CN110825765B - Face recognition method and device - Google Patents
Face recognition method and device Download PDFInfo
- Publication number
- CN110825765B CN110825765B CN201911012966.6A CN201911012966A CN110825765B CN 110825765 B CN110825765 B CN 110825765B CN 201911012966 A CN201911012966 A CN 201911012966A CN 110825765 B CN110825765 B CN 110825765B
- Authority
- CN
- China
- Prior art keywords
- face
- image
- face image
- screening
- request
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/2425—Iterative querying; Query formulation based on the results of a preceding query
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- 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
- G06V40/168—Feature extraction; Face representation
-
- 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
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Probability & Statistics with Applications (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Fuzzy Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a method and a device for face recognition, and relates to the technical field of computers. One embodiment of the method comprises: receiving a face pre-screening request, wherein the face pre-screening request comprises a first face image; searching an image set matched with the first face image from a face database according to the face pre-screening request, and storing the image set into the face pre-screening database; receiving a face recognition request, wherein the face recognition request comprises a second face image; and searching a face image matched with the second face image from the face pre-screening database according to the face recognition request, and taking the user information of the searched face image as a face recognition result. This embodiment is through carrying out prescreening in order to improve face identification's speed and efficiency to the face database, and the user need not to discern accurately through other additional means when carrying out face identification, has satisfied the scenic safety check-up demand in big passenger flow field, and face identification's speed and the degree of accuracy all have very big improvement.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for face recognition.
Background
At present, a face recognition technology based on RGB visible light images is relatively mature, and application scenes and application ranges are increasingly wide.
The main application scenarios of the face recognition technology are as follows: after face registration is carried out, the information processing system inputs user information and face images in a full amount, and when a user needs to carry out safety verification through a face, 1.
However, as N increases, the time consumption for recognition also increases, and the accuracy of various face recognition algorithms also decreases, and especially for some large passenger flow scenes, such as subway, airport, and bus, etc., the face recognition becomes unrealistic.
In order to improve the efficiency of face recognition, some additional means such as swiping an identity card or inputting a mobile phone number can be added, and the identity of the user can be accurately confirmed according to the additional information, however, the schemes still need the user to carry the identity card or manually input numbers, and poor experience is brought to the user.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:
along with the increase of the number of registered people, the efficiency and the accuracy of face recognition are reduced; and if the face recognition is carried out by combining additional technical means such as identity card swiping or mobile phone number inputting, the user needs to carry the certificate or manually input numbers, so that poor experience is brought to the user, and the face recognition method is not suitable for application scenes needing quick passing under large passenger flows, and the passing capacity of public places is influenced.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for face recognition, which can improve the speed and efficiency of face recognition by pre-screening a face database, and when a user performs face recognition, the user can accurately perform recognition without other additional means, thereby meeting the security verification requirement in a large passenger flow field, and greatly improving the speed and accuracy of face recognition.
To achieve the above object, according to an aspect of an embodiment of the present invention, a method of face recognition is provided.
A method of face recognition, comprising: receiving a face pre-screening request, wherein the face pre-screening request comprises a first face image; searching an image set matched with the first face image from a face database according to the face pre-screening request, and storing the image set into the face pre-screening database; receiving a face recognition request, wherein the face recognition request comprises a second face image; and searching the face image matched with the second face image from the face prescreening database according to the face identification request, and taking the user information of the searched face image as a face identification result.
Optionally, searching an image set matching the first face image from a face database according to the face prescreening request includes: performing feature extraction on the first face image to obtain a first feature; respectively carrying out similarity comparison on the features of each face image in a face database and the first features to obtain an image set matched with the first face image, wherein the image set is a face image corresponding to the features of which the similarity meets a first threshold value; searching the face image matched with the second face image from the face prescreening database according to the face identification request comprises the following steps: extracting the features of the second face image to obtain second features; and respectively carrying out similarity comparison on the features of each face image in the face prescreening database and the second features to obtain a face image matched with the second face image, wherein the face image matched with the second face image is a face image corresponding to the feature with the highest similarity in the features with the similarity meeting a second threshold, and the second threshold is greater than the first threshold.
Optionally, before receiving the face recognition request, the method further includes: and determining that the object corresponding to the second face image is a living body.
Optionally, the first face image is obtained by acquiring a video, extracting an image from the video, and then performing quality screening and face tracking processing on the extracted image.
Optionally, the extracted image is quality screened by not less than one of the following indicators: image definition, human face shielding rate and human face deflection angle.
Optionally, the face prescreening database includes a plurality of levels of databases.
According to another aspect of the embodiments of the present invention, an apparatus for face recognition is provided.
An apparatus for face recognition, comprising: the system comprises a pre-screening request receiving module, a pre-screening request receiving module and a pre-screening request sending module, wherein the pre-screening request receiving module is used for receiving a face pre-screening request which comprises a first face image; the pre-screening image searching module is used for searching an image set matched with the first face image from a face database according to the face pre-screening request and storing the image set into the face pre-screening database; the identification request receiving module is used for receiving a face identification request, and the face identification request comprises a second face image; and the face recognition matching module is used for searching the face image matched with the second face image from the face prescreening database according to the face recognition request and taking the user information of the searched face image as a face recognition result.
Optionally, the pre-screening image lookup module is further configured to: performing feature extraction on the first face image to obtain a first feature; respectively carrying out similarity comparison on the features of each facial image in a facial database and the first features to obtain an image set matched with the first facial image, wherein the image set is a facial image corresponding to the features of which the similarity meets a first threshold value; the face recognition matching module is further configured to: extracting the features of the second face image to obtain second features; and respectively carrying out similarity comparison on the features of each face image in the face prescreening database and the second features to obtain a face image matched with the second face image, wherein the face image matched with the second face image is a face image corresponding to the feature with the highest similarity in the features with the similarity meeting a second threshold, and the second threshold is greater than the first threshold.
Optionally, a living body detection module is further included for: and before receiving a face recognition request, determining that the object corresponding to the second face image is a living body.
Optionally, the first face image is obtained by acquiring a video, extracting an image from the video, and then performing quality screening and face tracking processing on the extracted image.
Optionally, the extracted image is quality screened by not less than one of the following indicators: image definition, human face shielding rate and human face deflection angle.
Optionally, the face prescreening database includes a database of a plurality of levels.
According to another aspect of the embodiment of the invention, an electronic device for face recognition is provided.
An electronic device for face recognition, comprising: one or more processors; the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the face recognition method provided by the embodiment of the invention.
According to yet another aspect of embodiments of the present invention, a computer-readable medium is provided.
A computer-readable medium, on which a computer program is stored, which when executed by a processor implements the method of face recognition provided by an embodiment of the present invention.
One embodiment of the above invention has the following advantages or benefits: when a face pre-screening request is received, an image set matched with the face pre-screening request is searched from a full face database according to a first face image included in the face pre-screening request and stored in the face pre-screening database, then when a face recognition request is received, a face image matched with the face pre-screening request is searched from the face pre-screening database according to a second face image included in the face pre-screening request, and user information of the searched face image is used as a face recognition result, so that the speed and the efficiency of face recognition can be improved by pre-screening the face database, a user can accurately recognize the face without other additional means when the user recognizes the face, the safety verification requirement in a large passenger flow field scene is met, and the speed and the accuracy of the face recognition are greatly improved.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of the main steps of a face recognition method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of face recognition according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of the main modules of an apparatus for face recognition according to an embodiment of the present invention;
FIG. 4 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 5 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Taking a scene that a person passes through on a gate additionally provided with face recognition as an example, when the person walks to the gate, the person is directly opposite to a portrait photographing device additionally arranged on the gate, after the face of the person is photographed by the photographing device, the face image is transmitted to an information processing system, the face image is compared with a face image of the person who has entered the face and has the passing authority of the gate one by one, until one item meeting a threshold value is found, the person is indicated to be the person who is successfully matched correspondingly, and the gate is opened and passes through. When the scale of the face input is increased, the face recognition speed is gradually reduced, and the passing speed is influenced.
In order to solve the technical problem, the value of the total number N of face pictures in the face database needs to be reduced as much as possible, so as to reduce the face database matched with face recognition. Therefore, the invention provides a method for screening face images in advance, wherein a face snapshot camera is installed on a channel before a user enters a gate, the camera collects the face of the user before the user prepares to enter the gate, 1. Therefore, on the premise of not reducing the face recognition accuracy, the invention does not need the user to manually input or draw out the certificate to assist in confirming the identity of the user, and greatly improves the passing efficiency of face recognition.
Fig. 1 is a schematic diagram of main steps of a face recognition method according to an embodiment of the present invention. As shown in fig. 1, the method for face recognition according to the embodiment of the present invention mainly includes the following steps S101 to S104.
Step S101: receiving a face pre-screening request, wherein the face pre-screening request comprises a first face image;
step S102: searching an image set matched with the first face image from a face database according to the face pre-screening request, and storing the image set into the face pre-screening database;
step S103: receiving a face recognition request, wherein the face recognition request comprises a second face image;
step S104: and searching a face image matched with the second face image from the face pre-screening database according to the face identification request, and taking the user information of the searched face image as a face identification result.
According to the technical scheme of the invention, the face is pre-screened before the final face recognition is carried out, a temporary face pre-screening database is generated, and then the face images are recognized and matched from the temporary face pre-screening database when the face recognition is needed, so that the face images to be recognized and matched can be reduced, and the face recognition efficiency is higher.
In an embodiment of the present invention, the first face image in step S101 may be obtained by capturing a video, extracting an image from the video, and performing quality screening and face tracking processing on the extracted image. Similarly, the first face image may also be obtained by directly taking a picture through a camera, and performing quality screening and face tracking processing on the taken picture. According to an embodiment of the present invention, the extracted image may be quality-screened by not less than one of the following indexes: image definition, human face shielding rate and human face deflection angle.
Because the first face image is generally captured, there may be a problem that the angle, the definition, the integrity (for example, wearing a mask or a hat) and the like are not good enough, when the first face image is searched from the face database, a plurality of images matched with the first face image may be found, and an image set is formed.
According to an embodiment of the present invention, when searching an image set matching with the first face image from the face database according to the face prescreening request, step S102 may be specifically executed according to the following steps:
performing feature extraction on the first face image to obtain a first feature;
similarity comparison is carried out on the features of each face image in the face database and the first features respectively to obtain an image set matched with the first face image, wherein the image set is the face image corresponding to the features of which the similarity meets a first threshold value.
Specifically, when performing feature extraction on the first face image to obtain the first feature, a common algorithm may be used, for example: algorithms such as HOG (histogram of Oriented Gradient), SIFT (Scale-invariant Features transform), SURF (Speeded Up Robust Features, improvement on SIFT), DOG (Difference of Gaussian), LBP (Local Binary Pattern), and so on. After feature extraction, a common similarity calculation method may be used in calculating the feature similarity, for example: similarity calculation based on euclidean distance or hamming distance, cosine similarity calculation, and the like. The invention is not limited in this regard.
When the face is pre-screened, the similarity is compared by respectively calculating the similarity of the first feature and the feature of each face image in the face database, and then the similarity is determined by comparing the similarity of the features with a preset first threshold value. Here, since the first face image is captured, there are reasons of sharpness, photographing angle, and the like, the set first threshold value may not be particularly high, and for example, the first threshold value may be set to have a feature similarity greater than 0.7. After the similarity threshold is set, the number of images in the image set with which the first face image is matched may be set, for example: and limiting the number of the images to be 10, and after the images corresponding to the features with the feature similarity reaching 0.7 are all obtained, sorting the images from large to small according to the feature similarity, and taking the first 10 images with the maximum feature similarity to form the image set matched with the first face image.
Similarly, according to the embodiment of the present invention, when the face image matching the second face image is searched from the face prescreening database according to the face recognition request, step S104 may be specifically performed according to the following steps:
extracting the features of the second face image to obtain second features;
and respectively carrying out similarity comparison on the features of each face image in the face pre-screening database and the second features to obtain a face image matched with the second face image, wherein the face image matched with the second face image is a face image corresponding to the feature with the highest similarity in the features with the similarity meeting a second threshold, and the second threshold is greater than the first threshold.
When a user needs to perform face recognition before arriving at the gate and passes the face recognition, the photographing device installed on the gate can acquire a front image of the face, namely: and the second face image is sent to the server side to request face recognition and verification. Generally, the second face image will have a higher quality than the first face image, such as: definition, integrity, angle and the like can be better, and accurate identification is more convenient.
After receiving the face recognition request, the server side firstly extracts the features of the second face image, and then calculates the feature similarity of the extracted second features and the features of each face image in the face prescreening database established in the prescreening process so as to compare the similarity. The data volume of the face image in the face pre-screening database is far less than that of the full face database, so that the face identification matching can be carried out more quickly.
When the similarity of each face image in the second feature and face pre-screening database is compared, in order to accurately compare and acquire the user information corresponding to the second face image, the set second threshold is greater than the first threshold, for example, the feature similarity is greater than 0.9, so as to ensure that the obtained face image matched with the second face image is the face image of the user. And if a plurality of face images meeting the threshold requirement exist, the face image corresponding to the feature with the highest feature similarity is taken as the face image matched with the second face image. If the face image meeting the threshold requirement does not exist, the user is possibly an unregistered user, or the face image of the user does not exist in the face database, and the user can be reminded to register so as to be verified through face recognition next time.
According to the technical scheme of the embodiment of the invention, before receiving the face recognition request, it is further required to determine in advance that the object corresponding to the second face image is a living body, that is: and performing living body detection on the object corresponding to the second face image. The living body detection is a method for determining the real physiological characteristics of an object in some identity verification scenes, and in the application of face recognition, the living body detection can verify whether a user operates for the real living body by combining actions of blinking, mouth opening, head shaking, head nodding and the like and using technologies such as face key point positioning, face tracking and the like. Common attack means such as images, face changing, masks, sheltering, screen copying and the like can be effectively resisted, so that a user is helped to discriminate fraudulent behaviors, and the benefit of the user is guaranteed.
The face prescreening database of the present invention may include a plurality of levels of databases. For example: the face pre-screening database is classified according to the region range, and the classification can be divided into: a face prescreening database corresponding to a country, a face prescreening database corresponding to a city, a face prescreening database corresponding to a face recognition site, and the like. When the face recognition is carried out, the face recognition matching can be carried out from the face prescreening database corresponding to the face recognition site, if the face recognition matching fails to be recognized or matched, the face recognition matching is carried out from the face prescreening database corresponding to the city, and the like. Similarly, the full face database can be divided into multiple levels, and when face prescreening is performed, the face prescreening can be performed from a small-range face database to a large-range face database step by step. And after the system runs for a period of time, a frequent visitor database can be established, and a user who often performs face recognition operation from the face recognition site is used as a frequent visitor to perform face recognition more quickly and conveniently.
And if the face images matched with the second face images cannot be found in all the face pre-screening databases, the second face images can be identified and matched in the whole face databases, and if the matched face images cannot be found, the user is possibly not subjected to face registration, and the user can be prompted to perform face registration so as to facilitate next face identification.
Fig. 2 is a schematic flow chart of face recognition according to an embodiment of the present invention. According to the technical scheme of the invention, the flow of face recognition can be mainly divided into two parts, namely a pre-screening flow and a recognition flow. Generally, a user has a channel before passing through a gate, a first face image of the user can be acquired by installing an image acquisition device such as a camera in the channel and the like, and the first face image is used for prescreening the face image and establishing a face prescreening database; when a user arrives at the gate to perform face recognition, a second clear face image is acquired through a face image acquisition device installed on the gate, and face matching is performed from a face pre-screening database to obtain accurate user information.
As shown in fig. 2, when a user enters a shooting area of a camera in a station channel, the shooting camera captures a face image and sends the face image to a back-end face recognition system through a network, the face image is pre-screened, and the pre-screened face image is stored in a face pre-screening database. The pre-screening process mainly comprises the following steps:
1) Capturing video streams
A site channel camera captures a live video stream in real time and pushes the live video stream to a server of a site machine room in real time through a local area network in a site to analyze the video stream;
2) Obtaining a first face image
The server analyzes the video stream sent by the camera frame by frame through the video stream analysis module, extracts effective face images, and performs quality screening and face tracking on the face images to obtain first face images meeting conditions (for example, the quality score meets a preset threshold). A pre-screening front-end module of the server monitors a video stream analysis module in real time to obtain a first face image;
3) Requesting security authentication
After the pre-screening front-end module acquires a first face image, sending a face pre-screening request to a gateway of a face service module according to an appointed message interface, and after receiving the request, carrying out security verification on the legality of the request message by the gateway;
4) Request route distribution
After the security gateway completes the transaction message verification, the transaction message is routed to the face service module according to a routing distribution strategy, for example, the routing distribution strategy is that the transaction message is sequentially and evenly distributed to a plurality of face service modules according to the sequence of received messages, wherein the face service modules can also be realized by an independent server;
5) Face prescreening search
After the face service module acquires the pre-screening request message, distributing a corresponding face pre-screening request route to different face pre-screening search modules according to service policy configuration, specifically, distributing the face pre-screening request route according to the size of a Graphics Processing Unit (GPU) of each face pre-screening search module;
6) Updating website face prescreening database information
If the GPU of the face prescreening search module is matched with similar people, relevant information of the matched people is updated to a face prescreening database corresponding to the site, wherein the relevant information can comprise user names, sexes, identity card numbers, mobile phone numbers, face images, feature matrixes and feature IDs of the face images and the like.
When a user arrives at a face recognition device (such as a gate), a face photographing device arranged on the face recognition device acquires a clear face image, sends the face image to a face recognition system through a network, performs face recognition in a multi-level face library according to a comparison strategy, inquires corresponding user information according to a characteristic ID after successful recognition, and returns the user information to the face recognition device at the front end. The identification process mainly comprises the following steps:
1) Uploading a second face picture
A PAD (human face photographing device) on a gate (human face recognition device) captures a second human face image of a passing gate user, and uploads the captured second human face image to a human face recognition system after the user passes through living body detection;
2) Request security verification and route distribution
After receiving the face recognition request, a gateway of the face recognition system carries out security verification on the legality of the request message and distributes a strategy route to a corresponding face service module according to the route;
3) Face image search
After the face service module acquires a message of a face recognition request, distributing a corresponding face recognition request route to different face image searching modules according to service policy configuration, specifically, distributing according to the size of a GPU of each face image searching module;
4) Face image database multi-level comparison
And the face image searching module acquires a face image matched with the second face image from the pre-screening face database through the GPU so as to complete face recognition and return a recognition result. The pre-screening face database can be multi-level;
5) Obtaining user information
Obtaining corresponding user information according to the identification result
6) Returning PAD recognition result
Returning the recognition result to a display module PAD deployed on the face recognition device;
7) Passing through the brake
If the identification is successful, the gate machine opens the door and gives permission; otherwise, the passage is refused.
Fig. 3 is a schematic diagram of main modules of an apparatus for face recognition according to an embodiment of the present invention. As shown in fig. 3, the apparatus 300 for face recognition according to the embodiment of the present invention mainly includes a prescreening request receiving module 301, a prescreening image searching module 302, a recognition request receiving module 303, and a face recognition matching module 304.
A pre-screening request receiving module 301, configured to receive a face pre-screening request, where the face pre-screening request includes a first face image;
a prescreening image searching module 302, configured to search an image set matching the first face image from a face database according to the face prescreening request, and store the image set in a face prescreening database;
an identification request receiving module 303, configured to receive a face identification request, where the face identification request includes a second face image;
a face recognition matching module 304, configured to search, according to the face recognition request, a face image matching the second face image from the face prescreening database, and use user information of the searched face image as a face recognition result.
According to an embodiment of the present invention, the pre-screen image lookup module 302 may be further configured to:
performing feature extraction on the first face image to obtain a first feature;
respectively carrying out similarity comparison on the features of each facial image in a facial database and the first features to obtain an image set matched with the first facial image, wherein the image set is a facial image corresponding to the features of which the similarity meets a first threshold value;
the face recognition matching module 304 may also be configured to:
extracting the features of the second face image to obtain second features;
and respectively carrying out similarity comparison on the features of each face image in the face prescreening database and the second features to obtain a face image matched with the second face image, wherein the face image matched with the second face image is a face image corresponding to the feature with the highest similarity in the features with the similarity meeting a second threshold, and the second threshold is greater than the first threshold.
According to another embodiment of the present invention, the apparatus 300 for face recognition may further include a living body detection module (not shown in the figure) for:
and before receiving a face recognition request, determining that the object corresponding to the second face image is a living body.
According to another embodiment of the invention, the first face image is obtained by acquiring a video, extracting an image from the video, and then performing quality screening and face tracking processing on the extracted image.
According to still another embodiment of the present invention, the extracted image is quality-screened by not less than one of the following indexes: image definition, human face shielding rate and human face deflection angle.
According to one embodiment of the invention, the face prescreening database includes a plurality of levels of databases.
According to the technical scheme of the embodiment of the invention, when a face pre-screening request is received, the image set matched with the first face image is searched from the full face database according to the first face image contained in the face pre-screening request and stored in the face pre-screening database, then when the face identification request is received, the face image matched with the second face image is searched from the face pre-screening database according to the second face image contained in the face pre-screening request, and the user information of the searched face image is used as the face identification result, so that the speed and the efficiency of face identification can be improved by pre-screening the face database.
Fig. 4 shows an exemplary system architecture 400 of a face recognition method or a face recognition apparatus to which an embodiment of the present invention may be applied.
As shown in fig. 4, the system architecture 400 may include terminal devices 401, 402, 403, a network 404, and a server 405. The network 404 serves as a medium for providing communication links between the terminal devices 401, 402, 403 and the server 405. Network 404 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.
A user may use terminal devices 401, 402, 403 to interact with a server 405 via a network 404 to receive or send messages or the like. The end devices 401, 402, 403 may have various communication client applications installed thereon, such as shopping applications, web browser applications, search applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 401, 402, 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 405 may be a server providing various services, such as a background management server (for example only) providing support for shopping websites browsed by users using the terminal devices 401, 402, 403. The backend management server may analyze and process the received data such as the product information query request, and feed back a processing result (for example, target push information and product information — just an example) to the terminal device.
It should be noted that the method for face recognition provided by the embodiment of the present invention is generally executed by the server 405, and accordingly, a device for face recognition is generally disposed in the server 405.
It should be understood that the number of terminal devices, networks, and servers in fig. 4 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 5, shown is a block diagram of a computer system 500 suitable for use with a terminal device or server implementing embodiments of the present invention. The terminal device or the server shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU) 501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted on the storage section 508 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 501.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units or modules described in the embodiments of the present invention may be implemented by software or hardware. The described units or modules may also be provided in a processor, and may be described as: a processor comprises a pre-screening request receiving module, a pre-screening image searching module, an identification request receiving module and a face identification matching module. Where the names of such units or modules do not in some cases constitute a limitation on the unit or module itself, for example, the prescreening request receiving module may also be described as a "module for receiving a face prescreening request.
As another aspect, the present invention also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be separate and not assembled into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: receiving a face pre-screening request, wherein the face pre-screening request comprises a first face image; searching an image set matched with the first face image from a face database according to the face pre-screening request, and storing the image set into a face pre-screening database; receiving a face recognition request, wherein the face recognition request comprises a second face image; and searching the face image matched with the second face image from the face prescreening database according to the face identification request, and taking the user information of the searched face image as a face identification result.
According to the technical scheme of the embodiment of the invention, when a face pre-screening request is received, an image set matched with the first face image is searched from a full face database according to the first face image contained in the face pre-screening request and stored in the face pre-screening database, then when a face recognition request is received, a face image matched with the second face image is searched from the face pre-screening database according to the second face image contained in the face pre-screening request, and user information of the searched face image is used as a face recognition result, so that the speed and the efficiency of face recognition can be improved by pre-screening the face database, a user can accurately recognize the face without other additional means when the face recognition is carried out, the safety verification requirement in a large passenger flow field scene is met, and the speed and the accuracy of the face recognition are greatly improved.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (14)
1. A method of face recognition, comprising:
receiving a face pre-screening request, wherein the face pre-screening request comprises a first face image;
searching an image set matched with the first face image from a face database according to the face pre-screening request, and storing the image set into a face pre-screening database;
receiving a face recognition request, wherein the face recognition request comprises a second face image, the first face image and the second face image are different face images of the same user, and the quality of the second face image is higher than that of the first face image;
searching a face image matched with the second face image from the face pre-screening database according to the face recognition request, and taking the user information of the searched face image as a face recognition result;
searching the face image matched with the second face image from the face pre-screening database according to the face recognition request comprises: extracting the features of the second face image to obtain second features; and respectively carrying out similarity comparison on the features of each face image in the face prescreening database and the second features to obtain a face image matched with the second face image, wherein the face image matched with the second face image is a face image corresponding to the feature with the highest similarity in the features with the similarity meeting a second threshold value.
2. The method of claim 1, wherein searching a face database for a set of images matching the first face image based on the face prescreening request comprises:
performing feature extraction on the first face image to obtain a first feature;
respectively carrying out similarity comparison on the features of each face image in a face database and the first features to obtain an image set matched with the first face image, wherein the image set is a face image corresponding to the features of which the similarity meets a first threshold value;
wherein the second threshold is greater than the first threshold.
3. The method of claim 1, wherein prior to receiving the face recognition request, further comprising:
and determining that the object corresponding to the second face image is a living body.
4. The method according to claim 1, wherein the first face image is obtained by acquiring a video, extracting an image from the video, and performing quality screening and face tracking processing on the extracted image.
5. The method of claim 4, wherein the extracted image is quality screened by not less than one of the following: image definition, human face shielding rate and human face deflection angle.
6. The method of claim 1, wherein the face prescreening database comprises a database of multiple levels.
7. An apparatus for face recognition, comprising:
the system comprises a pre-screening request receiving module, a pre-screening request receiving module and a pre-screening request sending module, wherein the pre-screening request receiving module is used for receiving a face pre-screening request which comprises a first face image;
the pre-screening image searching module is used for searching an image set matched with the first face image from a face database according to the face pre-screening request and storing the image set into the face pre-screening database;
the system comprises an identification request receiving module, a face identification processing module and a face identification processing module, wherein the identification request receiving module is used for receiving a face identification request, the face identification request comprises a second face image, the first face image and the second face image are different face images of the same user, and the quality of the second face image is higher than that of the first face image;
the face recognition matching module is used for searching a face image matched with the second face image from the face pre-screening database according to the face recognition request and taking the user information of the searched face image as a face recognition result;
the face recognition matching module is further used for: extracting the features of the second face image to obtain second features; and respectively carrying out similarity comparison on the features of each face image in the face prescreening database and the second features to obtain a face image matched with the second face image, wherein the face image matched with the second face image is a face image corresponding to the feature with the highest similarity in the features with the similarity meeting a second threshold value.
8. The apparatus of claim 7,
the pre-screening image lookup module is further configured to:
performing feature extraction on the first face image to obtain a first feature;
respectively carrying out similarity comparison on the features of each face image in a face database and the first features to obtain an image set matched with the first face image, wherein the image set is a face image corresponding to the features of which the similarity meets a first threshold value;
wherein the second threshold is greater than the first threshold.
9. The apparatus of claim 7, further comprising a liveness detection module to: and before receiving a face recognition request, determining that the object corresponding to the second face image is a living body.
10. The apparatus of claim 7, wherein the first face image is obtained by capturing a video, extracting an image from the video, and performing quality screening and face tracking processing on the extracted image.
11. The apparatus of claim 10, wherein the extracted image is quality screened by not less than one of: image definition, human face shielding rate and human face deflection angle.
12. The apparatus of claim 7, wherein the face prescreening database comprises a database of a plurality of levels.
13. An electronic device for face recognition, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.
14. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911012966.6A CN110825765B (en) | 2019-10-23 | 2019-10-23 | Face recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911012966.6A CN110825765B (en) | 2019-10-23 | 2019-10-23 | Face recognition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110825765A CN110825765A (en) | 2020-02-21 |
| CN110825765B true CN110825765B (en) | 2022-10-04 |
Family
ID=69550271
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911012966.6A Active CN110825765B (en) | 2019-10-23 | 2019-10-23 | Face recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110825765B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310580A (en) * | 2020-01-19 | 2020-06-19 | 四川联众竞达科技有限公司 | Face recognition method under non-matching state |
| CN111724497A (en) * | 2020-06-30 | 2020-09-29 | 重庆勤鸟圈科技有限公司 | Shower control system for gymnasium |
| CN111914649A (en) * | 2020-07-01 | 2020-11-10 | 珠海大横琴科技发展有限公司 | Face recognition method and device, electronic equipment and storage medium |
| CN112052728B (en) * | 2020-07-30 | 2024-04-02 | 广州市标准化研究院 | Portable portrait identification anti-deception device and control method thereof |
| CN112101254B (en) * | 2020-09-21 | 2024-06-14 | 深圳喜为智慧科技有限公司 | Method and system for improving image recognition precision and speed |
| 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 |
| CN112115910A (en) * | 2020-09-28 | 2020-12-22 | 中国银行股份有限公司 | Face library updating method and device |
| CN112488016A (en) * | 2020-12-09 | 2021-03-12 | 重庆邮电大学 | Multi-angle face recognition method and application |
| CN112288939A (en) * | 2020-12-15 | 2021-01-29 | 成都智元汇信息技术股份有限公司 | Gate face recognition method, system, terminal and storage medium based on face pre-acquisition |
| CN112597867B (en) * | 2020-12-17 | 2024-04-26 | 佛山科学技术学院 | Face recognition method and system for wearing mask, computer equipment and storage medium |
| CN112667840B (en) * | 2020-12-22 | 2024-05-28 | 中国银联股份有限公司 | Feature sample library construction method, traffic identification method, device and storage medium |
| CN113378738A (en) * | 2021-06-18 | 2021-09-10 | 北京市商汤科技开发有限公司 | Comparison method and device, equipment and storage medium |
| CN113792672B (en) * | 2021-09-16 | 2024-05-28 | 平安科技（深圳）有限公司 | Public place health code acquisition method, device, equipment and medium |
| CN115116174A (en) * | 2022-06-29 | 2022-09-27 | 中铁第四勘察设计院集团有限公司 | System and method for automatically acquiring pass health code based on user authorization information |
| CN115880745B (en) * | 2022-09-07 | 2023-07-04 | 以萨技术股份有限公司 | Data processing system for acquiring facial image characteristics |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102622581A (en) * | 2012-02-20 | 2012-08-01 | 华焦宝 | Face detection method and face detection system |
| CN105279496A (en) * | 2015-10-26 | 2016-01-27 | 浙江宇视科技有限公司 | Human face recognition method and apparatus |
| CN108256459A (en) * | 2018-01-10 | 2018-07-06 | 北京博睿视科技有限责任公司 | Library algorithm is built in detector gate recognition of face and face based on multiple-camera fusion automatically |
| CN108509846A (en) * | 2018-02-09 | 2018-09-07 | 腾讯科技（深圳）有限公司 | Image processing method, device, computer equipment and storage medium |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4321645B2 (en) * | 2006-12-08 | 2009-08-26 | ソニー株式会社 | Information processing apparatus, information processing method, recognition apparatus, information recognition method, and program |
| KR101170014B1 (en) * | 2010-03-25 | 2012-08-01 | 주식회사 시큐텍 | Ubiquitos monitoring system and method using face recognition dvr |
| EP2490151A1 (en) * | 2011-02-17 | 2012-08-22 | Nagravision S.A. | Method and device to speed up face recognition |
| CN106997447A (en) * | 2016-01-22 | 2017-08-01 | 鸿富锦精密工业（深圳）有限公司 | Face identification system and face identification method |
| US10083347B2 (en) * | 2016-07-29 | 2018-09-25 | NTech lab LLC | Face identification using artificial neural network |
| US9904844B1 (en) * | 2016-08-04 | 2018-02-27 | International Business Machines Corporation | Clustering large database of images using multilevel clustering approach for optimized face recognition process |
| CN107609508A (en) * | 2017-09-08 | 2018-01-19 | 深圳市金立通信设备有限公司 | A kind of face identification method, terminal and computer-readable recording medium |
| CN108280422B (en) * | 2018-01-22 | 2022-06-14 | 百度在线网络技术（北京）有限公司 | Method and device for recognizing human face |
| CN108920639B (en) * | 2018-07-02 | 2022-01-18 | 北京百度网讯科技有限公司 | Context obtaining method and device based on voice interaction |
| CN109117808B (en) * | 2018-08-24 | 2020-11-03 | 深圳前海达闼云端智能科技有限公司 | Face recognition method and device, electronic equipment and computer readable medium |
| CN109376614A (en) * | 2018-09-29 | 2019-02-22 | 爱笔（北京）智能科技有限公司 | A kind of service providing method and device based on face |
| CN109492538A (en) * | 2018-10-17 | 2019-03-19 | 广州云从信息科技有限公司 | Intelligent boarding system, method and readable storage medium storing program for executing based on face recognition technology |
| CN109977765A (en) * | 2019-02-13 | 2019-07-05 | 平安科技（深圳）有限公司 | Facial image recognition method, device and computer equipment |
| CN109993102B (en) * | 2019-03-28 | 2021-09-17 | 北京达佳互联信息技术有限公司 | Similar face retrieval method, device and storage medium |
-
2019
- 2019-10-23 CN CN201911012966.6A patent/CN110825765B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102622581A (en) * | 2012-02-20 | 2012-08-01 | 华焦宝 | Face detection method and face detection system |
| CN105279496A (en) * | 2015-10-26 | 2016-01-27 | 浙江宇视科技有限公司 | Human face recognition method and apparatus |
| CN108256459A (en) * | 2018-01-10 | 2018-07-06 | 北京博睿视科技有限责任公司 | Library algorithm is built in detector gate recognition of face and face based on multiple-camera fusion automatically |
| CN108509846A (en) * | 2018-02-09 | 2018-09-07 | 腾讯科技（深圳）有限公司 | Image processing method, device, computer equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| A facial sparse descriptor for single image based face recognition;Liu N 等;《Neurocomputing》;20120915;77-87 * |
| Face recognition using variance weightiness LBP based on single training image per person;R. Zhao 等;《2011 International Conference on Wavelet Analysis and Pattern Recognition》;20110908;7-11 * |
| 轻量级智能终端人脸识别系统研究与实现;马国峻 等;《通信学报》;20151125;第36卷(第Z1期);149-156 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110825765A (en) | 2020-02-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110825765B (en) | Face recognition method and device | |
| US11908238B2 (en) | Methods and systems for facial point-of-recognition (POR) provisioning | |
| KR101629224B1 (en) | Authentication method, device and system based on biological characteristics | |
| CN111886842B (en) | Remote user authentication using threshold-based matching | |
| CN110852193A (en) | Face recognition method and device | |
| CN107169458B (en) | Data processing method, device and storage medium | |
| TW202026948A (en) | Methods and devices for biological testing and storage medium thereof | |
| CN106303599B (en) | Information processing method, system and server | |
| CN111144366A (en) | Strange face clustering method based on joint face quality assessment | |
| CN108108711B (en) | Face control method, electronic device and storage medium | |
| CN110245573B (en) | Sign-in method and device based on face recognition and terminal equipment | |
| CN110647823A (en) | Method and device for optimizing human face base | |
| TWI789128B (en) | Face recognition method, device, equipment and storage medium | |
| CN111626371A (en) | Image classification method, device and equipment and readable storage medium | |
| CN108280422B (en) | Method and device for recognizing human face | |
| CN104751041A (en) | Authentication method, system and mobile terminal | |
| KR102297217B1 (en) | Method and apparatus for identifying object and object location equality between images | |
| CN110889314B (en) | Image processing method, device, electronic equipment, server and system | |
| WO2019196626A1 (en) | Media processing method and related apparatus | |
| CN111553327B (en) | Clothing identification method, device, equipment and medium | |
| CN111985360A (en) | Face recognition method, device, equipment and medium | |
| CN110929244A (en) | Digital identity identification method, device, equipment and storage medium | |
| CN111126159A (en) | Method, apparatus, electronic device, and medium for tracking pedestrian in real time | |
| CN108683901B (en) | Data processing method, MEC server and computer readable storage medium | |
| CN111126229A (en) | Data processing method and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220921 Address after: 25 Financial Street, Xicheng District, Beijing 100033 Applicant after: CHINA CONSTRUCTION BANK Corp. Address before: 25 Financial Street, Xicheng District, Beijing 100033 Applicant before: CHINA CONSTRUCTION BANK Corp. Applicant before: Jianxin Financial Science and Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right |