026446, of 03/20/2019, p. 107/137

103/113 [0276] The block can be added to the 1940 block chain, where it is stored. If the user tries to open the application again or provides the public key or a unique user identifier that matches the public key of the block in another application, then the user is again presented with the biometric data capture interface through which the user again presents its biometric data to the 1619 sensor or 1914 camera. The captured biometric data can again be optionally converted to a biometric model on the 1912 device. Then, the user's previous block is requested from the 1940 block chain and is downloaded to the 1912 smart device, where a private key can be kept in the application to decrypt the block. The biometric data and / or model (s) of the block can now be compared with the recently captured biometric data and / or biometric model (s). If a match is found, then the user will be authenticated and will have access to the application, will be able to make a transaction etc. and successful block decoding and model matching can be recorded with any combination of data, transaction, original model, most recently matched model, or both can be stored in the new block.

[0277] In addition or as an alternative to the comparison and matching being done on the 1912 device, the comparison and matching can be completed on the registration servers of the 1940 block chain. In this case, the biometric data obtained on the 1912 user device and / or biometric models generated on the 1912 user device from the biometric data are encrypted and sent to the 1940 block chain registration servers. Then, the public key and the private decryption key can be sent to the registration servers. 1940 block chain to decrypt one or more previous blocks of the user's biometric information and / or models, as well as to decrypt the most recently biometric data and / or models

Petition 870190026446, of 03/20/2019, p. 108/137

104/113 sent. The 1940 block chain record servers then run the matching algorithms to determine whether the biometric information and / or models stored in the block and the most recently collected biometric information and / or models are considered compatible by the limits previously defined in the algorithm of correspondence. By providing model matching on all 1940 block chain log servers (which can be hundreds or thousands of servers), an account provider can be sure that the 1912 device running in the application has not been compromised if the corresponding results are the same as the 1940 block chain log servers. The 1912 device and all 1940 block chain log servers would have to be compromised at the same time for a hacker to change all of them, which, of course, would be highly unlikely, if not impossible.

[0278] In yet another modality, a dedicated 1950's “mail server” could be employed, to which a copy of both the biometric information and / or models recently collected from the device and the biometric information and / or models in the block would be sent. The 1912 device can provide the decryption key directly to the corresponding 1950 server, or the 1940 block chain can be instructed to send the encrypted biometric model (s) to the corresponding server with a “smart contract” ”, Which is a set of computer instructions encoded in the block. This is a characteristic of block chains with decentralized processing skills like Ethereum.

[0279] It is also provided that when a new device requests a lock using a unique user ID, for example, an email address, phone number or public key, the device is only allowed to download blocks on the string that contains user biometric templates that are associated with this unique ID because the device contains private keys.

Petition 870190026446, of 03/20/2019, p. 109/137

105/113

Thus, the latest user models can be compared with all models that have been captured and stored in the block chain, allowing for multiple matches. This can provide less false rejections from the correct users that can result from changes in appearance due to lighting, aging, makeup, hair, beard, glasses etc.

[0280] In a system configuration and method disclosed here, there is a private key and the private key will decrypt the contents of the block, but the biometric data within the block is what is used in the comparison to determine whether there is a match between new ones biometric data and stored biometric data. Thus, the private key is required to gain access to the biometric data block. The private key can be created by the user, by the system, or the private key can correspond to a combination of unique identifiers that are easier to remember, a phone number, social security number, an email address and a date of birth etc. and thus also exclusive to the user. In this configuration, it is possible and contemplated that there are two block chains, one with personal data contained therein, and one with anonymous storage of biometric models only. The blocks of personal data in the first block chain would be decrypted by a private key or a combination of corresponding personal data that only you know, and that you share only with specific vendors that you want to be able to verify that identity, then in that data, the number from another block (s) with your biometric data is attached to that record and then the application can unlock that block and associate / update your newly loaded biometric data to the data in that biometric block.

[0281] In addition to biometric correspondence, the application that collects biometric data can perform life proof tests on the collected biometric data, such as those described above. If the user is shown to exhibit traits that would normally

Petition 870190026446, of 03/20/2019, p. 110/137

106/113 exist only in living human beings, at the exact moment that identity is verified, so the biometric data can be trusted as being from a real human being, not from a non-living object, such as a photo forgery or video.

[0282] Figure 20 is a schematic of a computing or mobile device, or server, such as one of the devices described above, according to an exemplary embodiment. Figure 20 shows an example of a 2070 computing device and a 2050 mobile computing device, which can be used with the techniques described here. The 2070 computing device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes and other appropriate computers. The computing device 2050 is intended to represent various forms of mobile devices, such as personal digital assistants, cell phones, smartphones and other similar computing devices. The components shown here, their connections and relationships, and their functions, should be exemplary only and should not limit the implementations described and / or claimed in this document.

[0283] The 2070 computing device includes a 2002 processor, 2004 memory, a 2006 storage device, a 2008 high speed interface or controller connecting to the 2004 memory and 2010 high speed expansion ports and a low speed interface or controller 2012 connected to low speed bus 2014 and storage device 2006. Each of the components 2002, 2004, 2006, 2008, 2010 and 2012 is interconnected using several buses and can be mounted on a common motherboard or in other ways, as appropriate. The 2002 processor can process instructions for execution within the 2070 computing device, including instructions stored in memory 2004 or on storage device 2006 to display graphical information for a GUI on an external input / output device, such as

Petition 870190026446, of 03/20/2019, p. 111/137

107/113 as the 2016 display coupled to the 2008 high speed controller. In other implementations, multiple processors and / or multiple buses can be used, as appropriate, along with multiple memories and memory types. In addition, multiple 2070 computing devices can be connected, with each device providing parts of the necessary operations (for example, such as a server bank, a group of blade servers or a multiprocessor system).

[0284] The 2004 memory stores information within the 2070 computing device. In an implementation, the 2004 memory is a unit or units of volatile memory. In another implementation, the 2004 memory is a unit or units of non-volatile memory. The 2004 memory can also be another form of computer-readable medium, such as a magnetic or optical disk.

[0285] The 2006 storage device is capable of providing mass storage for the 2070 computing device. In one implementation, the 2006 storage device can be or contain a computer-readable medium, such as a hard disk device, a optical disk device or tape device, flash memory or other similar solid state memory device or array of devices, including devices on a storage area network or other configurations. A computer program product can be tangibly incorporated into an information carrier. The computer program product may also contain instructions that, when executed, perform one or more methods, such as those described above. The information carrier is a computer or machine-readable medium, such as memory 2004, storage device 2006 or memory in processor 2002.

[0286] The 2008 high-speed controller manages bandwidth-intensive operations for the 2070 computing device, while the 2012 low-speed controller manages low-power intensive operations.

Petition 870190026446, of 03/20/2019, p. 112/137

108/113 bandwidth. This allocation of functions is only exemplary. In one implementation, the high-speed controller 2008 is coupled to the memory 2004, display 2016 (for example, through a processor or graphics accelerator) and to high-speed expansion ports 2010, which can accept multiple expansion cards (not shown) ). In the implementation, the low speed controller 2012 is coupled to the storage device 2006 and the low speed bus 2014. The low speed bus 2014, which can include multiple communication ports (for example, USB, Bluetooth, Ethernet, Ethernet without wire) can be coupled to one or more input / output devices, such as a keyboard, pointing device, scanner, or network device, such as a switch or router, for example, via a network adapter.

[0287] The 2070 computing device can be implemented in several different ways, as shown in the figure. For example, it can be implemented as a standard 2020 server or multiple times on a group of those servers. It can also be implemented as part of a 2024 rack server system. In addition, it can be implemented on a personal computer, such as a 2022 laptop. Alternatively, the components of the 2070 computing device can be combined with other components on a device mobile (not shown), such as the 2050 device. Each of these devices can contain one or more computing devices 2070, 2050, and an entire system can consist of multiple computing devices 2070, 2050 that communicate with each other.

[0288] The computing device 2050 includes a processor 2052, memory 2064, an input / output device, such as a display 2054, a communication interface 2066 and a transceiver 2068, among other components. The 2050 device may also be provided with a storage device, such as a microdrive or other device, to provide additional storage. Each one of

Petition 870190026446, of 03/20/2019, p. 113/137

109/113 components 2050, 2052, 2064, 2054, 2066 and 2068 are interconnected using multiple busbars, and several of the components can be mounted on a common motherboard or in other ways, as appropriate.

[0289] The 2052 processor can execute instructions within the 2050 computing device, including instructions stored in the 2064 memory. The processor can be implemented as a chip set that includes separate and multiple analog and digital processors. The processor can provide, for example, coordination of the other components of the 2050 device, such as control of user interfaces, applications run by the 2050 device and wireless communication by the 2050 device.

[0290] The 2052 processor can communicate with a user via the 2058 control interface and the 2056 display interface coupled with a 2054 display. The 2054 display can be, for example, a TFT LCD (Film Transistor Liquid Crystal Display) Thin) or an OLED (Organic Light Emitting Diode) display, or other appropriate display technology. The display interface 2056 may comprise a circuit suitable for triggering the display 2054 to present graphical and other information to a user. The 2058 control interface can receive commands from a user and convert them for sending to the 2052 processor. In addition, an external 2062 interface can be provided in communication with the 2052 processor, in order to allow communication of the area close to the 2050 device. with other devices. The external interface 2062 can provide, for example, cable communication in some implementations, or wireless communication in other implementations, and multiple interfaces can also be used.

[0291] The 2064 memory stores information within the 2050 computing device. The 2064 memory can be implemented as one or more of a computer-readable medium or media, a volatile memory unit or units or a non-volatile memory unit or units . The 2074 expansion memory

Petition 870190026446, of 03/20/2019, p. 114/137

110/113 can also be provided and connected to the 2050 device via the 2072 expansion interface, which may include, for example, a SIMM (Single Line Memory Module) interface. Such 2074 expansion memory can provide extra storage space for the 2050 device, or it can also store applications or other information for the 2050 device. Specifically, the 2074 expansion memory can include instructions for performing or supplementing the processes described above and can also include secure information. So, for example, the 2074 expansion memory can be provided as a security module for the 2050 device and can be programmed with instructions that allow the safe use of the 2050 device. In addition, secure applications can be provided via SIMM cards, along with additional information, such as placing identification information on the SIMM card in a way that cannot be hacked.

[0292] The memory can include, for example, flash memory and / or NVRAM memory, as discussed below. In an implementation, a computer program product is tangibly embedded in an information carrier. The computer program product contains instructions that, when executed, perform one or more methods, such as those described above. The information carrier is a computer- or machine-readable medium, such as memory 2064, expansion memory 2074 or memory in processor 2052, which can be received, for example, by transceiver 2068 or external interface 2062.

[0293] The 2050 device can communicate wirelessly via the 2066 communication interface, which can include digital signal processing circuits when needed. The 2066 communication interface can provide communications under various modes or protocols, such as GSM, SMS, EMS voice calls or MMS, CDMA, TDMA, PDC, WCDMA, CDMA2000 or GPRS messages, among others. Such communication can take place, for example, through the

Petition 870190026446, of 03/20/2019, p. 115/137

111/113 radio frequency 2068. In addition, short-range communication may occur, such as using a Bluetooth, Wi-Fi or other transceiver (not shown). In addition, the 2070 GPS (Global Positioning System) reception module can provide additional wireless data related to navigation and location to the 2050 device, which can be used as appropriate by applications running on the 2050 device.

[0294] The 2050 device can also communicate audibly using the 2060 audio codec, which can receive spoken information from a user and convert it into usable digital information. The 2060 audio codec can also generate audible sound for a user, such as through a loudspeaker, for example, on a portable device on the 2050 device. This sound may include sound from voice phone calls, may include recorded sound (e.g., voice messages, music files, etc.) and can also include sound generated by applications operating on the 2050 device.

[0295] The 2050 computing device can be implemented in a variety of different ways, as shown in the figure. For example, it can be implemented as a 2080 cell phone. It can also be implemented as part of a 2082 smartphone, personal digital assistant, tablet or other similar mobile device.

[0296] In this way, various implementations of the systems and techniques described here can be performed on specially designed digital electronic circuits, integrated circuits, ASICs (specific application integrated circuits), computer hardware, firmware, software and / or combinations thereof. These various implementations may include implementation in one or more computer programs that are executable and / or interpretable in a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions to and from transmit data

Petition 870190026446, of 03/20/2019, p. 116/137

112/113 and instructions for a storage system, at least one input device and at least one output device.

[0297] These computer programs (also known as programs, software, software applications or code) include machine instructions for a programmable processor and can be implemented in a high-level procedural and / or object-oriented programming language, and / or assembly language / machine. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus and / or device (for example, magnetic disks, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0298] To provide interaction with a user, the systems and techniques described here can be implemented on a computer with a display device (for example, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor to display information for the user, and a keyboard and pointing device (for example, a mouse or a trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with a user, for example , the feedback provided to the user can be any form of sensory feedback (for example, visual feedback, auditory feedback or tactile feedback), and user input can be received in any form, including acoustic, speech or tactile feedback.

[0299] The systems and techniques described here can be implemented in a computing system (for example, 2070 and / or 2050 computing device) that includes a back-end component (for example, as a data server) or

Petition 870190026446, of 03/20/2019, p. 117/137

113/113 that includes a middleware component (for example, an application server) or that includes a front-end component (for example, a client computer with a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here) or any combination of such back-end, middleware or front-end components. The system components can be interconnected by any form or means of communication of digital data (for example, a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN") and the Internet.

[0300] The computing system can include clients and servers. A client and a server are usually remote with each other and usually interact through a communication network. The client and server relationship arises because of computer programs running on the respective computers and having a client-server relationship between them.

[0301] Although various modalities of the invention have been described, it will be apparent to those skilled in the art that many more modalities and implementations are possible, which are within the scope of the present invention. In addition, the various features, elements and modalities described herein can be claimed or combined in any combination or arrangement.

Petition 870190026446, of 03/20/2019, p. 118/137

Claims (20)

1. Method to verify biometric authentication, CHARACTERIZED by the fact that it comprises: receiving root biometric identification information, corresponding to a user, from a reliable biometric information source to establish root biometric identification information that is reliable and verified; store the root biometric identification information in a database; subsequently, during an authentication process: capture a first image with an authentication camera, the first image captured when the user is at a first distance from the authentication camera; capture a second image with the authentication camera, the second image captured when the user is a second distance from the authentication camera, such that the first distance is different from the second distance; process the first image to create the first biometric authentication information; process the second image to create second biometric authentication information; compare the first biometric authentication information with the second biometric authentication information; comparing the root biometric identification information with the first biometric authentication information, the second biometric authentication information, or both; authenticate the user when: the comparison determines that the first biometric authentication information corresponds to the second biometric authentication information within Petition 870190007917, of 01/24/2019, p. 112/137 2/5 of a limit, but they are not identical; the comparison determines that the root biometric identification information corresponds to the first biometric authentication information, the second biometric authentication information, or both within a limit. 2. Method, according to claim 1, CHARACTERIZED by the fact that the authentication camera is one of the following types of camera: camera on a user's mobile device, camera on a user's computer, camera on an ATM, camera at a commercial point of sale and camera at a financial institution. 3. Method, according to claim 2, CHARACTERIZED by the fact that the source of reliable biometric information is a first camera in a reliable source. 4. Method, according to claim 3, CHARACTERIZED by the fact that the first camera is located in a financial institution. 5. Method, according to claim 3, CHARACTERIZED by the fact that the first camera is located in a government agency office. 6. Method, according to claim 3, CHARACTERIZED by the fact that an authentication server receives the root biometric identification information, the first biometric authentication information and the second biometric authentication information and the authentication server performs the comparison. 7. Method, according to claim 1, CHARACTERIZED by the fact that the first image and the second image are of the user's face. 8. Method, according to claim 7, CHARACTERIZED by the fact that one of the first image and the second image is distorted due to barrel-type distortion. 9. Method, according to claim 1, CHARACTERIZED by the fact that it still comprises performing one or more life proof tests (liveness) Petition 870190007917, of 01/24/2019, p. 113/137 3/5 additional in the first image or the second image to verify that the user is a living person during the authentication process. 10. Method for verifying a user's biometric authentication, CHARACTERIZED by the fact that it comprises: store the user's root biometric identification information obtained from a trusted biometric detection device that is located in a trusted location to establish the root biometric identification information as trusted and verified; during an authentication session: receive root biometric identification information; receiving biometric user authentication identification information from a computing device during an authentication session; compare the root biometric identification information with the authentication biometric identification information; and authenticating the user when the root biometric identification information matches the authentication biometric identification information within a predetermined limit. 11. Method, according to claim 10, CHARACTERIZED by the fact that the reliable biometric detection device is in one of the following locations: financial institution, commercial point of sale or government entity. 12. Method, according to claim 10, CHARACTERIZED by the fact that the computing device used during an authentication session is located in a financial institution, ATM, commercial point of sale, or is the user's or mobile device personal user. 13. Method, according to claim 10, CHARACTERIZED by the fact that the reliable biometric detection device includes a camera, and the computing device used during an authentication session includes a Petition 870190007917, of 01/24/2019, p. 114/137 4/5 camera. 14. Method, according to claim 10, CHARACTERIZED by the fact that the root biometric identification information and the biometric authentication identification information are based on a facial image of the user and at least one other item of biometric information. 15. Method, according to claim 10, CHARACTERIZED by the fact that it still comprises: capture biometric identification information for user complementary authentication during the authentication session; compare complementary authentication biometric identification information with authentication biometric identification information; compare the biometric identification information of complementary authentication with the root biometric identification information; authenticate the user when: the comparison determines that the biometric authentication identification information corresponds to the complementary biometric authentication information within a first limit, but they are not identical; the comparison determines that the root biometric identification information corresponds to the complementary authentication biometric information within the predetermined limit. 16. Identity authentication system, CHARACTERIZED by the fact that it comprises: a first computing device configured to request and receive root biometric identification information, for a user, from a trusted source, the trusted source comprising an entity affiliated with the government or a financial institution; a second computing device configured to, during a Petition 870190007917, of 01/24/2019, p. 115/137 5/5 authentication session: create biometric authentication information captured from the user during the authentication session; compare the biometric authentication information with the root biometric identification information; perform a proof of life determination on the user during the authentication session using biometric authentication information; in response to the comparison and execution, authenticate the user if: the comparison determines that the biometric authentication information matches the root biometric identification information within a limit; and the determination of proof of life to determine that the user is a living person. 17. System, according to claim 16, CHARACTERIZED by the fact that the biometric root identification information is derived from an image. 18. System, according to claim 17, CHARACTERIZED by the fact that an image of the user may not be recreated from the root biometric identification information. 19. System according to claim 16, CHARACTERIZED by the fact that the first computing device and the second computing device are the same computing device. 20. System, according to claim 16, CHARACTERIZED by the fact that the biometric authentication information is derived from at least a first image and a second image that are captured by a camera associated with the second computing device, the first image captured by the camera located at a first distance from the user and the second image captured by the camera located at a second distance from the user, the second distance less than the first distance, and the proof of life determination comprises determining that the second image has distortion barrel type compared to the first image.