CN110751025A - Business handling method, device, equipment and medium based on face recognition - Google Patents
Business handling method, device, equipment and medium based on face recognition Download PDFInfo
- Publication number
- CN110751025A CN110751025A CN201910842455.0A CN201910842455A CN110751025A CN 110751025 A CN110751025 A CN 110751025A CN 201910842455 A CN201910842455 A CN 201910842455A CN 110751025 A CN110751025 A CN 110751025A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- face recognition
- result
- face image
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 93
- 238000001514 detection method Methods 0.000 claims abstract description 60
- 238000012795 verification Methods 0.000 claims abstract description 56
- 230000008569 process Effects 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 230000009471 action Effects 0.000 claims description 9
- 238000007774 anilox coating Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 9
- 239000011159 matrix material Substances 0.000 description 5
- 239000003086 colorant Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000001815 facial effect Effects 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 2
- 238000001727 in vivo Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004397 blinking Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a business handling method, a device, equipment and a medium based on face recognition, wherein the business handling method based on face recognition comprises the steps of obtaining a business operation request, and if the business type is a specific type, obtaining a video stream recorded in real time, wherein the video stream comprises a video frame image; carrying out face detection on the video frame image to obtain a current face image; inquiring a user database based on the user identification to obtain an inquiry result; if the query result is not null, acquiring a target comparison image; calling a face recognition interface to process a current face image and a target comparison image to obtain a first score value; and if the first score value is smaller than the preset score value, inputting the current face image, the target comparison image and the third-party reticulated mottles image into a face recognition interface for processing, and acquiring a service operation result so as to solve the problem that the accuracy of face recognition identity verification is not high only according to the current face image and the third-party reticulated mottles image at present.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a business handling method, a business handling device, business handling equipment and a business handling medium based on face recognition.
Background
The face recognition technology is a biological recognition technology for carrying out identity recognition based on face feature information of people, and is a series of related technologies for collecting images or video streams containing faces by using a camera or a camera, automatically detecting and tracking the faces in the images and further carrying out face recognition on the detected faces. Traditional self-service business is handled when adopting face identification to carry out user authentication, only adopt current face image and third party's reticulation image to contrast, and often can receive the interference of some other factors when two images contrast, such as age, so it is not high to lead to adopting face identification to carry out authentication's rate of accuracy when leading to current self-service business to handle, and when the discernment fails, fail to provide alternative for the user, lead to the user can't handle the business, make the business handle by oneself have the limitation.
Disclosure of Invention
The embodiment of the invention provides a service handling method, a device, equipment and a medium based on face recognition, which are used for solving the problem that the user cannot handle services due to failure of face recognition at present, so that the service self-service handling has limitation.
A business handling method based on face recognition comprises the following steps:
acquiring a service operation request, wherein the service operation request comprises a user identifier and a service type;
if the service type is a specific type, acquiring a video stream recorded in real time, wherein the video stream comprises video frame images;
carrying out face detection on the video frame image to obtain a current face image;
inquiring a user database based on the user identification to obtain an inquiry result;
if the query result is not empty, acquiring a target comparison image based on the query result;
calling a face recognition interface to process the current face image and the target comparison image to obtain a first score value;
if the first score value is smaller than a preset score value, the current face image, the target comparison image and a third service handling device based on face recognition are processed, and the service handling device comprises:
a service operation request obtaining module, configured to obtain a service operation request, where the service operation request includes a user identifier and a service type;
the video stream acquisition module is used for acquiring a video stream recorded in real time if the service type is a specific type, wherein the video stream comprises video frame images;
the current face image acquisition module is used for carrying out face detection on the video frame image to acquire a current face image;
the query result acquisition module is used for querying the user database based on the user identification to acquire a query result;
the target comparison image acquisition module is used for acquiring a target comparison image based on the query result if the query result is not empty;
the first scoring value acquisition module is used for calling a face recognition interface to process the current face image and the target comparison image to acquire a first scoring value;
and the business operation result acquisition module is used for inputting the current face image, the target comparison image and the third-party reticulated images into the face recognition interface for processing to acquire a business operation result if the first score value is smaller than a preset score value.
A computer device comprises a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the processor implements the steps of the business transaction method based on face recognition when executing the computer program.
A computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the steps of the above-described face recognition-based transaction method.
In the above-mentioned service handling method, apparatus, device and medium based on face recognition, by obtaining a service operation request, the server makes a judgment according to the service type in the service operation request, if the service type is a specific type, a video stream recorded in real time is obtained, so as to perform face detection on the video frame image in the video stream, obtain a current face image to eliminate interference without a face, then query the user database based on the user identifier to obtain a query result, if the query result is not null, a target contrast image is obtained based on the query result, so as to facilitate the face recognition interface to process the current face image and the target contrast image to obtain a first score value, if the first score value is smaller than a preset score value, the current face image, the target contrast image and a third party cob's webbing image are input to the face recognition interface to be processed, and obtaining a service operation result to solve the problem that the accuracy of face identification authentication is not high only according to the current face image and the third-party reticulate pattern image, and effectively improve the accuracy of face identification authentication.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a schematic diagram of an application environment of a business handling method based on face recognition according to an embodiment of the present invention;
FIG. 2 is a flow chart of a business handling method based on face recognition according to an embodiment of the present invention;
FIG. 3 is a flow chart of a business handling method based on face recognition according to an embodiment of the present invention;
FIG. 4 is a detailed flowchart of step S17 in FIG. 2;
FIG. 5 is a flow chart of a business handling method based on face recognition according to an embodiment of the present invention;
FIG. 6 is a flow chart of a business handling method based on face recognition according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a face recognition-based transaction apparatus according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a computer device according to an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The business handling method based on face recognition provided by the embodiment of the invention can be applied to a self-service business handling system, is used for carrying out more detailed verification on the identity of a user, improves the accuracy of the user identity verification, further improves the business handling safety and is beneficial to the effectiveness of autonomous business handling. The service handling method based on face recognition can be applied to the application environment as shown in fig. 1, wherein computer equipment is communicated with a server through a network. The computer device may be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server may be implemented as a stand-alone server.
In an embodiment, as shown in fig. 2, a service handling method based on face recognition is provided, which is described by taking the server in fig. 1 as an example, and includes the following steps:
s11: and acquiring a service operation request, wherein the service operation request comprises a user identifier and a service type.
Wherein the user identifier is a unique identifier for identifying the user. The service operation request is a request for triggering the server to operate a certain service module. The type of service includes, but is not limited to, all services in the system, such as loans. Specifically, when entering the service system, the user needs to log in according to the user identifier and the user password, and after the login verification is passed, that is, after the user identifier and the user password are successfully matched, the user can enter the system, and the user can select the service of the service type to be handled in the system to perform operation, for example, select a loan service to perform loan application, and the like.
S12: and if the service type is a specific type, acquiring a video stream recorded in real time, wherein the video stream comprises video frame images.
In the scheme, the identity authentication requirements of different service types are different, for example, the loan service needs to be authenticated, and then the related service operation can be carried out; and the relevant business operation can be directly carried out without verification on basic business such as depositing and withdrawing. In particular, a particular type refers to a type of business that requires verification of the user's identity, such as loans. Specifically, if the service type is a specific type, an authentication process is entered, and a user is prompted to start a camera to record a video stream, so that a current face image containing a face is extracted subsequently. Understandably, in particular, the authentication process mainly adopts a face recognition technology to carry out authentication so as to effectively solve the phenomenon of imposition operation of others.
S13: and carrying out face detection on the video frame image to obtain a current face image.
The current face image is a face image obtained by inputting a video frame image into a pre-configured face detection interface for recognition. Specifically, the face detection interface can be implemented by training the image labeled with the face position by adopting a CascadeCNN network.
Specifically, the video frame images are input into a face detection model, whether each video frame image contains a face or not is detected, and then the frame image containing the face, namely the current face image, is extracted. The method comprises the steps of acquiring a human face, normalizing the human face to 256 × 256 pixels, and unifying the pixels of the video frame image to improve the efficiency of subsequent detection, wherein the human face needs to exist in the video frame image, the minimum size of the human face in a screen needs to reach 80 × 80 pixels, and after the human face is acquired.
Specifically, the step of performing face detection on at least one video frame image is as follows: and detecting whether a face exists in each video frame image by adopting a pre-trained face detection model, and if the face exists, taking the video frame image as the current face image. Specifically, the face detection model may adopt, but is not limited to, a model obtained by training based on a CascadeCNN network. CascadeCNN (face detection) is realized by a deep convolutional network of a classical Violajones method, and is a face detection method with higher detection speed. Violajones is a human face detection framework.
The CascadeCNN (face detection) is realized by a deep convolutional network of a classical Violajones method, and is a face detection method with high detection speed. Violajones is a human face detection framework. In this embodiment, the CascadeCNN method is adopted to train the image labeled with the face position, so as to realize a face detection interface and improve the detection efficiency of face detection. Specifically, a video frame image is input into a face detection interface configured in advance, the face position in the frame image is detected, a face image, namely a current face image, is further extracted, and if no face is detected, a user is prompted to shoot again.
S14: and querying a user database based on the user identification to obtain a query result.
S15: and if the query result is not null, acquiring a target comparison image based on the query result.
The target contrast image is an image determined based on the historical face image and used for face recognition. The server stores a plurality of historical face images corresponding to the user identification in advance, and queries a user database according to the user identification, so that the historical face images corresponding to the user identification can be quickly acquired. Specifically, a user database is queried based on the user identification to obtain a query result, if the query result is not empty, the user is proved not to transact the business for the first time, and a historical face image with the minimum time interval from the current system is obtained as a target comparison image based on the historical face image corresponding to the query result. The historical face image refers to a face image stored when the user transacts business each time.
In an embodiment, before step S13, as shown in fig. 3, the method for handling a business based on face recognition further includes the following steps:
s131: and generating living body verification information, wherein the living body verification information comprises a prompt action.
S132: and acquiring the video stream to be verified based on the prompt action.
S133: and calling a living body detection interface to carry out living body detection on the video stream to be verified, acquiring a detection result, and if the detection result is successful, carrying out face detection on the video frame image to acquire the current face image.
In this embodiment, before performing an identity verification (i.e., face recognition) process, a living body detection interface may also be called to perform living body verification on a target user. Specifically, the server generates living body verification information to prompt the target user for living body identification. The liveness verification information includes, but is not limited to, blinking, mouth opening, head shaking, and head nodding. The prompt action is prompted in a voice mode so as to avoid failure of the in-vivo verification and reduction of the efficiency of the in-vivo verification due to the fact that the prompt action is used as a new line when a user cannot clearly see the prompt action displayed on the interactive interface due to the fact that the text prompt is prompted on the interactive interface. The living body verification is carried out on the target user by calling the face living body recognition interface so as to verify whether the user is operated by the living body, common attack means such as photos, face changing, masks, sheltering and screen copying can be effectively resisted, and the safety of service handling is ensured.
S16: and calling a face recognition interface to process the current face image and the target comparison image to obtain a first score value.
The first scoring value is obtained by processing the current face image and the target comparison image through the face recognition interface. Specifically, before the face recognition interface is called to process the current face image and the target comparison image, the current face image and the target comparison image are respectively converted into base64 codes, and the face recognition interface is called to perform face recognition so as to obtain a first score value returned by the face recognition interface.
It should be noted that, the process of converting the current face image or the target contrast image into base64 encoding is as follows: the storage path of the current face image or the target contrast image is converted into a byte array by adopting a byte [ ] method, then the obtained byte array is subjected to BASE64 coding by adopting a BASE64 Encoder method, and a corresponding digital image is obtained, so that the digital image is identified by adopting a face identification interface. Because the security of converting the current face image or the target contrast image into the digital image coded by base64 is higher, the problem of user information leakage can be effectively avoided.
S17: and if the first score value is smaller than the preset score value, inputting the current face image, the target contrast image and the third-party reticulated images into a face recognition interface for processing, and acquiring a service operation result.
The third-party reticulated image refers to a reticulated image prestored in the public security system, and can be obtained by inquiring the third-party public security system through the user identification, namely the user identification number. The preset score is a threshold value for evaluating whether face recognition is successful. Specifically, if the first score value is not less than the preset score value, it is proved that the matching degree of the target comparison image of the user and the current face image is high, the historical recognition result corresponding to the target comparison image is used as a service operation result, that is, if the historical recognition result is successful, the service operation result with the operable service is obtained, identity verification is performed without adopting face recognition again, and the service handling efficiency is improved.
If the first score value is smaller than the preset score value, the fact that the matching degree of the current face image and the target contrast image is low due to the fact that the target contrast image is far away from the current time of the system is proved to be possible, the server inputs the current face image, the target contrast image and the third-party reticulated mottles image into a face recognition interface to be processed according to the preset contrast rule, a business operation result is obtained, identity verification is conducted through the combination of the current face image, the target contrast image and the third-party reticulated mottles image, the problem that the accuracy rate of whether face recognition passes or not is determined only through comparison between the current face image and the third-party reticulated mottles image at present is solved, an alternative verification scheme is provided for the user, and the generalization of a business handling.
In the embodiment, a service operation request is obtained, so that a server can judge according to a service type in the service operation request, if the service type is a specific type, a video stream recorded in real time is obtained, so that face detection is performed on a video frame image in the video stream, a current face image is obtained to eliminate interference without a face, a user database is queried based on a user identifier, a query result is obtained, if the query result is not null, a target comparison image is obtained based on the query result, so that the current face image and the target comparison image are processed by a face identification interface, a first score value is obtained, if the first score value is smaller than a preset score value, the current face image, the target comparison image and a third-party reticulated image are input into the face identification interface for processing, a service operation result is obtained, and the problem that the accuracy of face identification identity verification is not high only according to the current face image and the third-party reticulated image at present is solved The method and the system effectively improve the accuracy of face recognition authentication, provide an alternative authentication scheme for users, and improve the generalization and fault tolerance of a business handling system.
In an embodiment, as shown in fig. 4, in step S17, inputting the current face image, the target contrast image, and the third-party texture image into the face recognition interface for processing, and acquiring a service operation result, the method specifically includes the following steps:
s171: and calling a face recognition interface to process the current face image and the third-party reticulated images to obtain a second scoring value.
S172: and calling a face recognition interface to process the historical face image and the third-party reticulated images to obtain a third scoring value.
And the second scoring value is obtained by processing the current face image and the third-party anilox image through the face recognition interface. The third scoring value is obtained by processing the historical face image and the third-party anilox image through the face recognition interface. When the third-party texture image is used for face recognition, the third-party texture image is also converted into base64 code, and a face recognition interface is called for face recognition.
Specifically, the historical face image and the third-party reticulate pattern image are processed by calling a face recognition interface, namely, identity authentication is performed by face recognition, so that the problem that the accuracy of the result obtained only by comparing the current face image with the third-party reticulate pattern image is not high when identity authentication is performed by face recognition at present is solved, meanwhile, an alternative scheme is provided for a user, and the fault tolerance of a service system is improved.
S173: and performing weighted operation on the second score value and the third score value to obtain a service operation result.
Specifically, the second score value and the third score value may be weighted using the following formula,
wherein P represents the target score value, i represents the identifier corresponding to the second score value or the third score value, w represents the weight corresponding to the second score value or the weight corresponding to the third score value, and n represents the data dimension, in this embodiment, n is 2, that is, the second score value and the third score value.
Understandably, the third-party textured image comprises image uploading time, if the time interval of the current time of the image uploading time service handling system is short, the third-party textured image uploaded by the user in the public security system is proved to be recently updated, namely, the time interval between the current face image and the third-party textured image is short, the problem that the accuracy is not high due to the fact that the time interval between the two images is long cannot occur, so that the weight value corresponding to the second score value can be set to be relatively high, and the weight value corresponding to the third score value is set to be relatively low. If the time interval of the current time of the image uploading time service handling system is far, the fact that the third party anilox image uploaded by the user in the public security system is not updated is proved, the problem that the accuracy is not high due to the fact that the time interval of the two images is long may occur, therefore, the weight value corresponding to the second scoring value can be set to be relatively low, and the weight value corresponding to the third scoring value is set to be relatively high, and therefore the accuracy of face identity verification is further improved.
In the embodiment, the face recognition is respectively carried out on the current face image and the third-party reticulate pattern image, and the historical face image and the third-party reticulate pattern image to obtain the corresponding second score value and the third score value, and the analysis is carried out by integrating the second score value and the third score value to obtain the face recognition result, so that the problem that the face recognition accuracy is low due to the fact that the face recognition result is determined only by comparing the current face image and the third-party reticulate pattern image at present is solved.
In an embodiment, as shown in fig. 5, in step S15, that is, if the query result is not null, the method for obtaining the target comparison image based on the query result includes the following steps:
s151: and if the query result is not null, acquiring the image quantity of the historical face images corresponding to the query result.
S152: and if the number of the historical face images is equal to 1, taking the historical face images as target comparison images.
Specifically, if the number of images of the historical face image is equal to 1, it is proved that the user has transacted a service only by using the service system, and the historical face image is directly used as a target comparison image.
S153: and if the number of the historical face images is more than 1, calculating the time interval between the historical time corresponding to each historical face image and the current time of the system.
S154: and taking the historical face image with the minimum time interval as a target comparison image.
If the number of the images corresponding to the historical face images is greater than 1, the user uses the autonomous business handling system to handle business for multiple times, and in order to ensure the accuracy of subsequent face recognition, one historical face image closest to the current time of the system is used as a target comparison image, so that the problem that the accuracy of subsequent face recognition is affected due to the fact that the facial features of the user are changed greatly from the current facial features when the user handles business within the historical time is effectively solved. Specifically, if the number of images corresponding to the historical face images is greater than 1, the time interval between the historical time corresponding to each historical face image and the current time of the system is calculated, and the historical face image corresponding to the historical time with the minimum time interval is used as a target comparison image, that is, a historical face image closest to the current time of the system is used as the target comparison image.
In this embodiment, the number of the images of the historical face images is determined, that is, if the number of the images of the historical face images is equal to 1, the historical face images are used as target comparison images, and if the number of the images of the historical face images is greater than 1, the time interval between the historical time corresponding to each historical face image and the current time of the system is calculated, and the historical face image with the minimum time interval is used as the target comparison image, so that the problem that the change of the facial features and the current facial features when a user transacts a service in the historical time is large and the accuracy of subsequent face recognition is affected is effectively solved, and the accuracy of face recognition is further improved.
In an embodiment, as shown in fig. 6, after step S14, the method for handling business based on face recognition further includes the following steps:
s21: and if the query result is null, acquiring the identity verification image uploaded by the image acquisition module.
Specifically, if the query result is null, it is proved that the user does not use the system to transact the service, that is, the user transacts the service for the first time, and the authenticity of the user identity needs to be verified first. The authentication image includes, but is not limited to, an identification card image of the user. In this embodiment, the user may upload the identification card image through an image acquisition module provided in the system, and click an "upload" button to upload, so that the server acquires the identification card image. The image acquisition module includes, but is not limited to, taking with a camera and uploading locally.
Further, after obtaining the authentication image uploaded by the user, the method further comprises the step of performing fuzzy check on the authentication image, and the specific process is as follows: graying an authentication image uploaded by a user, performing convolution processing by using a Laplacian operator (which can be understood as a matrix of 3x 3) of 3x3, calculating a standard deviation of the image after convolution by using an std2() function, squaring the standard deviation to obtain a variance of the image, judging the variance, prompting to shoot again if the variance corresponding to the face image is verified to be smaller than a preset threshold value until a clearer authentication image is obtained, and improving the accuracy of subsequent face recognition.
S22: and carrying out image preprocessing on the identity authentication image to obtain a face image to be authenticated.
The preprocessing includes, but is not limited to, a sharpening process, a graying process, and a perspective transformation process. Specifically, in order to make the edge, the contour line, and the details of the image clear, the authentication image needs to be sharpened first, and a sharpened image is obtained. After the sharpened image is obtained, since the sharpened image may contain multiple colors, the colors themselves are very easily affected by factors such as illumination, and the colors of similar objects are changed, the colors themselves are difficult to provide key information, and therefore, the sharpened image needs to be grayed to obtain a human face image to be verified, so as to eliminate interference and reduce the complexity of the image and the information processing amount.
Because the identity verification image may have different degrees of inclination, which affects the model recognition result, the identity verification image needs to be subjected to a process of perspective transformation (correction), that is, the identity verification image is projected to a new view plane, and the corrected image is obtained. In this embodiment, the processing method of the perspective transformation includes, but is not limited to, performing the perspective transformation processing by using a perspectrive () function in OpenCv. OpenCV is a cross-platform computer vision library containing a large number of open source APIs (interfaces), and provides interfaces of languages such as Python, Ruby, MATLAB and the like, so that a lot of general algorithms in the aspects of image processing and computer vision are realized.
In this embodiment, the sharpening method includes, but is not limited to, using any one of a laplacian operator, a sobel (weighted average difference) operator, and a Prewitt (average difference) operator, which are commonly used in the prior art, and taking the sobel operator method as an example, the following formula may be used to transform the pixel matrix M (i, j) corresponding to the authentication image.
A＝|(M(i-1，j-1)+2M(i-1,j)+M(i-1,j+1))-(M(i+1,j-1)+2M(i+1,j)+M(i+1,j+1))|
B＝|(M(i-1，j-1)+2M(i,j-1)+M(i+1,j-1))-(M(i-1,j+1)+2M(i,j+1)+M(i+1,j+1))
S(i,j)＝A+B
Wherein M (i, j) represents the pixel matrix corresponding to the authentication image. i, j denote the rows and columns of the matrix, respectively. S (i, j) represents a pixel matrix corresponding to the sharpened image, a represents a weighting factor in the horizontal direction, and B represents a weighting factor in the vertical direction.
S23: and carrying out face detection on the face image to be verified to obtain the face image to be recognized.
The face image to be recognized is a face image obtained by inputting a video frame image into a face detection interface configured in advance for recognition. In this embodiment, the face detection interface may be implemented by training the image labeled with the face position by using a CascadeCNN network.
The CascadeCNN (face detection) is realized by a deep convolutional network of a classical Violajones method, and is a face detection method with high detection speed. Violajones is a human face detection framework. In this embodiment, the CascadeCNN method is adopted to train the image labeled with the face position, so as to realize a face detection interface and improve the detection efficiency of face detection. Specifically, a video frame image is input into a face detection interface which is configured in advance, the face position in the frame image is detected, a face image, namely a face image to be recognized, is further extracted, and if no face is detected, a user is prompted to shoot again.
S24: and calling a face recognition interface to process the face image to be recognized and the current face image to obtain a recognition result.
S25: and if the identification result is successful, acquiring a service operation result with operable service.
S26: and storing the current face image, the recognition result and the user identification in a user database in an associated manner so as to update the user database.
Specifically, a face recognition interface is called to process a face image to be recognized and a current face image, namely, the face image to be recognized and the current face image are verified through the face recognition interface to determine whether a user is matched with a certificate image or not, so that the purpose of verifying the authenticity of the identity of the user is achieved. The face recognition interface returns a recognition result, if the recognition result is successful, the face recognition interface proves whether the user is matched with the certificate image, namely the user is the user himself, the service operation result with operable service can be directly obtained, specifically, the user can be successfully registered, and the service system can be operated with authority. In this embodiment, when the recognition result is successful, the current face image and the recognition result are also stored in the database in association with the user identifier, that is, the current face image is stored in the database as a historical face image, so that the historical face image is used for verification in the following.
In this embodiment, if the query result is empty, the authenticity of the user identity needs to be verified first, so as to perform identity verification according to the authentication image uploaded by the user, and ensure that the user identity is authentic and valid, and if the user identity is authentic and valid, the current face image is stored in the user database as the historical face image, the recognition result, and the user identifier in an associated manner, so as to update the user database, so that when a subsequent user transacts the service again, the historical face image can be directly queried to repeatedly perform steps S14-S16.
In an embodiment, before step S24, the method for handling a service based on face recognition further includes the following steps:
s241: and inputting the face image to be recognized into a third-party identity verification interface for identity validity verification, and if the verification result passes, executing to call the face recognition interface to process the face image to be recognized and the current face image to obtain a recognition result.
Specifically, before the face image to be recognized and the current face image are processed by calling the face recognition interface, the face image to be recognized needs to be input to a third-party verification interface to verify the identity validity, that is, to verify whether the face image to be recognized of the user is a real and valid image, which can be understood as verifying whether the identity verification image uploaded by the user is recorded in a public security system, and further, verifying whether the face image to be recognized is a real and valid image. The third party verification interface is an interface which is provided by a public security system and used for verifying whether the user identity card image is real and valid, the third party verification interface can return a verification result, and the third party verification interface is used for continuously executing the step of processing the face image to be recognized and the current face image by calling the face recognition interface to acquire the recognition result if the verification result passes, namely the identity verification image uploaded by the user is proved to be real and valid; and the other is that the verification result is failed, namely the identity verification image uploaded by the user is proved to be an invalid certificate image, the service operation result which is not operable by the service is directly obtained, and the user is prompted to upload a real and valid certificate image.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In an embodiment, a business handling device based on face recognition is provided, and the business handling device based on face recognition corresponds to the business handling method based on face recognition in the above embodiment one to one. As shown in fig. 7, the service handling apparatus based on face recognition includes a service operation request obtaining module 11, a video stream obtaining module 12, a current face image obtaining module 13, a query result obtaining module 14, a target comparison image obtaining module 15, a first score value obtaining module 16, and a service operation result obtaining module 17. The functional modules are explained in detail as follows:
a service operation request obtaining module 11, configured to obtain a service operation request, where the service operation request includes a user identifier and a service type.
And a video stream obtaining module 12, configured to obtain a video stream recorded in real time if the service type is a specific type, where the video stream includes video frame images.
And the current face image acquisition module 13 is configured to perform face detection on the video frame image to acquire a current face image.
And the query result acquisition module 14 is used for querying the user database based on the user identifier to acquire a query result.
And the target comparison image obtaining module 15 is configured to, if the query result is not empty, obtain a target comparison image based on the query result.
And the first score value acquisition module 16 is configured to invoke a face recognition interface to process the current face image and the target comparison image, and acquire a first score value.
And the business operation result acquisition module 17 is configured to, if the first score value is smaller than a preset score value, input the current face image, the target comparison image, and the third-party moire image into the face recognition interface for processing, and acquire a business operation result.
Specifically, the service operation result acquisition module comprises a second score value acquisition unit, a third score value acquisition unit and a service operation result acquisition unit.
And the second scoring value acquisition unit is used for calling the face recognition interface to process the current face image and the third-party anilox image to acquire a second scoring value.
And the third scoring value acquisition unit is used for calling the face recognition interface to process the historical face image and the third-party anilox image to acquire a third scoring value.
And the business operation result acquisition unit is used for carrying out weighted operation on the second score value and the third score value to acquire a business operation result.
Specifically, the business transaction device based on face recognition further comprises an image quantity acquisition unit, a first target comparison image acquisition unit, a time interval acquisition unit and a second target comparison image acquisition unit.
And the image quantity acquisition unit is used for acquiring the image quantity of the historical face image corresponding to the query result if the query result is not empty.
And the first target comparison image acquisition unit is used for taking the historical face image as a target comparison image if the image quantity of the historical face image is equal to 1.
And the time interval acquisition unit is used for calculating the time interval between the historical time corresponding to each historical face image and the current time of the system if the number of the historical face images is greater than 1.
And the second target comparison image acquisition unit is used for taking the historical face image with the minimum time interval as a target comparison image.
Specifically, the business handling device based on face recognition further comprises an identity verification image acquisition unit, a face image to be verified acquisition unit, a face image to be recognized acquisition unit, a recognition result acquisition unit and a business operation result acquisition unit.
And the identity verification image acquisition unit is used for acquiring the identity verification image uploaded by the image acquisition module if the query result is empty.
And the face image acquisition unit to be verified is used for carrying out face detection on the identity verification image to acquire the face image to be verified.
And the face image acquisition unit to be recognized is used for carrying out image preprocessing on the face image to be verified to acquire the face image to be recognized.
And the recognition result acquisition unit is used for calling a face recognition interface to process the face image to be recognized and the current face image to acquire a recognition result.
And the service operation result acquisition unit is used for acquiring a service operation result with operable service if the identification result is successful.
And the user database updating unit is used for storing the current face image, the recognition result and the user identification in the user database in an associated manner so as to update the user database.
Specifically, the service handling device based on face recognition further comprises an identity verification unit.
And the identity verification unit is used for inputting the face image to be recognized into the third-party identity verification interface for identity validity verification, and if the verification result passes, executing to call the face recognition interface to process the face image to be recognized and the current face image to obtain a recognition result.
Specifically, the business handling device based on face recognition further comprises a living body verification information generation unit, a to-be-verified video stream acquisition unit and a living body detection unit.
A living body authentication information generation unit for generating living body authentication information including a prompt action.
And the to-be-verified video stream acquiring unit is used for acquiring the to-be-verified video stream based on the prompt action.
And the living body detection unit is used for calling a living body detection interface to carry out living body detection on the video stream to be verified, acquiring a detection result, and if the detection result is successful, carrying out face detection on the video frame image to acquire the current face image.
For specific limitations of the service handling apparatus based on face recognition, refer to the above limitations of the service handling method based on face recognition, which are not described herein again. All or part of the modules in the business handling device based on the face recognition can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a computer readable storage medium, an internal memory. The computer readable storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the computer-readable storage medium. The database of the computer device is used for storing data generated or acquired during execution of the business transaction method based on face recognition, such as historical face images. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a business transaction method based on face recognition.
In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the steps of the business transaction method based on face recognition in the above embodiments, such as the steps S11-S17 shown in fig. 2 or the steps shown in fig. 3 to 6. Alternatively, the processor implements the functions of each module/unit in the embodiment of the service transaction apparatus based on face recognition when executing the computer program, for example, the functions of each module/unit shown in fig. 7, and are not described herein again to avoid repetition.
In an embodiment, a computer-readable storage medium is provided, where a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program implements the steps of the service handling method based on face recognition in the foregoing embodiments, such as steps S11-S17 shown in fig. 2 or steps shown in fig. 3 to fig. 6, which are not repeated herein to avoid repetition. Alternatively, when being executed by the processor, the computer program implements the functions of the modules/units in the embodiment of the service transaction apparatus based on face recognition, for example, the functions of the modules/units shown in fig. 7, and are not described herein again to avoid repetition.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A business handling method based on face recognition is characterized by comprising the following steps:
acquiring a service operation request, wherein the service operation request comprises a user identifier and a service type;
if the service type is a specific type, acquiring a video stream recorded in real time, wherein the video stream comprises video frame images;
carrying out face detection on the video frame image to obtain a current face image;
inquiring a user database based on the user identification to obtain an inquiry result;
if the query result is not empty, acquiring a target comparison image based on the query result;
calling a face recognition interface to process the current face image and the target comparison image to obtain a first score value;
and if the first score value is smaller than a preset score value, inputting the current face image, the target contrast image and a third-party reticulate pattern image into the face recognition interface for processing, and acquiring a service operation result.
2. The business handling method based on face recognition according to claim 1, wherein if the current face image, the target contrast image and the third party texture image are input to the face recognition interface for processing, and a business operation result is obtained, the method comprises:
calling the face recognition interface to process the current face image and the third-party anilox image to obtain a second score value;
calling a face recognition interface to process the historical face image and the third-party reticulate pattern image to obtain a third scoring value;
and performing weighted operation on the second score value and the third score value to obtain a service operation result.
3. The business handling method based on face recognition according to claim 1, wherein if the query result is not empty, a target comparison image is obtained based on the query result, including;
if the query result is not empty, acquiring the image quantity of the historical face image corresponding to the query result;
if the number of the historical face images is equal to 1, taking the historical face images as the target comparison images;
if the number of the historical face images is larger than 1, calculating the time interval between the historical time corresponding to each historical face image and the current time of the system;
and taking the historical face image with the minimum time interval as the target comparison image.
4. The business handling method based on face recognition according to claim 1, wherein after the querying the user database based on the user identifier and obtaining the query result, the method comprises:
if the query result is empty, acquiring an identity verification image uploaded by an image acquisition module;
performing face detection on the identity verification image to obtain a face image to be verified;
carrying out image preprocessing on the face image to be verified to obtain a face image to be recognized;
calling the face recognition interface to process the face image to be recognized and the current face image to obtain a recognition result;
if the identification result is successful, acquiring a service operation result with operable service;
and storing the current face image, the recognition result and the user identification in a user database in an associated manner so as to update the user database.
5. The service handling method based on face recognition according to claim 4, wherein before the calling the face recognition interface to process the face image to be recognized and the current face image and obtain the recognition result, the service handling method based on face recognition further comprises:
and inputting the face image to be recognized into a third-party identity verification interface for identity validity verification, and if the verification result passes, executing the calling of the face recognition interface to process the face image to be recognized and the current face image to obtain a recognition result.
6. The service handling method based on face recognition according to claim 1, wherein before the face detection is performed on the video frame image to obtain the current face image, the service handling method based on face recognition further comprises:
generating living body verification information, wherein the living body verification information comprises a prompt action;
acquiring a video stream to be verified based on the prompt action;
and calling a living body detection interface to carry out living body detection on the video stream to be verified, acquiring a detection result, and if the detection result is successful, executing the face detection on the video frame image to acquire the current face image.
7. A business handling device based on face recognition is characterized by comprising:
a service operation request obtaining module, configured to obtain a service operation request, where the service operation request includes a user identifier and a service type;
the video stream acquisition module is used for acquiring a video stream recorded in real time if the service type is a specific type, wherein the video stream comprises video frame images;
the current face image acquisition module is used for carrying out face detection on the video frame image to acquire a current face image;
the query result acquisition module is used for querying the user database based on the user identification to acquire a query result;
the target comparison image acquisition module is used for acquiring a target comparison image based on the query result if the query result is not empty;
the first scoring value acquisition module is used for calling a face recognition interface to process the current face image and the target comparison image to acquire a first scoring value;
and the business operation result acquisition module is used for inputting the current face image, the target comparison image and the third-party reticulated images into the face recognition interface for processing to acquire a business operation result if the first score value is smaller than a preset score value.
8. The business handling device based on face recognition according to claim 1, wherein the business operation result obtaining module comprises:
the second scoring value acquisition unit is used for calling the face recognition interface to process the current face image and the third-party anilox image to acquire a second scoring value;
a third scoring value obtaining unit, configured to call a face recognition interface to process the historical face image and the third-party texture image, and obtain a third scoring value;
and the business operation result acquisition unit is used for carrying out weighted operation on the second score value and the third score value to acquire a business operation result.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the face recognition based transaction method according to any of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the face recognition based transaction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910842455.0A CN110751025A (en) | 2019-09-06 | 2019-09-06 | Business handling method, device, equipment and medium based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910842455.0A CN110751025A (en) | 2019-09-06 | 2019-09-06 | Business handling method, device, equipment and medium based on face recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110751025A true CN110751025A (en) | 2020-02-04 |
Family
ID=69276117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910842455.0A Pending CN110751025A (en) | 2019-09-06 | 2019-09-06 | Business handling method, device, equipment and medium based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110751025A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111768178A (en) * | 2020-06-30 | 2020-10-13 | 银联商务股份有限公司 | Method and related device for examining and approving business member |
| CN112084355A (en) * | 2020-09-14 | 2020-12-15 | 重庆农村商业银行股份有限公司 | Face sub-library updating method, device, equipment and storage medium |
| CN112132074A (en) * | 2020-09-28 | 2020-12-25 | 平安养老保险股份有限公司 | Face image verification method and device, computer equipment and storage medium |
| CN112215574A (en) * | 2020-10-19 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | Method, device and equipment for generating driving management business work order and storage medium |
| CN112287830A (en) * | 2020-10-29 | 2021-01-29 | 泰康保险集团股份有限公司 | Image detection method and device |
| CN112632504A (en) * | 2020-12-17 | 2021-04-09 | 苏宁金融科技(南京)有限公司 | Webpage access method, device, system, computer equipment and storage medium |
| CN112686244A (en) * | 2020-12-29 | 2021-04-20 | 平安银行股份有限公司 | Automatic approval method, device, equipment and medium based on picture processing interface |
| CN112800997A (en) * | 2020-04-10 | 2021-05-14 | 支付宝(杭州)信息技术有限公司 | Living body detection method, device and equipment |
| CN112818960A (en) * | 2021-03-25 | 2021-05-18 | 平安科技（深圳）有限公司 | Waiting time processing method, device, equipment and medium based on face recognition |
| CN112989307A (en) * | 2021-04-21 | 2021-06-18 | 北京金和网络股份有限公司 | Service information processing method, device and terminal |
| CN113111846A (en) * | 2021-04-29 | 2021-07-13 | 上海商汤智能科技有限公司 | Diagnosis method, device, equipment and storage medium based on face recognition |
| CN113222466A (en) * | 2021-05-28 | 2021-08-06 | 深圳市大恩信息科技有限公司 | Accounting project process monitoring method and system based on ERP |
| CN114676409A (en) * | 2022-02-28 | 2022-06-28 | 广西柳钢东信科技有限公司 | Online electronic signing method based on mobile phone screen video and AI voice synthesis |
| CN114978759A (en) * | 2022-06-25 | 2022-08-30 | 平安银行股份有限公司 | Test method, test system thereof, electronic device, and computer-readable storage medium |
| CN115100713A (en) * | 2022-06-27 | 2022-09-23 | 飞虎互动科技(北京)有限公司 | Financial wind control detection method and device based on real-time audio and video and electronic equipment |
| CN115564387A (en) * | 2022-10-19 | 2023-01-03 | 常州瀚森科技股份有限公司 | Digital intelligent operation management method and system for industrial park under digital economic condition |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109003178A (en) * | 2018-06-26 | 2018-12-14 | 深圳市买买提信息科技有限公司 | A kind of recognition of face service-seeking method, apparatus and terminal device |
| CN110009481A (en) * | 2019-03-12 | 2019-07-12 | 平安科技（深圳）有限公司 | A kind of loan measures and procedures for the examination and approval and system based on recognition of face |
| WO2019144513A1 (en) * | 2018-01-24 | 2019-08-01 | 平安科技（深圳）有限公司 | Bank password information change implementation method, device, and system, and storage medium |
| CN110086799A (en) * | 2019-04-23 | 2019-08-02 | 广州腾讯科技有限公司 | Auth method and device |
-
2019
- 2019-09-06 CN CN201910842455.0A patent/CN110751025A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019144513A1 (en) * | 2018-01-24 | 2019-08-01 | 平安科技（深圳）有限公司 | Bank password information change implementation method, device, and system, and storage medium |
| CN109003178A (en) * | 2018-06-26 | 2018-12-14 | 深圳市买买提信息科技有限公司 | A kind of recognition of face service-seeking method, apparatus and terminal device |
| CN110009481A (en) * | 2019-03-12 | 2019-07-12 | 平安科技（深圳）有限公司 | A kind of loan measures and procedures for the examination and approval and system based on recognition of face |
| CN110086799A (en) * | 2019-04-23 | 2019-08-02 | 广州腾讯科技有限公司 | Auth method and device |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112800997B (en) * | 2020-04-10 | 2024-01-05 | 支付宝(杭州)信息技术有限公司 | Living body detection method, device and equipment |
| CN112800997A (en) * | 2020-04-10 | 2021-05-14 | 支付宝(杭州)信息技术有限公司 | Living body detection method, device and equipment |
| CN111768178A (en) * | 2020-06-30 | 2020-10-13 | 银联商务股份有限公司 | Method and related device for examining and approving business member |
| CN112084355A (en) * | 2020-09-14 | 2020-12-15 | 重庆农村商业银行股份有限公司 | Face sub-library updating method, device, equipment and storage medium |
| CN112132074A (en) * | 2020-09-28 | 2020-12-25 | 平安养老保险股份有限公司 | Face image verification method and device, computer equipment and storage medium |
| CN112215574A (en) * | 2020-10-19 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | Method, device and equipment for generating driving management business work order and storage medium |
| CN112287830A (en) * | 2020-10-29 | 2021-01-29 | 泰康保险集团股份有限公司 | Image detection method and device |
| CN112632504A (en) * | 2020-12-17 | 2021-04-09 | 苏宁金融科技(南京)有限公司 | Webpage access method, device, system, computer equipment and storage medium |
| CN112686244A (en) * | 2020-12-29 | 2021-04-20 | 平安银行股份有限公司 | Automatic approval method, device, equipment and medium based on picture processing interface |
| CN112686244B (en) * | 2020-12-29 | 2024-03-19 | 平安银行股份有限公司 | Automatic approval method, device, equipment and medium based on picture processing interface |
| CN112818960A (en) * | 2021-03-25 | 2021-05-18 | 平安科技（深圳）有限公司 | Waiting time processing method, device, equipment and medium based on face recognition |
| CN112818960B (en) * | 2021-03-25 | 2023-09-05 | 平安科技（深圳）有限公司 | Waiting time processing method, device, equipment and medium based on face recognition |
| CN112989307A (en) * | 2021-04-21 | 2021-06-18 | 北京金和网络股份有限公司 | Service information processing method, device and terminal |
| CN113111846A (en) * | 2021-04-29 | 2021-07-13 | 上海商汤智能科技有限公司 | Diagnosis method, device, equipment and storage medium based on face recognition |
| CN113222466A (en) * | 2021-05-28 | 2021-08-06 | 深圳市大恩信息科技有限公司 | Accounting project process monitoring method and system based on ERP |
| CN114676409A (en) * | 2022-02-28 | 2022-06-28 | 广西柳钢东信科技有限公司 | Online electronic signing method based on mobile phone screen video and AI voice synthesis |
| CN114978759A (en) * | 2022-06-25 | 2022-08-30 | 平安银行股份有限公司 | Test method, test system thereof, electronic device, and computer-readable storage medium |
| CN114978759B (en) * | 2022-06-25 | 2024-03-22 | 平安银行股份有限公司 | Test method and test system thereof, electronic device and computer readable storage medium |
| CN115100713A (en) * | 2022-06-27 | 2022-09-23 | 飞虎互动科技(北京)有限公司 | Financial wind control detection method and device based on real-time audio and video and electronic equipment |
| CN115100713B (en) * | 2022-06-27 | 2024-01-30 | 飞虎互动科技(北京)有限公司 | Financial wind control detection method and device based on real-time audio and video and electronic equipment |
| CN115564387A (en) * | 2022-10-19 | 2023-01-03 | 常州瀚森科技股份有限公司 | Digital intelligent operation management method and system for industrial park under digital economic condition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110751025A (en) | Business handling method, device, equipment and medium based on face recognition | |
| US20200175250A1 (en) | Feature extraction and matching for biometric authentication | |
| KR102038851B1 (en) | Method and system for verifying identities | |
| WO2018001371A1 (en) | Method and apparatus for identity recognition | |
| WO2019062080A1 (en) | Identity recognition method, electronic device, and computer readable storage medium | |
| CN109756458B (en) | Identity authentication method and system | |
| CN111340008A (en) | Method and system for generation of counterpatch, training of detection model and defense of counterpatch | |
| CN111191567A (en) | Identity data processing method and device, computer equipment and storage medium | |
| US10885171B2 (en) | Authentication verification using soft biometric traits | |
| US20110142297A1 (en) | Camera Angle Compensation in Iris Identification | |
| CN106096582A (en) | Distinguish real and flat surfaces | |
| US20160294824A1 (en) | Methods and systems for detecting head motion during an authentication transaction | |
| CN111339897B (en) | Living body identification method, living body identification device, computer device, and storage medium | |
| CN110612530A (en) | Method for selecting a frame for use in face processing | |
| CN116453196B (en) | Face recognition method and system | |
| CN112418189B (en) | Face recognition method, device and equipment for wearing mask and storage medium | |
| CN111079587A (en) | Face recognition method and device, computer equipment and readable storage medium | |
| KR20220062595A (en) | A method for obtaining data from an image of an object of a user that has a biometric characteristic of the user | |
| US9613252B1 (en) | Fingerprint matching method and device | |
| KR20200109977A (en) | Smartphone-based identity verification method using fingerprints and facial images | |
| CN116681443A (en) | Payment method and device based on biological recognition | |
| WO2022104340A1 (en) | Artificial intelligence for passive liveness detection | |
| CN116226817A (en) | Identity recognition method, identity recognition device, computer equipment and storage medium | |
| CN114067383B (en) | Passive three-dimensional facial imaging based on macrostructure and microstructure image dimensions | |
| KR20210050649A (en) | Face verifying method of mobile device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200204 |
|
| WD01 | Invention patent application deemed withdrawn after publication |