WO2018001371A1 - 一种身份识别方法及装置 - Google Patents

一种身份识别方法及装置 Download PDF

Info

Publication number
WO2018001371A1
WO2018001371A1 PCT/CN2017/091264 CN2017091264W WO2018001371A1 WO 2018001371 A1 WO2018001371 A1 WO 2018001371A1 CN 2017091264 W CN2017091264 W CN 2017091264W WO 2018001371 A1 WO2018001371 A1 WO 2018001371A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
identified
target point
identity information
information database
Prior art date
Application number
PCT/CN2017/091264
Other languages
English (en)
French (fr)
Inventor
黄通兵
秦林婵
Original Assignee
北京七鑫易维信息技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京七鑫易维信息技术有限公司 filed Critical 北京七鑫易维信息技术有限公司
Priority to US16/312,301 priority Critical patent/US10891507B2/en
Priority to EP17819367.8A priority patent/EP3480727A4/en
Priority to AU2017287619A priority patent/AU2017287619B2/en
Priority to JP2018565013A priority patent/JP6762380B2/ja
Publication of WO2018001371A1 publication Critical patent/WO2018001371A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/18—Eye characteristics, e.g. of the iris
    • G06V40/197—Matching; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/18—Eye characteristics, e.g. of the iris
    • G06V40/193—Preprocessing; Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/40—Spoof detection, e.g. liveness detection
    • G06V40/45—Detection of the body part being alive
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/60—Static or dynamic means for assisting the user to position a body part for biometric acquisition
    • G06V40/67—Static or dynamic means for assisting the user to position a body part for biometric acquisition by interactive indications to the user
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition

Definitions

  • the present invention relates to the field of identity recognition technologies, and in particular, to an identity recognition method and apparatus.
  • the iris is an annular part between the black pupil and the white sclera that forms during the fetal development. For everyone, the structure of the iris is different and hardly changes throughout life. Therefore, the iris is widely used. It is applied to identification in various environments, but it is often the case that the forged iris is attached to the eye to achieve the purpose of deception. Therefore, when using the iris for identification, it is necessary to detect whether the iris is a living body.
  • the optical devices are added, and the light source is irradiated to the human eye to obtain a sequence in which the iris and the eyeball react under light excitation, such as stimulating pupil scaling, light reflection imaging, etc., and the obtained sequence and a preset reaction sequence threshold are obtained.
  • the comparison is performed to determine whether the object is a living body based on whether the obtained sequence is within the threshold.
  • the pupil zoom under the light excitation is also affected by mood, color, external light source and individual differences, which may easily lead to judgment errors, and the preset reaction sequence threshold is difficult to ensure adaptation in practical applications.
  • the method of using the human eye film is easy to fool the optical device, and therefore, the adaptability and the anti-counterfeiting performance are poor.
  • the purpose of the embodiments of the present invention is to provide an identification method and device, which solves the problem that the living body judging method using optical excitation is easy to judge errors in the related art, and the adaptability and anti-counterfeiting performance are poor. .
  • an embodiment of the present invention provides an identity recognition method, where the method includes:
  • the coordinates of the target point, the user identity information database, and the identification result, the user to be identified is subjected to the living body detection.
  • the embodiment of the present invention provides the first possible implementation manner of the foregoing first aspect, wherein the identifying the user according to the eye image and the pre-established user identity information database includes:
  • the identity information and calibration data corresponding to the iris feature are obtained from the user identity information database.
  • the embodiment of the present invention provides the second possible implementation manner of the foregoing first aspect, wherein the image according to the eye image, the coordinates of the target point, the user identity information database, and The result of the identification, the living detection of the user to be identified, including:
  • the theoretical gaze point coordinates of the user to be identified are calculated according to the eye movement feature and the acquired calibration data;
  • the embodiment of the present invention provides a third possible implementation manner of the foregoing first aspect, wherein the image according to the eye image, the coordinates of the target point, the user identity information database, and The result of the identification, the living detection of the user to be identified, including:
  • the calibration data of the user to be identified is calculated according to the eye movement feature and the coordinates of the target point;
  • the calibration data of the user to be identified is compared with the acquired calibration data to determine whether the user to be identified is a living user.
  • the embodiment of the present invention provides the fourth possible implementation manner of the foregoing first aspect, wherein the image according to the eye image, the coordinates of the target point, the user identity information database, and The result of the identification, the living detection of the user to be identified, including:
  • the calibration data of each user is retrieved from the user identity information database
  • the coordinates of the theoretical fixation point are compared with the coordinates of the target point, and it is determined whether the number of users to be identified is a living user.
  • the embodiment of the present invention provides the fifth possible implementation manner of the foregoing first aspect, wherein, before collecting the eye image when the user to be identified is gazing at the target point, the method further includes:
  • the target point is randomly generated on the display screen in chronological order, and a target point is displayed on the display screen at each time and the position of the target point is random;
  • generating a target point on the display screen according to the chronological order and the preset position sequence.
  • a target point is displayed on the display at each time and the position of the target point is set by the preset position sequence.
  • an embodiment of the present invention provides an identity recognition apparatus, where the apparatus includes:
  • An acquisition module configured to collect an eye image when the user to be identified looks at the target point
  • An identity recognition module configured to identify a user to be identified according to an eye image and a pre-established user identity information database
  • the living body detecting module is configured to perform living body detection on the user to be identified according to the eye image, the coordinates of the target point, the user identity information database, and the identity recognition result.
  • the identity recognition module includes:
  • An extracting unit configured to extract an eye feature from the eye image, the eye feature including an iris feature and an eye movement feature;
  • a first determining unit configured to determine whether an iris feature is included in the user identity information database
  • an obtaining unit configured to acquire identity information and calibration data corresponding to the iris feature from the user identity information database in a case where the iris feature is included in the user identity information database.
  • the embodiment of the present invention provides the second possible implementation manner of the foregoing second aspect, wherein the living body detection module includes:
  • a calculating unit configured to calculate a theoretical gaze point coordinate of the user to be identified according to the eye movement feature and the acquired calibration data when the identification result indicates that the user identity information database includes the iris feature;
  • the second determining unit is configured to compare the coordinates of the theoretical fixation point with the coordinates of the target point, and determine whether the user to be identified is a living user.
  • the embodiment of the present invention provides a third possible implementation manner of the foregoing second aspect, wherein the living body detection module includes:
  • a calculating unit configured to calculate calibration data of the user to be identified according to the eye movement feature and the coordinates of the target point when the identification result indicates that the user identity information database includes the iris feature;
  • the second determining unit is configured to compare the calibration data of the user to be identified with the acquired calibration data, and determine whether the user to be identified is a living user.
  • the embodiment of the present invention provides the fourth possible implementation manner of the foregoing second aspect, wherein the living body detection module includes:
  • a calculating unit configured to: when the identification result indicates that the user identity information database includes an iris feature, retrieve calibration data of each user from the user identity information database; according to the eye movement feature and the calibration data of each user retrieved, Calculate the coordinates of the theoretical fixation point;
  • the second determining unit is configured to compare the coordinates of the theoretical fixation point with the coordinates of the target point, and determine whether the number of users to be identified is a living user.
  • the embodiment of the present invention provides the fifth possible implementation manner of the foregoing second aspect, wherein the device further includes:
  • a first generating module configured to randomly generate a target point on the display screen in chronological order, and display a target point on the display screen at each time and the position of the target point is random;
  • the second generating module is configured to generate a target point on the display screen according to the chronological order and the preset position order, and each time the display screen displays a target point position and the position of the target point position is a preset position sequence. Set.
  • an embodiment of the present invention provides a storage medium, where the storage medium includes a stored program, where the device where the storage medium is located is controlled to execute the foregoing identity recognition method when the program is running.
  • an embodiment of the present invention provides a processor, where a processor is configured to run a program, where the program is executed to execute the foregoing identity recognition method.
  • an embodiment of the present invention provides a terminal, including: an acquisition module, configured to collect an eye image when a user to be identified is gazing at a target point; and an identity recognition module, configured to use the eye image and a pre-established user
  • the identity information database identifies the user to be identified
  • the living body detection module is configured to perform living body detection on the user to be identified according to the eye image, the coordinates of the target point, the user identity information database, and the identity recognition result
  • the processor and the processor operate The program, wherein the program execution method performs the above identification method on data output from the acquisition module, the identity recognition module, and the living body detection module.
  • an embodiment of the present invention provides a terminal, including: an acquisition module, configured to collect an eye image when a user to be identified is gazing at a target point; and an identity recognition module, configured to use an eye image and a pre-established user
  • the identity information database identifies the user to be identified
  • the living body detection module is configured to perform living body detection on the user to be identified according to the eye image, the coordinates of the target point, the user identity information database, and the identity recognition result
  • the storage medium is used for storage a program, wherein the program performs the above identification method on data output from the acquisition module, the identification module, and the living body detection module at runtime.
  • the method and device for identifying an identity include: collecting an eye image when the user to be identified is looking at the target point; and identifying the user to be identified according to the eye image and the pre-established user identity information database; According to the eye image, the coordinates of the target point, the user identity information database, and the identification result, the user to be identified is allowed to live. Body detection.
  • the eye tracking technology is combined with the identity recognition technology.
  • FIG. 1 is a flowchart of an identity recognition method according to Embodiment 1 of the present invention.
  • FIG. 2 is a schematic structural diagram of an identity recognition apparatus according to Embodiment 2 of the present invention.
  • an embodiment of the present invention provides an identification method and apparatus, which are described below by way of embodiments.
  • the embodiment of the invention provides an identification method, which combines the eye tracking technology with the iris recognition technology, and the eye tracking technology extracts the eye image of the user to be identified while collecting the eye image when the user is looking at the target point. Iris feature and eye movement feature, the iris recognition is performed on the identified user and the calibration data is retrieved, and the coordinates of the target point are combined to determine whether the user to be identified is a living user, and the iris to be identified is successfully identified and the user to be identified is determined to be a living user. Then, it is determined that the identity of the user to be identified is successful.
  • the identification method provided by the embodiment of the invention has high accuracy, adaptability and anti-counterfeiting performance.
  • the identity identification method provided by the embodiment of the present invention can be applied to a scenario of a bank access control, a prison access control, a password payment, and the like.
  • an identity information database of the application scenario authorized user needs to be established. For example, if the above identification method is applied to the bank's access control, it is necessary to establish a database of identity information of the bank employee for identifying the bank employee. When the bank employee identification is passed, the bank door is opened, and the employee can Enter, if the above identification method is applied to the prison access control, it is necessary to establish a database of identity information of the prison guard.
  • Establishing a database of user identity information includes the following steps: acquiring iris characteristics of the user, calibration data, and identity information of the user; and selecting iris characteristics, calibration data, and identity information of the user and The corresponding relationship is stored in the user identity information database.
  • the iris features include features such as spots, filaments, crowns, stripes, and crypts of the user's iris.
  • the calibration data is calculated based on the eye movement characteristics and the coordinates of the fixation points when the user looks at one or more sets of specific target points. User individual feature data.
  • the above specific target points may be the four corners of the display screen and the five target points displayed in the center, or the four corners on the display screen, the center of the four sides, and the nine target points displayed in the center of the display screen. Bit, the above specific target point is recorded as a calibration point.
  • the above calibration point can also be a target point at other positions on the display screen, and the number and position of the above-mentioned one calibration point can be based on the actual application scenario. Make settings.
  • the calibration points are continuously generated on the display screen in chronological order, one calibration point is displayed each time, the calibration eye image when the user eyes are gazing at the calibration point is obtained, and the user's iris feature is extracted from the collected calibration eye image.
  • eye movement features include, but are not limited to, features such as spots, filaments, crowns, stripes, and crypts.
  • the eye movement feature is an eye feature acquired when the user looks at the calibration point, including but not limited to the eye corner of the user, the center position of the pupil, the size of the pupil radius, and the eye features such as the Purcelle formed by the corneal emission.
  • the user's calibration data is obtained according to the eye movement characteristics and calibration point information when the user looks at one or more sets of calibration points, and the calibration data includes, but is not limited to, eye characteristic data such as the angle between the user's visual axis and the optical axis. .
  • the identity information of the user including but not limited to the user's name, ID number, gender, position, etc., establishing the identity information of the user, the iris feature, and the correspondence of the calibration data. Relationship, and store the user's identity information, iris characteristics, calibration data and their corresponding relationships in the user identity information database.
  • the user to be identified needs to be gaze at the target point, and the target point may be a series of target points displayed on the display screen, or may be a fixed position. Display target points, for example, on the wall, glass door Superior, it can also be an object at a certain location.
  • the above display screen can also display a virtual keyboard, which can be a numeric keypad consisting of 0-9 ten digits, or an alphabetic keyboard composed of 26 English letters, or It is an alphanumeric keyboard consisting of 0-9 ten digits and 26 English letters, and the group of letters or numbers on the above virtual keyboard is random, and the user to be identified can look at the keys on the virtual keyboard.
  • the method enters a pre-agreed password, for example, the pre-agreed password is 123, and the user to be identified sequentially looks at the numeric key 123 on the virtual keyboard in order, or may also be the user to be identified to follow the indication on the virtual keyboard.
  • Keys indicate that the user to be identified looks at the 3, 6, and 9 numeric keys on the virtual keyboard in sequence, or the P, M, V, etc., etc., and the above may indicate the user's gaze by voice.
  • the letters or numbers on the virtual keyboard can also be the letters or numbers on the display that show the virtual keyboard that the user needs to look at.
  • Some of the graphics may also be displayed on the display screen, and the user to be identified looks at certain parts of the graphic on the display screen according to the indication.
  • the target point to be recognized by the user to be identified is the target point displayed on the display
  • the target point needs to be generated on the display.
  • the target point generated on the display screen includes the following two situations: the target point is randomly generated on the display screen in chronological order, and a target point is displayed on the display screen at each time and the position of the target point is random; Alternatively, the target point is generated on the display screen in chronological order and preset position order, and a target point is displayed on the display screen at each time and the position of the target point is set by the preset position sequence.
  • the preset position sequence is a preset sequence of multiple positions. Each time the user to be identified is identified, a sequence of positions is randomly selected, and a target point is generated according to a randomly selected sequence of positions on a corresponding position on the display screen.
  • the identity recognition method provided by the embodiment of the present invention is used to identify the user, as shown in FIG. 1 , and the specific steps include S110-S130.
  • S110 Collect an eye image when the user to be identified looks at the target point.
  • the user to be identified may click the start button to identify the user to be identified, or when the eye of the user to be recognized enters the area of image collection. Internally, the identified user is automatically identified.
  • the user's eye image can be collected at a certain frame rate, so that multiple eye images are acquired when the user to be recognized looks at a target point.
  • the eye image of the user to be recognized is collected, the eye image of the user to be recognized is included in the collected eye image, and if the eye image of the user to be recognized is not included in the collected eye image, The eye of the user to be identified may not be aligned with the image capturing device, and the user is prompted to adjust the position to re-acquire the image. If the collected eye image includes the eye region of the user to be identified, the user to be identified is identified.
  • the collected eye image may be processed by interference suppression or the like.
  • S120 Identify the user to be identified according to the eye image and the pre-established user identity information database.
  • the process of identifying the user to be identified is actually a process of identifying the user for iris recognition.
  • the method for identifying the user to be identified includes the following steps: extracting an eye feature from the eye image, the eye feature includes an iris feature and an eye movement feature; determining whether the iris feature is included in the user identity information database; if yes, The identity information and the calibration data corresponding to the iris feature are obtained in the user identity information database.
  • the center position of the pupil of the eye to be recognized, the radius of the pupil, the corner of the eye, and the angle of the eye are extracted from the eye image.
  • Eye movement characteristics such as Purkin's plaque formed by corneal emission, and iris features such as spots, filaments, crowns, and crypts of the eyes of the user to be identified are extracted.
  • the identity of the user to be identified is determined.
  • the recognition fails. At this time, the eye image of the user to be identified when the target point is gazing can be re-acquired, and the user to be identified is identified.
  • the iris feature extracted from the eye image of the user to be identified is matched with the iris feature stored in the user identity information database, and it is determined whether the user identity information database has the extracted user to be identified.
  • the iris feature is consistent with the iris feature. If there is an iris feature consistent with the extracted iris feature of the user to be identified, it is determined that the iris recognition is successful, and the iris identity corresponding to the user to be identified is retrieved from the user identity information database.
  • the identity information and the calibration data determine the identity information corresponding to the iris feature as the identity information of the user to be identified.
  • the user identity information database does not store the iris feature of the user to be identified, that is, the user to be identified is an unauthorized user.
  • the identity of the user to be identified fails.
  • the user to be identified can perform identity verification by the administrator. After the identity verification is passed, the iris feature, the calibration data, and the identity information of the user of the user to be identified are entered.
  • the user to be identified Since the user to be identified is in the process of gazing at the target point, multiple eye images of the user to be identified are collected, so that the user may be identified multiple times by the iris recognition. In the process of multiple iris recognition, as long as the iris recognition occurs once If successful, it can be determined that the iris recognition of the user to be identified is successful, that is, the identity information and the calibration data corresponding to the iris feature exist in the user number identity information database.
  • q iris features are randomly selected, and q iris recognition is performed, wherein q is smaller than the mesh displayed on the display screen.
  • the number of punctuation points, in the process of q-time iris recognition, as long as the recognition succeeds m times, it can be judged that the iris recognition of the user to be recognized is successful, and m can be calculated by the following formula (1) or formula (2).
  • m is the number of successful iris recognition
  • q is the number of iris recognition
  • q is an odd number
  • q It is even.
  • S130 Perform a living body detection on the user to be identified according to the eye image, the coordinates of the target point, the user identity information database, and the identity recognition result.
  • the identity recognition method provided by the embodiment of the present invention also needs to perform living body detection on the user to be identified.
  • the coordinates of the target point are the coordinates of the target point being displayed, and the coordinates of the target point can be calculated according to the relative position of the target point and the calibration point or other specific points or objects.
  • the living detection is performed on the user to be identified, and the living detection of the user to be identified includes two cases:
  • the theoretical gaze point coordinates of the user to be identified are calculated; the coordinates of the theoretical gaze point are compared with the coordinates of the target point, and it is determined whether the user to be identified is a living user.
  • the data of the angle between the visual axis and the optical axis is used as the calibration data of the user, and the pupil position, the pupil radius, and The Purcelle or the like formed by the corneal reflection serves as an eye movement feature of the extracted user.
  • the calibration data can be calculated by the calibration data of the eye movement characteristics such as the pupil position, the pupil radius, the corneal reflection, and the angle of the visual axis and the optical axis corresponding to the iris feature of the user to be identified.
  • a theoretical gaze point coordinate the calculated coordinates of the theoretical gaze point of the user to be identified are compared with the coordinates of the target point, and it is determined whether the theoretical gaze point falls within the range of the target point, and the range is The target area is the center of the preset area, which is an acceptable error area range. If the theoretical gaze point falls within the area of the target point and continues for a preset length of time, it is determined that the target point is successfully identified. After the above target point recognition is successful, the next target point will be generated on the display screen, and the gaze point identification of the target point appearing on the display screen is performed by the above method, and the user to be identified continuously pairs the preset number of target points. If the identification is successful, it is determined that the user to be identified is a living user, and the preset number of target points is any number of target points greater than or equal to 3. The embodiment of the present invention does not limit the specific number of the preset number.
  • the preset time length is greater than or equal to the response time of the human eye following the target point, and is less than or equal to the display time of the target point.
  • the preset time length is greater than or equal to 0.1 second.
  • the preset time length is 0.5. -1.5 seconds between.
  • the preset ratio may be set and modified according to the accuracy requirement of the identification. Generally, the preset ratio is greater than 50%. Preferably, the preset ratio is between 50% and 70%, which is not in the embodiment of the present invention. The specific value of the preset ratio is limited.
  • the school to be identified is calculated based on the eye movement characteristics and the coordinates of the target point. Quasi-data; the calibration data of the user to be identified is compared with the acquired calibration data to determine whether the user to be identified is a living user.
  • the angle between the visual axis of the eye and the optical axis is constant. Therefore, the data of the angle between the visual axis and the optical axis is used as the calibration data of the user, and the pupil position, the pupil radius, and The Purcelle or the like formed by the corneal reflection serves as an eye movement feature of the extracted user.
  • the target point on the display is the actual gaze point coordinate of the user to be identified. The coordinates of the target point can be calculated according to the relative position of the target point and the calibration point or other specific points or objects.
  • the eye axis and the optical axis of the user to be identified are calculated by extracting the eye movement characteristics such as the pupil position, pupil radius and corneal reflection of the user to be recognized and the actual fixation point coordinates of the user, that is, the coordinates of the target point.
  • Calibration data such as the angle of the angle.
  • the calibration data corresponding to the iris feature of the user to be identified is retrieved from the pre-established user identity information database, and the calculated calibration data is compared with the acquired calibration data, if the calculation is performed.
  • the obtained calibration data falls within the error range of the retrieved calibration data and continues for a preset length of time, and it is considered that the user to be identified is looking at the target point on the display screen, that is, the target point is successfully identified.
  • the next target point will be displayed on the display screen, and the target point appearing on the display screen is identified by the above method, and the user to be identified continuously recognizes the preset number of target points. If the number of the target points is any number of target points greater than or equal to 3, the preset number of the specific number is not limited in the embodiment of the present invention.
  • the preset time length is greater than or equal to the response time of the human eye following the target point, and is less than or equal to the display time of the target point.
  • the preset time length is greater than or equal to 0.1 second.
  • the preset time length is 0.5. -1.5 seconds between.
  • the preset ratio may be set and modified according to the accuracy requirement of the identification. Generally, the preset ratio is greater than 50%. Preferably, the preset ratio is between 50% and 70%, which is not in the embodiment of the present invention. The specific value of the preset ratio is limited.
  • the user is authenticated by the calibration data corresponding to the iris feature of the user to be identified from the user identity information database, and the calibration data of all users is retrieved from the user identity information database.
  • the user performs a living body test.
  • the calibration data of each user is retrieved from the identity information database; and the theoretical gaze is calculated according to the eye movement feature and the calibration data of each user retrieved.
  • Point coordinates compare the coordinates of the theoretical fixation point with the coordinates of the target point, and determine whether the user to be identified is a living user.
  • the angle between the visual axis of the eye and the optical axis is constant. Therefore, the data of the angle between the visual axis and the optical axis is used as the calibration data of the user, and the pupil position, the pupil radius, and The Purcelle or the like formed by the corneal reflection serves as an eye movement feature of the extracted user.
  • the eye movements such as the pupillary spot formed by the pupil position, the pupil radius and the corneal reflection of the user to be identified are The characteristics are respectively calculated from calibration data such as the angle between the visual axis and the optical axis of each user in the pre-established user identity information database, and a plurality of theoretical fixation point coordinates can be obtained. Comparing the plurality of theoretical gaze point coordinates with the coordinates of the target point, respectively, determining whether there is a theoretical gaze point coordinate in the range of the plurality of theoretical gaze points in the range of the target point, the range of The target point is the center of the preset area, which is an acceptable error area range.
  • the target point is identified as At the same time, it is judged that the calibration data of the user acquired when calculating the coordinates of the theoretical fixation point is the calibration data of the user to be identified.
  • the next target point will be displayed on the display screen, and the target point appearing on the display screen is identified by the above method, and the user to be identified continuously recognizes the preset number of target points.
  • the user to be identified is determined to be a living user, wherein the preset number of target points is any number greater than or equal to 3.
  • the embodiment of the present invention does not limit the specific number of the preset number.
  • the eye images of the plurality of users to be recognized are continuously collected at a certain frame rate, and the theoretical gaze points calculated according to the eye images collected within the preset time length. If there is a preset ratio falling within the range of the target point, it is determined that the preset time length is continued, and the target point recognition is successful.
  • the preset time length is greater than or equal to the response time of the human eye following the target point, and is less than or equal to the display time of the target point.
  • the preset time length is greater than or equal to 0.1 second.
  • the preset time length is 0.5. -1.5 seconds between.
  • the preset ratio may be set and modified according to the accuracy requirement of the identification. Generally, the preset ratio is greater than 50%. Preferably, the preset ratio is between 50% and 70%, which is not in the embodiment of the present invention. The specific value of the preset ratio is limited.
  • the user is prompted to perform the identification again.
  • the number of identifications of the user to be identified reaches a preset number of times, the identity of the user to be identified is locked.
  • the preset number of times may be 3, and may be other values.
  • the specific value of the preset number of times may be set according to actual conditions, and the embodiment of the present invention does not The specific value of the preset number of times is defined.
  • the user's identity information and knowledge are displayed on the display.
  • a voice prompt may also be issued to prompt the identity of the user to be identified to be successful.
  • the identification failure and display again are displayed on the display.
  • the prompt of the identification, or when the identification of the user to be identified fails, may also issue a voice prompt, prompting the identification of the user to be identified to fail, and performing the second identification.
  • the user to be identified needs to be gazing on the display screen when identifying the user to be identified.
  • the calibration point is calculated, the calibration data of the user to be identified is calculated, and the calibration data, the iris characteristics of the user, the identity information and the corresponding relationship are stored in the user identity information database, and the process of inputting the calibration data of the user to be identified may be performed.
  • the user to be identified may be subjected to the living body detection according to the eye movement feature extracted from the acquired eye image and the calibration data of the user to be identified.
  • the identity recognition method provided by the embodiment of the present invention includes: collecting an eye image when the user to be identified looks at the target point; and identifying the user according to the eye image and the pre-established user identity information database; The image, the coordinates of the target point, the user identity information database, and the identification result, and the living detection is performed on the user to be identified.
  • the method provided by the invention combines the eye tracking technology and the identification technology. When the living detection and identification of the user to be identified are successful, the identification of the user to be identified is successful, the accuracy of the identification is high, and the adaptability and Anti-counterfeiting performance is very good.
  • the embodiment of the invention provides an identity recognition device.
  • the device comprises:
  • the collecting module 210 is configured to collect an eye image when the user to be identified looks at the target point;
  • the identity recognition module 220 is configured to identify the user to be identified according to the eye image and the pre-established user identity information database;
  • the living body detecting module 230 is configured to perform living body detection on the user to be identified according to the eye image, the coordinates of the target point, the user identity information database, and the identity recognition result.
  • the identity identification device provided by the embodiment of the present invention can be applied to a scenario of a bank access control, a prison access control, a password payment, and the like.
  • an identity information database of the application scenario authorized user needs to be established. For example, if the above identification method is applied to the bank's access control, it is necessary to establish a database of identity information of the bank employee for identifying the bank employee. When the bank employee identification is passed, the bank door is opened, and the employee can Enter, if the above identification method is applied to the prison access control, it is necessary to establish a database of identity information of the prison guard.
  • the foregoing collection module 210, the identity recognition module 220, and the living body detection module 230 may be run in a computer terminal as part of the device, and the functions implemented by the above module may be performed by a processor in the computer terminal, the computer terminal It can also be a smart phone (such as Android phone, iOS phone, etc.), tablet, PDA, and mobile Internet devices (MID), PAD and other terminal devices.
  • a smart phone such as Android phone, iOS phone, etc.
  • MID mobile Internet devices
  • the above-mentioned identity recognition module 220 performs identification on the user to be identified according to the image of the eye and the database of the user identity information that is pre-established, and is specifically implemented by the extraction unit, the first determination unit, and the acquisition unit, and includes:
  • the extracting unit is configured to extract an eye feature from the eye image, the eye feature includes an iris feature and an eye movement feature; the first determining unit is configured to determine whether the iris feature is included in the user identity information database; In the case that the iris feature is included in the user identity information database, the identity information and the calibration data corresponding to the iris feature are acquired from the user identity information database.
  • iris features include, but are not limited to, features such as spots, filaments, crowns, stripes, and crypts, including but not limited to the user's eye corners, pupil center position, pupil radius, and corneal emission. Eye features such as plaques.
  • the user to be identified Since the user to be identified is in the process of gazing at the target point, multiple eye images of the user to be identified are collected, so that the user may be identified multiple times by the iris recognition. In the process of multiple iris recognition, as long as the iris recognition occurs once If successful, it can be determined that the iris recognition of the user to be identified is successful, that is, the identity information and the calibration data corresponding to the iris feature exist in the user number identity information database.
  • q iris features are randomly selected, and q times iris recognition is performed, wherein q is smaller than the number of target points displayed on the display screen,
  • m can be calculated by the following formula (1) or formula (2).
  • m is the number of successful iris recognition
  • q is the number of iris recognition
  • q is an odd number
  • q It is even.
  • the above-mentioned extracting unit, the first judging unit and the obtaining unit may be operated in a computer terminal as part of the device, and the function implemented by the above module may be executed by a processor in the computer terminal, and the computer terminal may also be Smartphones (such as Android phones, iOS phones, etc.), tablets, PDAs, and mobile Internet devices (MID), PAD and other terminal devices.
  • Smartphones such as Android phones, iOS phones, etc.
  • MID mobile Internet devices
  • the living body detecting module 230 is based on the above-mentioned eye image, the coordinates of the target point, and the user's body.
  • the information database and the identification result, and the living detection of the user to be identified is specifically implemented by the calculation unit and the second judgment unit, including:
  • the calculating unit is configured to calculate, according to the eye movement feature and the acquired calibration data, a theoretical gaze point coordinate of the user to be recognized when the identity recognition result indicates that the user identity information database includes the iris feature; the second determining unit is configured to: Aligning the coordinates of the gaze point with the coordinates of the target point, and determining whether the user to be identified is a living user; the calculating unit may be configured to be used when the identity recognition result indicates that the user identity information database includes the iris feature.
  • the second determining unit may be further configured to compare the calibration data of the user to be identified with the acquired calibration data to determine the to-be-identified Whether the user is a living user; the calculating unit may be configured to: when the identification result indicates that the user identity information database includes the iris feature, retrieve calibration data of each user from the user identity information database; according to the eye movement feature And the calibration data of each user retrieved, the theory of calculation Viewpoint coordinates; second determination means may be provided for the theoretical coordinates of the fixation point are aligned with coordinates of the target point, it is determined whether the number of users to be identified in vivo users.
  • the identification of the iris and the detection of the living body are not successful at the same time, if the identification of the user to be identified fails, the user is prompted to perform the identification again.
  • the number of identifications of the user to be identified reaches a preset number of times, the identity of the user to be identified is locked. The identification is continued, and the user to be identified is determined to be an unauthorized user.
  • the preset number of times may be 3, and may be other values.
  • the specific value of the preset number of times may be set according to an actual situation, which is not limited by the embodiment of the present invention. The specific value of the above preset number of times.
  • the user's identity information and the prompt for identifying success are displayed on the display, or when the identity of the user to be identified is successful, a voice can be sent.
  • the prompting indicates that the identity of the user to be identified is successful.
  • the prompt of the identification failure and the identification of the identity again is displayed on the display screen, or when the identification of the user to be identified fails, the voice may also be issued.
  • a prompt prompts that the identity of the user to be identified fails, and a second identity is performed.
  • the above computing unit and the second determining unit may be run in a computer terminal as part of the device, and the functions implemented by the above module may be performed by a processor in the computer terminal, and the computer terminal may also be a smart phone (such as Android phones, iOS phones, etc.), tablets, handheld computers and mobile Internet devices (Mobile Internet Devices, MID), PAD and other terminal devices.
  • the collecting module 210 needs to generate a target point on the display screen before collecting the eye image when the user is gazing at the target point, and generating the target point on the display screen is specifically implemented by the first generating module or the second generating module. ,include:
  • the first generating module is configured to randomly generate a target point on the display screen in chronological order, and display a target point on the display screen at each time and the position of the target point is random; or the second generating module, It is used to generate a target point on the display screen according to the chronological order and the preset position sequence. At each moment, a target point is displayed on the display screen and the position of the target point is set by the preset position sequence.
  • the preset position sequence is a preset sequence of multiple positions. Each time the user to be identified is identified, a sequence of positions is randomly selected, and a target point is generated according to a randomly selected sequence of positions on a corresponding position on the display screen.
  • first generation module and the second generation module may be run in a computer terminal as part of the device, and the functions implemented by the module may be performed by a processor in the computer terminal, and the computer terminal may also be intelligent.
  • Mobile devices such as Android phones, iOS phones, etc.
  • tablets such as tablets, handheld computers, and mobile Internet devices (MID), PAD and other terminal devices.
  • MID mobile Internet devices
  • the identity recognition device provided by the embodiment of the present invention combines the eye tracking technology and the identity recognition technology.
  • the identity of the user to be identified is successful, and the accuracy of the identity recognition is high. And the adaptability and anti-counterfeiting performance are very good.
  • the identity recognition device provided by the embodiment of the present invention may be specific hardware on the device or software or firmware installed on the device.
  • the implementation principle and the technical effects of the device provided by the embodiments of the present invention are the same as those of the foregoing method embodiments.
  • a person skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working processes of the foregoing system, the device and the unit can refer to the corresponding processes in the foregoing method embodiments, and details are not described herein again.
  • An embodiment of the present invention provides a storage medium, where the storage medium includes a stored program, wherein the device where the storage medium is located is controlled to execute the foregoing identity recognition method when the program is running.
  • An embodiment of the present invention provides a processor, where a processor is configured to run a program, where the program is executed to execute the foregoing identity recognition method.
  • the embodiment of the present invention provides a terminal, including: an acquisition module, configured to collect an eye image when the user to be identified is gazing at a target point; and an identity recognition module, configured to use the eye image and the pre-established user identity information database. Identification of the user to be identified; live detection module, The utility model is configured to perform a living body detection on the user to be identified according to the image of the eye, the coordinates of the target point, the database of the user identity information, and the identification result; the processor and the processor run the program, wherein the program runs for the slave acquisition module and the identity recognition module.
  • the data output by the living body detection module performs the above identification method.
  • the embodiment of the present invention provides a terminal, including: an acquisition module, configured to collect an eye image when the user to be identified is gazing at a target point; and an identity recognition module, configured to use the eye image and the pre-established user identity information database. Identifying the user to be identified; the living body detecting module is configured to perform a living body detection on the user to be identified according to the eye image, the coordinates of the target point, the user identity information database, and the identification result; the storage medium is used to store the program, wherein The program performs the above identification method on the data output from the acquisition module, the identification module, and the living body detection module at runtime.
  • the various functional units provided by the embodiments of the present application may be operated in a mobile terminal, a computer terminal, or the like, or may be stored as part of a storage medium.
  • embodiments of the present invention may provide a computer terminal, which may be any computer terminal device in a group of computer terminals.
  • a computer terminal may also be replaced with a terminal device such as a mobile terminal.
  • the computer terminal may be located in at least one network device of the plurality of network devices of the computer network.
  • the computer terminal may execute the program code of the following steps in the identity recognition method: collecting an eye image when the user to be identified looks at the target point; according to the eye diagram Like the pre-established user identity information database, the user to be identified is identified; according to the eye image, the coordinates of the target point, the user identity information database and the identity recognition result, the user to be identified is subjected to the living body detection.
  • the computer terminal can include: one or more processors, memory, and transmission means.
  • the memory can be used to store software programs and modules, such as the identification method and the program instructions/modules corresponding to the device in the embodiment of the present invention, and the processor executes various functional applications by running software programs and modules stored in the memory. And data processing, that is, the above identification method is implemented.
  • the memory may include a high speed random access memory, and may also include non-volatile memory such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory.
  • the memory can further include memory remotely located relative to the processor, which can be connected to the terminal over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the above transmission device is for receiving or transmitting data via a network.
  • Specific examples of the above network may include a wired network and a wireless network.
  • the transmission device includes a Network Interface Controller (NIC) that can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network.
  • the transmission device is a Radio Frequency (RF) module for communicating with the Internet wirelessly.
  • NIC Network Interface Controller
  • RF Radio Frequency
  • the memory is used to store preset action conditions and information of the preset rights user, and an application.
  • the processor can call the memory stored information and the application by the transmitting device to execute the program code of the method steps of each of the alternative or preferred embodiments of the above method embodiments.
  • the computer terminal can also be a smart phone (eg, Android phones, iOS phones, etc.), tablets, PDAs, and mobile Internet devices (MID), PAD and other terminal devices.
  • smart phone eg, Android phones, iOS phones, etc.
  • tablets e.g.
  • PDAs e.g.
  • MID mobile Internet devices
  • Embodiments of the present invention also provide a storage medium.
  • the foregoing storage medium may be used to save the program code executed by the identity identification method provided by the foregoing method embodiment and the device embodiment.
  • the foregoing storage medium may be located in any one of the computer terminal groups in the computer network, or in any one of the mobile terminal groups.
  • the storage medium is configured to store program code for performing the following steps: collecting an eye image when the user to be identified looks at the target point; according to the eye image and the pre-established user identity information
  • the database identifies the user to be identified; according to the eye image, the coordinates of the target point, the user identity information database, and the identity recognition result, the user to be identified is subjected to the living body detection.
  • the storage medium may also be provided as program code of various preferred or optional method steps provided by the identification method.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some communication interface, device or unit, and may be electrical, mechanical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in the embodiment provided by the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the functions may be stored in a computer readable storage medium if implemented in the form of a software functional unit and sold or used as a standalone product.
  • the technical solution of the present invention which is essential or contributes to the prior art, or a part of the technical solution, may be embodied in the form of a software product, which is stored in a storage medium, including
  • the instructions are used to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Ophthalmology & Optometry (AREA)
  • Collating Specific Patterns (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

本发明提供了一种身份识别方法及装置，该方法包括：采集待识别用户注视目标点位时的眼部图像；根据上述眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别；根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测。本发明提供的身份识别方法及装置，将眼动跟踪技术与身份识别技术结合起来，当待识别用户活体检测及身份识别均成功时，待识别用户身份识别才成功，身份识别的准确性高，且实用性及抗伪性能均很好。

Description

一种身份识别方法及装置 技术领域
本发明涉及身份识别技术领域，具体而言，涉及一种身份识别方法及装置。
背景技术
虹膜是位于黑色瞳孔和白色巩膜之间的圆环状部分，在胎儿发育阶段形成，对于每个人来说，虹膜的结构都是各不相同并且在一生中几乎不发生变化，因此，虹膜被广泛应用于各种环境下的身份识别，但是经常会出现将伪造的虹膜贴在眼睛上，以此达到欺骗的目的，因此，在采用虹膜进行身份识别时，需要检测虹膜是否为活体。
相关技术中，大都是添加光学装置，由光源照射人眼，得到光激励下虹膜和眼球产生反应的序列，比如刺激瞳孔缩放、光反射成像等，将得到的序列与预先设定的反应序列阈值进行比对，根据得到的序列是否在阈值内判断对象是否为活体。
但是，相关技术中的活体判断方式，光激励下的瞳孔缩放还受到心情、色彩、外界光源及个体差异等的影响，容易导致判断出错，预先设定的反应序列阈值难以保证实际应用中的适应性，且采用人眼贴膜的方法容易骗过光学装置，因此，适应性及抗伪性能均很差。
发明内容
有鉴于此，本发明实施例的目的在于提供一种身份识别方法及装置，以解决相关技术中，采用光激励的活体判断方式，容易判断出错，且适应性及抗伪性能均很差的问题。
第一方面，本发明实施例提供了一种身份识别方法，其中，方法包括：
采集待识别用户注视目标点位时的眼部图像；
根据眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别；
根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测。
结合第一方面，本发明实施例提供了上述第一方面的第一种可能的实现方式，其中，根据眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别，包括：
从眼部图像中提取眼睛特征，眼睛特征包括虹膜特征和眼动特征；
判断用户身份信息数据库中是否包括虹膜特征；
如果是，则从用户身份信息数据库中获取虹膜特征对应的身份信息及校准数据。
结合第一方面的第一种可能的实现方式，本发明实施例提供了上述第一方面的第二种可能的实现方式，其中，根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测，包括：
当身份识别结果指示用户身份信息数据库中包括虹膜特征时，根据眼动特征及获取的校准数据，计算待识别用户的理论注视点坐标；
将理论注视点坐标与目标点位的坐标进行比对，判断待识别用户是 否为活体用户。
结合第一方面的第一种可能的实现方式，本发明实施例提供了上述第一方面的第三种可能的实现方式，其中，根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测，包括：
当身份识别结果指示用户身份信息数据库中包括虹膜特征时，根据眼动特征及目标点位的坐标，计算待识别用户的校准数据；
将待识别用户的校准数据与获取的校准数据进行比对，判断待识别用户是否为活体用户。
结合第一方面的第一种可能的实现方式，本发明实施例提供了上述第一方面的第四种可能的实现方式，其中，根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测，包括：
当身份识别结果指示用户身份信息数据库中包括虹膜特征时，从用户身份信息数据库中调取每个用户的校准数据；
根据眼动特征及调取的每个用户的校准数据，计算理论注视点坐标；
将理论注视点坐标分别与目标点位的坐标进行比对，判断待识别用户数是否为活体用户。
结合第一方面，本发明实施例提供了上述第一方面的第五种可能的实现方式，其中，采集待识别用户注视目标点位时的眼部图像之前，还包括：
按照时间先后顺序在显示屏上随机生成目标点位，每个时刻显示屏上显示一个目标点位且目标点位的位置是随机的；
或者，按照时间先后顺序及预设位置序列在显示屏上生成目标点位， 每个时刻显示屏上显示一个目标点位且目标点位的位置是由预设位置序列设定的。
第二方面，本发明实施例提供了一种身份识别装置，装置包括：
采集模块，用于采集待识别用户注视目标点位时的眼部图像；
身份识别模块，用于根据眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别；
活体检测模块，用于根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测。
结合第二方面，本发明实施例提供了上述第二方面的第一种可能的实现方式，其中，身份识别模块包括：
提取单元，用于从眼部图像中提取眼睛特征，眼睛特征包括虹膜特征和眼动特征；
第一判断单元，用于判断用户身份信息数据库中是否包括虹膜特征；
获取单元，用于在用户身份信息数据库中包括虹膜特征的情况下，从用户身份信息数据库中获取虹膜特征对应的身份信息及校准数据。
结合第二方面的第一种可能的实现方式，本发明实施例提供了上述第二方面的第二种可能的实现方式，其中，活体检测模块包括：
计算单元，用于当身份识别结果指示用户身份信息数据库中包括虹膜特征时，根据眼动特征及获取的校准数据，计算待识别用户的理论注视点坐标；
第二判断单元，用于将理论注视点坐标与目标点位的坐标进行比对，判断待识别用户是否为活体用户。
结合第二方面的第一种可能的实现方式，本发明实施例提供了上述第二方面的第三种可能的实现方式，其中，活体检测模块包括：
计算单元，用于当身份识别结果指示用户身份信息数据库中包括虹膜特征时，根据眼动特征及目标点位的坐标，计算待识别用户的校准数据；
第二判断单元，用于将待识别用户的校准数据与获取的校准数据进行比对，判断待识别用户是否为活体用户。
结合第二方面的第一种可能的实现方式，本发明实施例提供了上述第二方面的第四种可能的实现方式，其中，活体检测模块包括：
计算单元，用于当身份识别结果指示用户身份信息数据库中包括虹膜特征时，从用户身份信息数据库中调取每个用户的校准数据；根据眼动特征及调取的每个用户的校准数据，计算理论注视点坐标；
第二判断单元，用于将理论注视点坐标分别与目标点位的坐标进行比对，判断待识别用户数是否为活体用户。
结合第二方面，本发明实施例提供了上述第二方面的第五种可能的实现方式，其中，装置还包括：
第一生成模块，用于按照时间先后顺序在显示屏上随机生成目标点位，每个时刻显示屏上显示一个目标点位且目标点位的位置是随机的；
或者，第二生成模块，用于按照时间先后顺序及预设位置顺序在显示屏上生成目标点位，每个时刻显示屏上显示一个目标点位且目标点位的位置是由预设位置序列设定的。
第三方面，本发明实施例提供了一种存储介质，存储介质包括存储的程序，其中，在程序运行时控制存储介质所在设备执行上述身份识别方法。
第四方面，本发明实施例提供了一种处理器，处理器用于运行程序，其中，程序运行时执行上述身份识别方法。
第五方面，本发明实施例提供了一种终端，包括：采集模块，用于采集待识别用户注视目标点位时的眼部图像；身份识别模块，用于根据眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别；活体检测模块，用于根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测；处理器，处理器运行程序，其中，程序运行时对于从采集模块、身份识别模块和活体检测模块输出的数据执行上述身份识别方法。
第六方面，本发明实施例提供了一种终端，包括：采集模块，用于采集待识别用户注视目标点位时的眼部图像；身份识别模块，用于根据眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别；活体检测模块，用于根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测；存储介质，用于存储程序，其中，程序在运行时对于从采集模块、身份识别模块和活体检测模块输出的数据执行上述身份识别方法。
本发明实施例提供的身份识别方法及装置，该方法包括采集待识别用户注视目标点位时的眼部图像；根据上述眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别；根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活 体检测。本发明实施例中，将眼动跟踪技术与身份识别技术结合起来，当待识别用户活体检测及身份识别均成功时，待识别用户身份识别才成功，身份识别的准确性高，且适应性及抗伪性能均很好。
为使本发明的上述目的、特征和优点能更明显易懂，下文特举较佳实施例，并配合所附附图，作详细说明如下。
附图说明
为了更清楚地说明本发明实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，应当理解，以下附图仅示出了本发明的某些实施例，因此不应被看作是对范围的限定，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的附图。
图1示出了本发明实施例1所提供的一种身份识别方法的流程图；
图2示出了本发明实施例2所提供的一种身份识别装置的结构示意图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。通常在此处附图中描述和示出的本发明实施例的组件可以以各种不同的配置来布置和设计。因此，以下对在附图中提供的本发明的实施例的详细描述并非旨在限制要求保护的本发明的范围，而是仅仅表示本发明的选定实施例。基于本发明的实施例，本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本发明保护的范围。
考虑到相关技术中，采用虹膜进行身份识别时，大都是通过光激励的方式判断虹膜是否为活体，但是光激励下的瞳孔缩放还受到心情、色彩、外界光源及个体差异等的影响，容易导致判断出错，且预先设定的反映序列阈值难以保证实际应用中的适应性，且采用人眼贴膜的方式容易骗过光学装置，因此，适应性及抗伪性能均很差。基于此，本发明实施例提供了一种身份识别方法及装置，下面通过实施例进行描述。
实施例1
本发明实施例提供了一种身份识别方法，该方法将眼动跟踪技术与虹膜识别技术结合起来，眼动跟踪技术通过采集待识别用户在注视目标点位时的眼睛图像，提取待识别用户的虹膜特征和眼动特征，对待识别用户进行虹膜识别并调取校准数据，结合目标点位的坐标，判断待识别用户是否为活体用户，当待识别用户虹膜识别成功且判断待识别用户为活体用户时，则判断为待识别用户身份识别成功。本发明实施例提供的身份识别方法，身份识别的准确性高，适应性及抗伪性能均很好。
本发明实施例提供的身份识别方法，可以应用于银行的门禁、监狱的门禁、密码支付等场景，在采用本发明实施例提供的方法进行身份识别之前，需要建立应用场景授权用户的身份信息数据库，比如说，将上述身份识别方法应用于银行的门禁，则需要建立银行员工的身份信息数据库，以用于对银行员工进行身份识别，当银行员工身份识别通过，则银行门开启，该员工可以进入，如果将上述身份识别方法应用于监狱的门禁，则需要建立狱警的身份信息数据库。
建立用户身份信息数据库，具体包括如下步骤：获取用户的虹膜特征、校准数据及用户的身份信息；将用户的虹膜特征、校准数据、身份信息及 其对应关系存储在用户身份信息数据库中。
上述虹膜特征包括用户虹膜的斑点、细丝、冠状、条纹及隐窝等特征，上述校准数据是根据用户注视一组或多组特定的目标点位时的眼动特征及注视点的坐标计算得出的用户个体特征数据。
上述特定的目标点位可以是显示屏的四个角及中心显示的五个目标点位，也可以是显示屏上的四个角、四条边的中心及显示屏的中心显示的九个目标点位，将上述特定的目标点位记为校准点位，当然，上述校准点位还可以是显示屏上其它位置的目标点位，上述一组校准点位的个数及位置可以根据实际应用场景进行设置。
其中，获取用户的虹膜特征及校准数据的过程包括：
按照时间先后顺序在显示屏上连续生成校准点位，每次显示一个校准点位，获取用户眼睛注视校准点位时的校准眼部图像，从采集的校准眼部图像中提取出用户的虹膜特征及眼动特征。用户的虹膜特征包括但不限于斑点、细丝、冠众、条纹及隐窝等特征。上述眼动特征为用户注视校准点位时获取的眼部特征，包括但不限于用户的眼睛角点、瞳孔中心位置、瞳孔半径大小、角膜发射所形成的普尔钦斑等眼部特征。根据用户注视一组或多组校准点位时的眼动特征及校准点位信息进行计算，获得用户的校准数据，校准数据包括但不限于用户的视轴和光轴的夹角等眼部特征数据。获取虹膜特征和校准数据后，获取该用户的身份信息，该身份信息包括但不限于用户的姓名、身份证号、性别、职务等信息，建立该用户的身份信息、虹膜特征及校准数据的对应关系，并将该用户的身份信息、虹膜特征、校准数据及其对应关系存储在用户身份信息数据库中。
采用本发明实施例提供的方法对待识别用户进行身份识别时，需要待识别用户注视目标点位，该目标点位可以是在显示屏上显示的一系列目标点位，也可以是某个固定位置处显示目标点位，比如说，墙壁上、玻璃门 上等，还可以是某个位置的物体。
上述显示屏上除了显示目标点位外，还可以显示虚拟键盘，该虚拟键盘可以是由0-9十个数字组成的数字键盘，也可以是由26个英文字母组成的字母键盘，或者还可以是由0-9十个数字和26个英文字母组成的数字字母组合键盘，且上述虚拟键盘上的字母或数字的顺组是随机的，待识别用户可以通过注视上述虚拟键盘上的键位的方式输入预先约定的密码，比如说，预先约定的密码为123，则待识别用户按照顺序依次注视虚拟键盘上的数字键位123，或者还可以是待识别用户按照指示注视上述虚拟键盘上的某个键位，比如说，指示待识别用户按照顺序注视上述虚拟键盘上的3、6、9数字键位，或者P、M、V等字母键位等等，上述可以通过语音的形式指示用户注视虚拟键盘上的字母或数字，也可以是在显示屏上显示用户需要注视的虚拟键盘上的字母或数字。
上述显示屏上还可以显示某些图形，待识别用户根据指示注视显示屏上的图形的某些部位。
如果待识别用户注视的目标点位是显示屏上显示的目标点位，则需要在显示屏上生成目标点位。在显示屏上生成的目标点位包括如下两种情况，按照时间先后顺序在显示屏上随机生成目标点位，每个时刻显示屏上显示一个目标点位且目标点位的位置是随机的；或者，按照时间先后顺序及预设位置顺序在显示屏上生成目标点位，每个时刻显示屏上显示一个目标点位且目标点位的位置是由预设位置序列设定的。
上述预设位置序列是预先设置的多个位置序列，每次对待识别用户进行身份识别时，随机选取一个位置序列，按照随机选取的位置序列在显示屏上相应的位置生成目标点位。
采用本发明实施例提供的身份识别方法对待识别用户进行身份识别，如图1所示，具体步骤包括S110-S130。
S110，采集待识别用户注视目标点位时的眼部图像。
当待识别用户在公司门禁、小区门禁或密码支付等场景下需要进行身份识别时，待识别用户可以点击开始按钮进行待识别用户身份识别，或者当待识别用户的眼睛进入到图像采集的区域范围内时，自动对待识别用户进行身份识别。
当待识别用户注视目标点位时，可以以一定的帧率采集用户的眼部图像，这样，在待识别用户注视一个目标点位时会采集多张眼部图像。
当采集了待识别用户注视目标点位时的眼部图像后，首先判断采集的眼部图像中是否包括待识别用户的眼睛区域，如果采集的眼部图像中不包括待识别用户的眼睛区域，可能待识别用户的眼睛并没有对准图像采集设备，这时提示待识别用户调整位置重新采集图像，如果采集的眼部图像中包括待识别用户的眼睛区域，则对待识别用户进行身份识别。
如果采集的眼部图像由于受到干扰等因素导致不清晰等，这时可以对采集的眼部图像进行干扰抑制等方法处理后使用。
S120，根据眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别。
上述对待识别用户进行身份识别的过程实际上就是对待识别用户进行虹膜识别的过程。
上述对待识别用户进行身份识别，具体包括如下过程：从上述眼部图像中提取眼睛特征，上述眼睛特征包括虹膜特征和眼动特征；判断用户身份信息数据库中是否包括上述虹膜特征；如果是，则用户身份信息数据库中获取上述虹膜特征对应的身份信息及校准数据。
由于已经获取了待识别用户注视目标点位时的眼部图像，从眼部图像中提取出待识别用户的眼睛瞳孔中心位置、瞳孔半径大小、眼睛角点、 角膜发射所形成的普尔钦斑等眼动特征，以及提取出待识别用户的眼睛的斑点、细丝、冠状、隐窝等虹膜特征。
如果上述眼睛特征提取失败，即无法提取出待识别用户的虹膜特征，或者无法提取出待识别用户的眼动特征，或者无法提取出待识别用户的虹膜特征和眼动特征，则待识别用户身份识别失败，这时可以重新采集待识别用户注视目标点位时的眼部图像，对待识别用户进行身份识别。
如果上述眼睛特征提取成功，将上述从待识别用户的眼部图像中提取的虹膜特征与用户身份信息数据库中存储的虹膜特征进行匹配，判断用户身份信息数据库中是否存在与上述提取的待识别用户的虹膜特征一致的虹膜特征，如果存在与上述提取的待识别用户的虹膜特征一致的虹膜特征，则判断为虹膜识别成功，并从用户身份信息数据库中调取与待识别用户的虹膜特征对应的身份信息及校准数据，将上述虹膜特征对应的身份信息确定为待识别用户的身份信息。
如果用户身份信息数据库中不存在与上述提取的待识别用户的虹膜特征一致的虹膜特征，则说明用户身份信息数据库中没有存储该待识别用户的虹膜特征，即该待识别用户为非授权用户，待识别用户身份识别失败，这时待识别用户可以通过管理员进行身份验证，当身份验证通过后，录入该待识别用户的虹膜特征、校准数据及用户的身份信息。
由于待识别用户在注视目标点位的过程中，会采集多张待识别用户的眼部图像，因此可以对待识别用户进行多次虹膜识别，在多次虹膜识别的过程中，只要出现一次虹膜识别成功，即可判断为待识别用户虹膜识别成功，即用户数身份信息数据库中存在与该虹膜特征对应的身份信息及校准数据。
或者，还可以从上述采集的眼部图像中提取的多个虹膜特征中，随机选取q个虹膜特征，进行q次虹膜识别，其中，q小于显示屏上显示的目 标点位的次数，在进行q次虹膜识别的过程中，只要识别成功m次即可判断为待识别用户虹膜识别成功，m可以通过下述公式(1)或公式(2)计算，
m＝(q-1)/2         (1)
m＝q/2            (2)
其中，在公式(1)和公式(2)中，m为虹膜识别成功的次数，q为进行虹膜识别的次数，且在公式(1)中，q为奇数，在公式(2)中，q为偶数。
S130，根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测。
为了防止待识别用户将伪造的虹膜贴在眼睛上，以此达到欺骗的目的，本发明实施例提供的身份识别方法还需要对待识别用户进行活体检测。
上述目标点位的坐标为正在显示的目标点位的坐标，该目标点位的坐标可以根据该目标点位与校准点位或其他特定点位或物体的相对位置计算。
当上述身份识别结果指示用户身份信息数据库中包括上述虹膜特征时，对待识别用户进行活体检测，对待识别用户进行活体检测具体包括两种情况：
第一种情况，根据眼动特征及获取的校准数据，计算待识别用户的理论注视点坐标；将理论注视点坐标与目标点位的坐标进行比对，判断待识别用户是否为活体用户。
下面将以一个例子详细介绍计算待识别用户的理论注视点的坐标的过程。
用户在注视不同目标点位时，眼睛的视轴和光轴的夹角是不变的，因此，将视轴和光轴的夹角这一个数据作为上述用户的校准数据，将瞳孔位置、瞳孔半径和角膜反射所形成的普尔钦斑等作为提取的用户的眼动特征。通过待识别用户的瞳孔位置、瞳孔半径、角膜反射所形成的普尔钦斑等眼动特征与待识别用户的虹膜特征对应的视轴和光轴的夹角等校准数据，可以计算得出待识别用户的一个理论注视点坐标，将计算得到的待识别用户的理论注视点坐标与目标点位的坐标进行比对，判断上述理论注视点是否落在目标点位的区域范围内，该区域范围以该目标点位为中心的预设区域，为可接受的误差区域范围，如果理论注视点落在目标点位的区域范围内，且持续了预设时间长度，则判断为该目标点位识别成功。当上述目标点位识别成功后，显示屏上会生成下一个目标点位，采用上述方法对显示屏上出现的目标点位进行注视点识别，当待识别用户连续对预设数量个目标点位均识别成功，则判断待识别用户为活体用户，其中，该预设数量个目标点位为大于等于3的任意数量个目标点位，本发明实施例并不限定该预设数量的具体数值。
由于待识别用户在注视每个目标点位时，都会以一定的帧率连续采集多张待识别用户的眼部图像，上述第一种情况中，如果根据预设时间长度内采集的眼部图像计算得出的理论注视点中有预设比例均落在目标点位的区域范围内，则判断为持续了预设时间长度，该目标点位识别成功。上述预设时间长度大于等于人眼跟随目标点位的反应时间，小于等于目标点位的显示时间，一般情况下，该预设时间长度大于等于0.1秒，优选的，该预设时间长度在0.5-1.5秒之间。上述预设比例可以根据识别的精准度要求进行设置和修改，一般情况下，该预设比例大于50％，优选的，该预设比例在50％-70％之间，本发明实施例并不限定该预设比例的具体数值。
第二种情况，根据眼动特征及目标点位的坐标，计算待识别用户的校 准数据；将待识别用户的校准数据与获取的校准数据进行比对，判断待识别用户是否为活体用户。
下面将以一个例子详细介绍计算待识别用户的校准数据的过程。
用户在注视不同目标点位时，眼睛的视轴和光轴的夹角是不变的，因此，将视轴和光轴的夹角这一个数据作为上述用户的校准数据，将瞳孔位置、瞳孔半径和角膜反射所形成的普尔钦斑等作为提取的用户的眼动特征。显示屏上的目标点位为待识别用户的实际注视点坐标，目标点位的坐标可以根据该目标点位与校准点位或其他特定点位或物体的相对位置计算。
通过提取的待识别用户的瞳孔位置、瞳孔半径和角膜反射所形成的普洱钦斑等眼动特征与用户的实际注视点坐标，即目标点位的坐标，计算获得待识别用户的视轴和光轴的夹角等校准数据。
在进行虹膜识别的过程中，从预先建立的用户身份信息数据库中调取待识别用户的虹膜特征对应的校准数据，将上述计算得出的校准数据与调取的校准数据进行比对，如果计算得出的校准数据落在调取的校准数据的误差范围之内，且持续了预设时间长度，则认为待识别用户在注视显示屏上的目标点位，即该目标点位识别成功。
当上述目标点位识别成功后，显示屏上会显示下一个目标点位，采用上述方法对显示屏上出现的目标点位进行识别，当待识别用户连续对预设数量个目标点位均识别成功时，则判断待识别用户为活体用户，其中，该预设数量个目标点位为大于等于3的任意数量个目标点位，本发明实施例并不限定该预设数量的具体数值。
由于待识别用户在注视每个目标点位时，都会以一定的帧率连续采集多张待识别用户的眼部图像，上述第二种情况中，如果根据预设时间长度内采集的眼部图像计算得出的校准数据中有预设比例落在调取的校准数 据的误差范围之内，则判断为持续了预设时间长度，该目标点位识别成功。上述预设时间长度大于等于人眼跟随目标点位的反应时间，小于等于目标点位的显示时间，一般情况下，该预设时间长度大于等于0.1秒，优选的，该预设时间长度在0.5-1.5秒之间。上述预设比例可以根据识别的精准度要求进行设置和修改，一般情况下，该预设比例大于50％，优选的，该预设比例在50％-70％之间，本发明实施例并不限定该预设比例的具体数值。
上述两种情况是通过从用户身份信息数据库中调取与待识别用户的虹膜特征对应的校准数据对待识别用户进行活体检测，还可以通过从用户身份信息数据库中调取所有用户的校准数据对待识别用户进行活体检测。
当上述身份识别结果指示用户身份信息数据库中包括上述虹膜特征时，从上述身份信息数据库中调取每个用户的校准数据；根据眼动特征及调取的每个用户的校准数据，计算理论注视点坐标；将理论注视点坐标分别与目标点位的坐标进行比对，判断待识别用户是否为活体用户。
用户在注视不同目标点位时，眼睛的视轴和光轴的夹角是不变的，因此，将视轴和光轴的夹角这一个数据作为上述用户的校准数据，将瞳孔位置、瞳孔半径和角膜反射所形成的普尔钦斑等作为提取的用户的眼动特征。当上述调取的校准数据是从预先建立的用户身份信息数据库中调取存储的所有用户的校准数据时，通过待识别用户的瞳孔位置、瞳孔半径和角膜反射所形成的普尔钦斑等眼动特征，分别与预先建立的用户身份信息数据库中每个用户的视轴和光轴的夹角等校准数据计算，可以得出多个理论注视点坐标。将上述多个理论注视点坐标分别与目标点位的坐标进行比对，判断上述多个理论注视点坐标中是否存在一个落在目标点位的区域范围内的理论注视点坐标，该区域范围以该目标点位为中心的预设区域，为可接受的误差区域范围，如果存在这样一个理论注视点，且持续了预设时间长度，则认为待识别用户在注视显示屏上的目标点位，即目标点位识别成 功，同时，判断在计算这一理论注视点坐标时调取的用户的校准数据为待识别用户的校准数据。当上述目标点位识别成功后，显示屏上会显示下一个目标点位，采用上述方法对显示屏上出现的目标点位进行识别，当待识别用户连续对预设数量个目标点位均识别成功，且注视预设数量个目标点位时获得的待识别用户的校准数据是相同的，则判断待识别用户为活体用户，其中，该预设数量个目标点位为大于等于3的任意数量个目标点位，本发明实施例并不限定该预设数量的具体数值。
由于待识别用户在注视每个目标点位时，都会以一定的帧率连续采集多张待识别用户的眼部图像，如果根据预设时间长度内采集的眼部图像计算得出的理论注视点中有预设比例均落在目标点位的区域范围内，则判断为持续了预设时间长度，该目标点位识别成功。上述预设时间长度大于等于人眼跟随目标点位的反应时间，小于等于目标点位的显示时间，一般情况下，该预设时间长度大于等于0.1秒，优选的，该预设时间长度在0.5-1.5秒之间。上述预设比例可以根据识别的精准度要求进行设置和修改，一般情况下，该预设比例大于50％，优选的，该预设比例在50％-70％之间，本发明实施例并不限定该预设比例的具体数值。
当上述虹膜识别及活体检测均成功时，则判断为待识别用户身份识别成功。
如果虹膜识别和活体检测没有同时成功，则待识别用户身份识别失败，则提示用户需要再次进行身份识别，当待识别用户身份识别的次数达到预设次数时，该待识别用户身份被锁定，不可继续识别，这时判断为该待识别用户为非授权用户，上述预设次数可以是3，还可以是其它数值，该预设次数的具体数值可以根据实际情况进行设置，本发明实施例并不限定上述预设次数的具体数值。
当待识别用户身份识别成功时，显示屏上会显示用户的身份信息及识 别成功的提示，或者，当待识别用户身份识别成功时，还可以发出语音提示，提示待识别用户身份识别成功，当待识别用户身份识别失败时，显示屏上会显示身份识别失败及再次进行身份识别的提示，或者，当待识别用户身份识别失败时，还可以发出语音提示，提示待识别用户身份识别失败，及进行第二次身份识别。
如果预先建立的用户身份信息数据库中只录入了用户的虹膜特征和身份信息的对应关系，并没有录入用户的校准数据，则在对待识别用户进行身份识别时，需要让待识别用户注视显示屏上的校准点位，计算得到待识别用户的校准数据，并将校准数据、用户的虹膜特征、身份信息及其对应关系存储在用户身份信息数据库中，可以将上述录入待识别用户的校准数据的过程作为活体检测的过程，也可以在录入待识别用户的校准数据后，再根据从采集的眼部图像中提取的眼动特征及待识别用户的校准数据，对待识别用户进行活体检测。
本发明实施例提供的身份识别方法，包括：采集待识别用户注视目标点位时的眼部图像；根据眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别；根据上述眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测。本发明提供的方法，将眼动跟踪技术与身份识别技术结合起来，当待识别用户活体检测及身份识别均成功时，待识别用户身份识别才成功，身份识别的准确性高，且适应性及抗伪性能均很好。
实施例2
本发明实施例提供了一种身份识别装置。如图2所示，该装置包括：
采集模块210，用于采集待识别用户注视目标点位时的眼部图像；
身份识别模块220，用于根据眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别；
活体检测模块230，用于根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测。
本发明实施例提供的身份识别装置，可以应用于银行的门禁、监狱的门禁、密码支付等场景，在采用本发明实施例提供的方法进行身份识别之前，需要建立应用场景授权用户的身份信息数据库，比如说，将上述身份识别方法应用于银行的门禁，则需要建立银行员工的身份信息数据库，以用于对银行员工进行身份识别，当银行员工身份识别通过，则银行门开启，该员工可以进入，如果将上述身份识别方法应用于监狱的门禁，则需要建立狱警的身份信息数据库。
此处需要说明的是，上述采集模块210、身份识别模块220和活体检测模块230可以作为装置的一部分运行在计算机终端中，可以通过计算机终端中的处理器来执行上述模块实现的功能，计算机终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌上电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
上述身份识别模块220根据眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别，具体通过提取单元、第一判断单元和获取单元实现，包括：
上述提取单元，用于从眼部图像中提取眼睛特征，该眼睛特征包括虹膜特征和眼动特征；上述第一判断单元，用于判断用户身份信息数据库中是否包括虹膜特征；上述获取单元，用于在用户身份信息数据库中包括虹膜特征的情况下，从用户身份信息数据库中获取虹膜特征对应的身份信息及校准数据。
上述虹膜特征包括但不限于斑点、细丝、冠状、条纹及隐窝等特征，上述眼动特征包括但不限于用户的眼睛角点、瞳孔中心位置、瞳孔半径大小、角膜发射所形成的普尔钦斑等眼部特征。
由于待识别用户在注视目标点位的过程中，会采集多张待识别用户的眼部图像，因此可以对待识别用户进行多次虹膜识别，在多次虹膜识别的过程中，只要出现一次虹膜识别成功，即可判断为待识别用户虹膜识别成功，即用户数身份信息数据库中存在与该虹膜特征对应的身份信息及校准数据。
或者，还可以从上述采集的眼部图像中提取的多个虹膜特征中，随机选取q个虹膜特征，进行q次虹膜识别，其中，q小于显示屏上显示的目标点位的次数，在进行q次虹膜识别的过程中，只要识别成功m次即可判断为待识别用户虹膜识别成功，m可以通过下述公式(1)或公式(2)计算，
m＝(q-1)/2        (1)
m＝q/2          (2)
其中，在公式(1)和公式(2)中，m为虹膜识别成功的次数，q为进行虹膜识别的次数，且在公式(1)中，q为奇数，在公式(2)中，q为偶数。
此处需要说明的是，上述提取单元、第一判断单元和获取单元可以作为装置的一部分运行在计算机终端中，可以通过计算机终端中的处理器来执行上述模块实现的功能，计算机终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌上电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
上述活体检测模块230根据上述眼部图像、目标点位的坐标、用户身 份信息数据库及身份识别结果，对待识别用户进行活体检测，具体通过计算单元及第二判断单元实现，包括：
上述计算单元，用于当身份识别结果指示用户身份信息数据库中包括上述虹膜特征时，根据眼动特征及获取的校准数据，计算待识别用户的理论注视点坐标；上述第二判断单元，用于将理论注视点坐标与目标点位的坐标进行比对，判断待识别用户是否为活体用户；上述计算单元，也可以设置为用于当身份识别结果指示用户身份信息数据库中包括上述虹膜特征时，根据眼动特征及目标点位的坐标，计算待识别用户的校准数据；上述第二判断单元，也可以设置为用于将待识别用户的校准数据与获取的校准数据进行比对，判断待识别用户是否为活体用户；上述计算单元，也可以设置为用于当身份识别结果指示用户身份信息数据库中包括虹膜特征时，从用户身份信息数据库中调取每个用户的校准数据；根据眼动特征及调取的每个用户的校准数据，计算理论注视点坐标；上述第二判断单元，也可以设置为用于将理论注视点坐标分别与目标点位的坐标进行比对，判断待识别用户数是否为活体用户。
当上述虹膜识别及活体检测均成功时，则判断为待识别用户身份识别成功。
如果虹膜识别和活体检测没有同时成功，则待识别用户身份识别失败，则提示用户需要再次进行身份识别，当待识别用户身份识别的次数达到预设次数时，该待识别用户身份被锁定，不可继续识别，这时判断该待识别用户为非授权用户，上述预设次数可以是3，还可以是其它数值，该预设次数的具体数值可以根据实际情况进行设置，本发明实施例并不限定上述预设次数的具体数值。
当待识别用户身份识别成功时，显示屏上会显示用户的身份信息及识别成功的提示，或者，当待识别用户身份识别成功时，还可以发出语音提 示，提示待识别用户身份识别成功，当待识别用户身份识别失败时，显示屏上会显示身份识别失败及再次进行身份识别的提示，或者，当待识别用户身份识别失败时，还可以发出语音提示，提示待识别用户身份识别失败，及进行第二次身份识别。
此处需要说明的是，上述计算单元及第二判断单元可以作为装置的一部分运行在计算机终端中，可以通过计算机终端中的处理器来执行上述模块实现的功能，计算机终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌上电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
上述采集模块210采集待识别用户注视目标点位时的眼部图像之前，还需要在显示屏上生成目标点位，在显示屏上生成目标点位具体通过第一生成模块或者第二生成模块实现，包括：
上述第一生成模块，用于按照时间先后顺序在显示屏上随机生成目标点位，每个时刻显示屏上显示一个目标点位且目标点位的位置是随机的；或者上述第二生成模块，用于按照时间先后顺序及预设位置序列在显示屏上生成目标点位，每个时刻显示屏上显示一个目标点位且目标点位的位置是由预设位置序列设定的。
上述预设位置序列是预先设置的多个位置序列，每次对待识别用户进行身份识别时，随机选取一个位置序列，按照随机选取的位置序列在显示屏上相应的位置生成目标点位。
此处需要说明的是，上述第一生成模块和第二生成模块可以作为装置的一部分运行在计算机终端中，可以通过计算机终端中的处理器来执行上述模块实现的功能，计算机终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌上电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
本发明实施例提供的身份识别装置，将眼动跟踪技术与身份识别技术结合起来，当待识别用户活体检测及身份识别均成功时，待识别用户身份识别才成功，身份识别的准确性高，且适应性及抗伪性能均很好。
本发明实施例所提供的身份识别装置可以为设备上的特定硬件或者安装于设备上的软件或固件等。本发明实施例所提供的装置，其实现原理及产生的技术效果和前述方法实施例相同，为简要描述，装置实施例部分未提及之处，可参考前述方法实施例中相应内容。所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，前述描述的系统、装置和单元的具体工作过程，均可以参考上述方法实施例中的对应过程，在此不再赘述。
实施例3
本发明实施例提供了一种存储介质，存储介质包括存储的程序，其中，在程序运行时控制存储介质所在设备执行上述身份识别方法。
实施例4
本发明实施例提供了一种处理器，处理器用于运行程序，其中，程序运行时执行上述身份识别方法。
实施例5
本发明实施例提供了一种终端，包括：采集模块，用于采集待识别用户注视目标点位时的眼部图像；身份识别模块，用于根据眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别；活体检测模块， 用于根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测；处理器，处理器运行程序，其中，程序运行时对于从采集模块、身份识别模块和活体检测模块输出的数据执行上述身份识别方法。
实施例6
本发明实施例提供了一种终端，包括：采集模块，用于采集待识别用户注视目标点位时的眼部图像；身份识别模块，用于根据眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别；活体检测模块，用于根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测；存储介质，用于存储程序，其中，程序在运行时对于从采集模块、身份识别模块和活体检测模块输出的数据执行上述身份识别方法。
本申请实施例所提供的各个功能单元可以在移动终端、计算机终端或者类似的运算装置中运行，也可以作为存储介质的一部分进行存储。
由此，本发明的实施例可以提供一种计算机终端，该计算机终端可以是计算机终端群中的任意一个计算机终端设备。可选地，在本实施例中，上述计算机终端也可以替换为移动终端等终端设备。
可选地，在本实施例中，上述计算机终端可以位于计算机网络的多个网络设备中的至少一个网络设备。
在本实施例中，上述计算机终端可以执行身份识别方法中以下步骤的程序代码：采集待识别用户注视目标点位时的眼部图像；根据眼部图 像及预先建立的用户身份信息数据库，对待识别用户进行身份识别；根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测。
可选地，该计算机终端可以包括：一个或多个处理器、存储器、以及传输装置。
其中，存储器可用于存储软件程序以及模块，如本发明实施例中的身份识别方法及装置对应的程序指令/模块，处理器通过运行存储在存储器内的软件程序以及模块，从而执行各种功能应用以及数据处理，即实现上述的身份识别方法。存储器可包括高速随机存储器，还可以包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器可进一步包括相对于处理器远程设置的存储器，这些远程存储器可以通过网络连接至终端。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
上述的传输装置用于经由一个网络接收或者发送数据。上述的网络具体实例可包括有线网络及无线网络。在一个实例中，传输装置包括一个网络适配器(Network Interface Controller，NIC)，其可通过网线与其他网络设备与路由器相连从而可与互联网或局域网进行通讯。在一个实例中，传输装置为射频(Radio Frequency，RF)模块，其用于通过无线方式与互联网进行通讯。
其中，具体地，存储器用于存储预设动作条件和预设权限用户的信息、以及应用程序。
处理器可以通过传输装置调用存储器存储的信息及应用程序，以执行上述方法实施例中的各个可选或优选实施例的方法步骤的程序代码。
本领域普通技术人员可以理解，计算机终端也可以是智能手机(如 Android手机、iOS手机等)、平板电脑、掌上电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令终端设备相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：闪存盘、只读存储器(Read-Only Memory，ROM)、随机存取器(Random Access Memory，RAM)、磁盘或光盘等。
本发明的实施例还提供了一种存储介质。可选地，在本实施例中，上述存储介质可以用于保存上述方法实施例和装置实施例所提供的身份识别方法所执行的程序代码。
可选地，在本实施例中，上述存储介质可以位于计算机网络中计算机终端群中的任意一个计算机终端中，或者位于移动终端群中的任意一个移动终端中。
可选地，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：采集待识别用户注视目标点位时的眼部图像；根据眼部图像及预先建立的用户身份信息数据库，对待识别用户进行身份识别；根据眼部图像、目标点位的坐标、用户身份信息数据库及身份识别结果，对待识别用户进行活体检测。
可选地，在本实施例中，存储介质还可以被设置为身份识别方法提供的各种优选地或可选的方法步骤的程序代码。
如上参照附图以示例的方式描述了根据本发明的身份识别方法及装置。但是，本领域技术人员应当理解，对于上述本发明所提出的身份识别方法及装置，还可以在不脱离本发明内容的基础上做出各种改进。因此，本发明的保护范围应当由所附的权利要求书的内容确定。
在本发明所提供的实施例中，应该理解到，所揭露装置和方法，可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，又例如，多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明提供的实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步 定义和解释，此外，术语“第一”、“第二”、“第三”等仅用于区分描述，而不能理解为指示或暗示相对重要性。
最后应说明的是：以上所述实施例，仅为本发明的具体实施方式，用以说明本发明的技术方案，而非对其限制，本发明的保护范围并不局限于此，尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化，或者对其中部分技术特征进行等同替换；而这些修改、变化或者替换，并不使相应技术方案的本质脱离本发明实施例技术方案的精神和范围。都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以所述权利要求的保护范围为准。

Claims (16)

  1. 一种身份识别方法，其中，所述方法包括：
    采集待识别用户注视目标点位时的眼部图像；
    根据所述眼部图像及预先建立的用户身份信息数据库，对所述待识别用户进行身份识别；
    根据所述眼部图像、所述目标点位的坐标、所述用户身份信息数据库及身份识别结果，对所述待识别用户进行活体检测。
  2. 根据权利要求1所述的方法，其中，所述根据所述眼部图像及预先建立的用户身份信息数据库，对所述待识别用户进行身份识别，包括：
    从所述眼部图像中提取眼睛特征，所述眼睛特征包括虹膜特征和眼动特征；
    判断所述用户身份信息数据库中是否包括所述虹膜特征；
    如果是，则从所述用户身份信息数据库中获取所述虹膜特征对应的身份信息及校准数据。
  3. 根据权利要求2所述的方法，其中，所述根据所述眼部图像、所述目标点位的坐标、所述用户身份信息数据库及身份识别结果，对所述待识别用户进行活体检测，包括：
    当身份识别结果指示所述用户身份信息数据库中包括所述虹膜特征时，根据所述眼动特征及获取的校准数据，计算待识别用户的理论注视点坐标；
    将所述理论注视点坐标与所述目标点位的坐标进行比对，判断所述待识别用户是否为活体用户。
  4. 根据权利要求2所述的方法，其中，所述根据所述眼部图像、所述目标点位的坐标、所述用户身份信息数据库及身份识别结果，对所述待识别用户进行活体检测，包括：
    当身份识别结果指示所述用户身份信息数据库中包括所述虹膜特征时，根据所述眼动特征及所述目标点位的坐标，计算所述待识别用户的校准数据；
    将所述待识别用户的校准数据与获取的校准数据进行比对，判断所述待识别用户是否为活体用户。
  5. 根据权利要求2所述的方法，其中，所述根据所述眼部图像、所述目标点位的坐标、所述用户身份信息数据库及身份识别结果，对所述待识别用户进行活体检测，包括：
    当身份识别结果指示所述用户身份信息数据库中包括所述虹膜特征时，从所述用户身份信息数据库中调取每个用户的校准数据；
    根据所述眼动特征及调取的每个用户的校准数据，计算理论注视点坐标；
    将所述理论注视点坐标分别与所述目标点位的坐标进行比对，判断所述待识别用户数是否为活体用户。
  6. 根据权利要求1所述的方法，其中，所述采集待识别用户注视目标点位时的眼部图像之前，还包括：
    按照时间先后顺序在显示屏上随机生成目标点位，每个时刻显示屏上显示一个目标点位且目标点位的位置是随机的；
    或者，按照时间先后顺序及预设位置序列在显示屏上生成目标点位，每个时刻显示屏上显示一个目标点位且目标点位的位置是由所述预设位置序列设定的。
  7. 一种身份识别装置，其中，所述装置包括：
    采集模块，用于采集待识别用户注视目标点位时的眼部图像；
    身份识别模块，用于根据所述眼部图像及预先建立的用户身份信息数据库，对所述待识别用户进行身份识别；
    活体检测模块，用于根据所述眼部图像、所述目标点位的坐标、所述用户身份信息数据库及身份识别结果，对所述待识别用户进行活体检测。
  8. 根据权利要求7所述的装置，其中，所述身份识别模块包括：
    提取单元，用于从所述眼部图像中提取眼睛特征，所述眼睛特征包括虹膜特征和眼动特征；
    第一判断单元，用于判断所述用户身份信息数据库中是否包括所述虹膜特征；
    获取单元，用于在所述用户身份信息数据库中包括所述虹膜特征的情况下，从所述用户身份信息数据库中获取所述虹膜特征对应的身份信息及校准数据。
  9. 根据权利要求8所述的装置，其中，所述活体检测模块包括：
    计算单元，用于当身份识别结果指示所述用户身份信息数据库中包括所述虹膜特征时，根据所述眼动特征及获取的校准数据，计算待识别用户的理论注视点坐标；
    第二判断单元，用于将所述理论注视点坐标与所述目标点位的坐标进行比对，判断所述待识别用户是否为活体用户。
  10. 根据权利要求8所述的装置，其中，所述活体检测模块包括：
    计算单元，用于当身份识别结果指示所述用户身份信息数据库中包括所述虹膜特征时，根据所述眼动特征及所述目标点位的坐标，计算所述待识别用户的校准数据；
    第二判断单元，用于将所述待识别用户的校准数据与获取的校准数据进行比对，判断所述待识别用户是否为活体用户。
  11. 根据权利要求8所述的装置，其中，所述活体检测模块包括：
    计算单元，用于当身份识别结果指示所述用户身份信息数据库中包括所述虹膜特征时，从所述用户身份信息数据库中调取每个用户的校准数据；根据所述眼动特征及调取的每个用户的校准数据，计算理论注视点坐标；
    第二判断单元，用于将所述理论注视点坐标分别与所述目标点位的坐标进行比对，判断所述待识别用户数是否为活体用户。
  12. 根据权利要求7所述的装置，其中，所述装置还包括：
    第一生成模块，用于按照时间先后顺序在显示屏上随机生成目标点位，每个时刻显示屏上显示一个目标点位且目标点位的位置是随机的；
    或者，第二生成模块，用于按照时间先后顺序及预设位置序列在显示屏上生成目标点位，每个时刻显示屏上显示一个目标点位且目标点位的位置是由所述预设位置序列设定的。
  13. 一种存储介质，其中，所述存储介质包括存储的程序，其中，在所述程序运行时控制所述存储介质所在设备执行权利要求1至6中任意一项所述的身份识别方法。
  14. 一种处理器，其中，所述处理器用于运行程序，其中，所述程序运行时执行权利要求1至6中任意一项所述的身份识别方法。
  15. 一种终端，其中，包括：
    采集模块，用于采集待识别用户注视目标点位时的眼部图像；
    身份识别模块，用于根据所述眼部图像及预先建立的用户身份信息数据库，对所述待识别用户进行身份识别；
    活体检测模块，用于根据所述眼部图像、所述目标点位的坐标、所述用户身份信息数据库及身份识别结果，对所述待识别用户进行活体检测；
    处理器，所述处理器运行程序，其中，所述程序运行时对于从所述采集模块、所述身份识别模块和所述活体检测模块输出的数据执行权利要求1至6中任意一项所述的身份识别方法。
  16. 一种终端，其中，包括：
    采集模块，用于采集待识别用户注视目标点位时的眼部图像；
    身份识别模块，用于根据所述眼部图像及预先建立的用户身份信息数据库，对所述待识别用户进行身份识别；
    活体检测模块，用于根据所述眼部图像、所述目标点位的坐标、所述用户身份信息数据库及身份识别结果，对所述待识别用户进行活体检测；
    存储介质，用于存储程序，其中，所述程序在运行时对于从所述采集模块、所述身份识别模块和所述活体检测模块输出的数据执行权利要求1至6中任意一项所述的身份识别方法。
PCT/CN2017/091264 2016-06-30 2017-06-30 一种身份识别方法及装置 WO2018001371A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
US16/312,301 US10891507B2 (en) 2016-06-30 2017-06-30 Method and device for recognizing identity
EP17819367.8A EP3480727A4 (en) 2016-06-30 2017-06-30 METHOD AND APPARATUS FOR IDENTITY RECOGNITION
AU2017287619A AU2017287619B2 (en) 2016-06-30 2017-06-30 Method and apparatus for identity recognition
JP2018565013A JP6762380B2 (ja) 2016-06-30 2017-06-30 身分認証方法および装置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610509755.3 2016-06-30
CN201610509755.3A CN106203297B (zh) 2016-06-30 2016-06-30 一种身份识别方法及装置

Publications (1)

Publication Number Publication Date
WO2018001371A1 true WO2018001371A1 (zh) 2018-01-04

Family

ID=57463172

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/091264 WO2018001371A1 (zh) 2016-06-30 2017-06-30 一种身份识别方法及装置

Country Status (6)

Country Link
US (1) US10891507B2 (zh)
EP (1) EP3480727A4 (zh)
JP (1) JP6762380B2 (zh)
CN (2) CN110705507B (zh)
AU (1) AU2017287619B2 (zh)
WO (1) WO2018001371A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112966142A (zh) * 2021-04-20 2021-06-15 南京云玑信息科技有限公司 一种准确率与识别速度提高的优化方法

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110705507B (zh) * 2016-06-30 2022-07-08 北京七鑫易维信息技术有限公司 一种身份识别方法及装置
CN108319830A (zh) * 2017-01-17 2018-07-24 中兴通讯股份有限公司 一种身份验证方法及装置
CN106713368B (zh) * 2017-03-08 2019-09-27 四川大学 一种身份验证方法及装置
CN106803829A (zh) * 2017-03-30 2017-06-06 北京七鑫易维信息技术有限公司 一种认证方法、装置及系统
US11403881B2 (en) * 2017-06-19 2022-08-02 Paypal, Inc. Content modification based on eye characteristics
CN108073897A (zh) * 2017-12-01 2018-05-25 沈海斌 一种基于视线的活体认证方法
CN112270299A (zh) * 2018-04-25 2021-01-26 北京嘀嘀无限科技发展有限公司 一种识别头部运动的系统和方法
CN109190509B (zh) 2018-08-13 2023-04-25 创新先进技术有限公司 一种身份识别方法、装置和计算机可读存储介质
CN109472195A (zh) * 2018-09-26 2019-03-15 北京七鑫易维信息技术有限公司 识别对象的方法、装置和系统
CN109655790A (zh) * 2018-12-18 2019-04-19 天津大学 基于室内led光源的多目标检测及身份识别系统及方法
CN110341617B (zh) * 2019-07-08 2021-05-28 北京七鑫易维信息技术有限公司 眼球追踪方法、装置、车辆和存储介质
CN110347257A (zh) * 2019-07-08 2019-10-18 北京七鑫易维信息技术有限公司 眼球追踪设备的校准方法、装置、设备和存储介质
CN111402480A (zh) * 2020-02-29 2020-07-10 深圳壹账通智能科技有限公司 访客信息管理方法、装置、系统、设备和存储介质
JP7314848B2 (ja) * 2020-03-25 2023-07-26 トヨタ自動車株式会社 表示制御装置、画像補正方法及びプログラム
CN111629265B (zh) * 2020-05-13 2021-12-21 深圳创维－Rgb电子有限公司 电视机及其电视控制方法、控制装置和可读存储介质
CN111985298B (zh) * 2020-06-28 2023-07-25 百度在线网络技术（北京）有限公司 人脸识别样本收集方法和装置
CN111860345A (zh) * 2020-07-22 2020-10-30 海尔优家智能科技（北京）有限公司 对象位置的确定方法、装置、存储介质及电子装置
CN112215113A (zh) * 2020-09-30 2021-01-12 张成林 人脸识别方法及装置
CN112232255B (zh) * 2020-10-26 2022-11-01 北京鹰瞳科技发展股份有限公司 基于多模态数据的身份认证方法及设备
CN114389909A (zh) * 2021-11-29 2022-04-22 珠海格力电器股份有限公司 设备控制方法、装置、存储介质及电子设备
CN114546569B (zh) * 2022-02-24 2024-06-04 深圳创维－Rgb电子有限公司 显示设备控制方法、装置、电子设备及可读存储介质
CN116049868B (zh) * 2022-07-26 2023-12-08 荣耀终端有限公司 隐私保护方法、设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1299103A (zh) * 1999-12-03 2001-06-13 朴宰佑 在网络上通过生物情报进行的使用者认证系统及方法
US20100202667A1 (en) * 2009-02-06 2010-08-12 Robert Bosch Gmbh Iris deblurring method based on global and local iris image statistics
CN105184277A (zh) * 2015-09-29 2015-12-23 杨晴虹 活体人脸识别方法以及装置
CN105354473A (zh) * 2015-11-09 2016-02-24 南京运航科技有限公司 基于虹膜识别认证的设备桌面解锁方法及装置
CN105550625A (zh) * 2015-06-30 2016-05-04 宇龙计算机通信科技(深圳)有限公司 一种活体虹膜检测方法及终端
CN106203297A (zh) * 2016-06-30 2016-12-07 北京七鑫易维信息技术有限公司 一种身份识别方法及装置

Family Cites Families (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4470663B2 (ja) * 2004-09-14 2010-06-02 沖電気工業株式会社 虹彩認証における不正検出システム
CN100392669C (zh) * 2006-09-21 2008-06-04 杭州电子科技大学 虹膜识别中的活体检测方法及装置
CN101727574A (zh) * 2008-10-17 2010-06-09 深圳富泰宏精密工业有限公司 虹膜识别系统及方法
US8364971B2 (en) * 2009-02-26 2013-01-29 Kynen Llc User authentication system and method
CN101833646B (zh) * 2009-03-11 2012-05-02 北京中科虹霸科技有限公司 一种虹膜活体检测方法
CN101710383B (zh) * 2009-10-26 2015-06-10 北京中星微电子有限公司 一种身份认证的方法及认证装置
CN102844766B (zh) * 2011-04-20 2014-12-24 中国科学院自动化研究所 基于人眼图像的多特征融合身份识别方法
EP3200046A1 (en) * 2011-10-27 2017-08-02 Tobii Technology AB Power management in an eye-tracking system
US9082011B2 (en) * 2012-03-28 2015-07-14 Texas State University—San Marcos Person identification using ocular biometrics with liveness detection
JP6175945B2 (ja) * 2013-07-05 2017-08-09 ソニー株式会社 視線検出装置及び視線検出方法
CN105243386B (zh) * 2014-07-10 2019-02-05 汉王科技股份有限公司 人脸活体判断方法以及系统
EP4047551A1 (en) * 2014-10-15 2022-08-24 NEC Corporation Impersonation detection device, impersonation detection method, and recording medium
WO2016076914A1 (en) 2014-11-13 2016-05-19 Intel Corporation Facial liveness detection in image biometrics
JP6452236B2 (ja) * 2014-12-08 2019-01-16 国立大学法人静岡大学 眼球識別装置及び眼球識別方法
CN104462923B (zh) * 2014-12-31 2018-10-09 河南华辰智控技术有限公司 应用于移动通信设备的智能型虹膜身份识别系统
US10678897B2 (en) * 2015-04-16 2020-06-09 Tobii Ab Identification, authentication, and/or guiding of a user using gaze information
CN114077726A (zh) * 2015-04-16 2022-02-22 托比股份公司 用于对用户进行认证的系统、方法和机器可读介质
CN104966070B (zh) * 2015-06-30 2018-04-10 北京汉王智远科技有限公司 基于人脸识别的活体检测方法和装置
US10546183B2 (en) * 2015-08-10 2020-01-28 Yoti Holding Limited Liveness detection
CN105184246B (zh) * 2015-08-28 2020-05-19 北京旷视科技有限公司 活体检测方法和活体检测系统
CN105139006A (zh) * 2015-09-29 2015-12-09 清华大学 一种基于虹膜变化的活体识别方法及系统
CN105205379A (zh) * 2015-10-28 2015-12-30 广东欧珀移动通信有限公司 一种终端应用的控制方法、装置和终端
TWI630507B (zh) * 2017-09-25 2018-07-21 仁寶電腦工業股份有限公司 目光偵測、辨識與控制方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1299103A (zh) * 1999-12-03 2001-06-13 朴宰佑 在网络上通过生物情报进行的使用者认证系统及方法
US20100202667A1 (en) * 2009-02-06 2010-08-12 Robert Bosch Gmbh Iris deblurring method based on global and local iris image statistics
CN105550625A (zh) * 2015-06-30 2016-05-04 宇龙计算机通信科技(深圳)有限公司 一种活体虹膜检测方法及终端
CN105184277A (zh) * 2015-09-29 2015-12-23 杨晴虹 活体人脸识别方法以及装置
CN105354473A (zh) * 2015-11-09 2016-02-24 南京运航科技有限公司 基于虹膜识别认证的设备桌面解锁方法及装置
CN106203297A (zh) * 2016-06-30 2016-12-07 北京七鑫易维信息技术有限公司 一种身份识别方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3480727A4 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112966142A (zh) * 2021-04-20 2021-06-15 南京云玑信息科技有限公司 一种准确率与识别速度提高的优化方法

Also Published As

Publication number Publication date
CN106203297B (zh) 2019-11-08
AU2017287619B2 (en) 2020-09-17
CN110705507B (zh) 2022-07-08
EP3480727A1 (en) 2019-05-08
JP6762380B2 (ja) 2020-09-30
CN106203297A (zh) 2016-12-07
EP3480727A4 (en) 2019-08-14
AU2017287619A1 (en) 2019-01-17
US20190205681A1 (en) 2019-07-04
US10891507B2 (en) 2021-01-12
CN110705507A (zh) 2020-01-17
JP2019522278A (ja) 2019-08-08

Similar Documents

Publication Publication Date Title
WO2018001371A1 (zh) 一种身份识别方法及装置
KR102139795B1 (ko) 생채 특징 패턴을 업데이트하는 방법 및 이를 위한 전자 장치
WO2019134246A1 (zh) 基于人脸识别的安全监控方法、装置及存储介质
KR102316278B1 (ko) 지문 정보를 저장하기 위한 전자 장치 및 방법
WO2019062080A1 (zh) 身份识别方法、电子装置及计算机可读存储介质
AU2017201463B2 (en) Methods and systems for authenticating users
CN108701178A (zh) 认证方法及使用认证方法的电子设备
WO2021004499A1 (zh) 一种人脸识别的方法和装置
CN110751025A (zh) 基于人脸识别的业务办理方法、装置、设备及介质
KR20180014624A (ko) 홍채 인증 시스템 및 방법
CN108804006B (zh) 用于可穿戴设备的解锁方法、装置、设备和存储介质
WO2019011072A1 (zh) 虹膜活体检测方法及相关产品
EP2984599A1 (en) The identity caddy: a tool for real-time determination of identity in the mobile environment
KR20160147515A (ko) 사용자 인증 방법 및 이를 지원하는 전자장치
KR102497477B1 (ko) 개인 정보를 보호하기 위한 방법 및 그 전자 장치
Kurkovsky et al. Experiments with simple iris recognition for mobile phones
CN107622246A (zh) 人脸识别方法及相关产品
EP4060551B1 (en) Fingerprint anti-counterfeiting method and electronic device
CN107368723A (zh) 一种身份认证方法、可穿戴设备及计算机可读存储介质
KR102579895B1 (ko) 전자장치, 이를 활용한 적외선 센서 기반의 심장 박동 수 측정 방법
US11636188B2 (en) Combining biometrics, hidden knowledge and intent to authenticate
CN110119604B (zh) 提高信息系统安全性的方法、装置、终端和存储设备
KR102574772B1 (ko) 생체 데이터를 등록 및 인증하기 위한 방법 및 그 전자 장치
WO2019218905A1 (zh) 验证对象的方法、装置和系统
CN107786349B (zh) 一种针对用户账号的安全管理方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17819367

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2018565013

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2017287619

Country of ref document: AU

Date of ref document: 20170630

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2017819367

Country of ref document: EP

Effective date: 20190130