CN110647823A - Method and device for optimizing human face base - Google Patents
Method and device for optimizing human face base Download PDFInfo
- Publication number
- CN110647823A CN110647823A CN201910822620.6A CN201910822620A CN110647823A CN 110647823 A CN110647823 A CN 110647823A CN 201910822620 A CN201910822620 A CN 201910822620A CN 110647823 A CN110647823 A CN 110647823A
- Authority
- CN
- China
- Prior art keywords
- face
- face image
- image
- user
- identity
- 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
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
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a method and a device for optimizing a human face base library, and relates to the technical field of computers. One embodiment of the method comprises: collecting a plurality of face images of a user, respectively calculating the quality score of each face image, and screening out one face image as an identity checking face image; carrying out identity verification on the identity verification face image and the identity face image of the user in the identity verification system; and if the identity verification is passed, taking the identity verification face image as a registered face image of the user in a face bottom library. The implementation method can solve the technical problems of high error recognition rate and low response speed.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for optimizing a human face base.
Background
The face recognition application has penetrated the square of our life, and each city gradually releases 'one face to go', particularly releases face brushing for outgoing in the outgoing fields of various subways, buses and the like, and under the background, the face recognition mainly depends on comparison of on-site snapshot and reserved basement comparison. But the reserved base photo may not be the best initially, and the quality of the base photo directly influences the subsequent recognition rate and the false recognition rate. At present, rail transit such as each city subway, public transit, trolley-bus is all pushing out and is brushed the face current, and the public transit field is brushed face trip and is required that the discernment speed is fast, the misconception rate is low to prevent to appear blocking up and take the lane, put forward higher requirement to face discernment. In such a high-frequency face brushing scene, the quality of the face recognition base directly affects the recognition speed and the false recognition.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:
the existing method for improving the base library by face recognition is to register a plurality of base library photos, identify one person in different angles of the photos as much as possible, and improve the face recognition passing rate by using the method of the plurality of base library photos for the same person. Moreover, because the comprehensive quality of the photos in the base stock, the photographing time and other factors are not controlled, the false recognition rate is increased to a certain extent, particularly, the registration link is not strictly controlled, the photos closest to the certificate photo can not be screened out in the subsequent optimization updating process, and even if a plurality of base stock photos are registered, the comprehensive quality of the photos is common. If in a payment scene (especially a scene of a subway with high frequency and high traffic speed), the scheme not only increases the false recognition rate, but also increases the search time, so that the response speed is slow, and the requirement of quick and accurate subway traffic cannot be met.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for optimizing a face base library, so as to solve the technical problems of high false recognition rate and low response speed.
To achieve the above object, according to an aspect of the embodiments of the present invention, there is provided a method for optimizing a face base, including:
collecting a plurality of face images of a user, respectively calculating the quality score of each face image, and screening out one face image as an identity checking face image;
carrying out identity verification on the identity verification face image and the identity face image of the user in the identity verification system;
and if the identity verification is passed, taking the identity verification face image as a registered face image of the user in a face bottom library.
Optionally, before acquiring a plurality of facial images of the user, the method further includes:
acquiring identity information and a face video of a user;
and performing living body detection on the user according to the face video.
Optionally, the step of respectively calculating a quality score of each face image, and screening out one face image from the quality scores as an identity verification face image includes:
respectively calculating the quality score of each face image according to the image characteristics and the weight corresponding to each image characteristic;
screening a face image with the highest quality score from the plurality of face images, and judging whether the quality score of the screened face image is greater than or equal to a preset score threshold value or not; if so, taking the screened face image as an identity checking face image;
wherein the image features include at least two of: face integrity, face definition, face resolution, face brightness, face angle, and face expression.
Optionally, after the identity verification face image is used as a registered face image of the user in a face base library, the method further includes:
and storing the identity information of the user, the registered face image, and the face key point, the registration time and the quality score of the registered face image in a face bottom library.
Optionally, after storing the identity information of the user, the registered face image, and the face key point, the registration time, and the quality score of the registered face image in a face base, the method further includes:
acquiring a face image to be verified of the user, and calculating the quality score of the face image to be verified;
and if the difference value between the acquisition time of the face image to be verified and the registration time of the registered face image is greater than or equal to a preset time threshold value, and the difference value between the quality score of the face image to be verified and the quality score of the registered face image is smaller than a preset difference threshold value, taking the face image to be verified as the registered face image of the user.
In addition, according to another aspect of the embodiments of the present invention, there is provided an apparatus for optimizing a human face base library, including:
the computing module is used for collecting a plurality of face images of a user, respectively computing the quality score of each face image, and screening out one face image from the face images to serve as an identity checking face image;
the verification module is used for performing identity verification on the identity verification face image and the identity face image of the user in the identity verification system;
and the optimization module is used for taking the identity checking face image as a registered face image of the user in a face bottom library if the identity checking passes.
Optionally, the computing module is further configured to:
before collecting a plurality of face images of a user, collecting identity information and a face video of the user;
and performing living body detection on the user according to the face video.
Optionally, the computing module is further configured to:
respectively calculating the quality score of each face image according to the image characteristics and the weight corresponding to each image characteristic;
screening a face image with the highest quality score from the plurality of face images, and judging whether the quality score of the screened face image is greater than or equal to a preset score threshold value or not; if so, taking the screened face image as an identity checking face image;
wherein the image features include at least two of: face integrity, face definition, face resolution, face brightness, face angle, and face expression.
Optionally, the optimization module is further configured to:
and after the identity verification face image is used as a registered face image of the user in a face base library, storing the identity information of the user, the registered face image, and face key points, registration time and quality scores of the registered face image in the face base library.
Optionally, the optimization module is further configured to:
after the identity information of the user, the registered face image, and the face key points, the registration time and the quality scores of the registered face image are stored in a face base, acquiring a face image to be verified of the user, and calculating the quality score of the face image to be verified;
and if the difference value between the acquisition time of the face image to be verified and the registration time of the registered face image is greater than or equal to a preset time threshold value, and the difference value between the quality score of the face image to be verified and the quality score of the registered face image is smaller than a preset difference threshold value, taking the face image to be verified as the registered face image of the user.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including:
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 of the embodiments described above.
According to another aspect of the embodiments of the present invention, there is also provided a computer readable medium, on which a computer program is stored, which when executed by a processor implements the method of any of the above embodiments.
One embodiment of the above invention has the following advantages or benefits: because the face image with the highest quality score is screened from the plurality of face images and is used as the technical means for registering the face image after the identity verification is passed, the technical problems of high false recognition rate and low response speed in the prior art are solved. The embodiment of the invention calculates the quality score of each facial image through a plurality of dimensional information, screens out the facial image with the highest quality score, and then takes the facial image as the registered facial image after the identity verification is passed, thereby optimizing the facial base. The registered face image obtained by screening in the embodiment of the invention can improve the quality of the photos in the base, and is beneficial to further improving the passing rate of face recognition and reducing the false recognition rate. And only one registered face image is in the bottom library, so that the face brushing speed can be obviously improved, and the method is particularly suitable for traffic travel scenes or payment scenes.
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 a main flow of a method for optimizing a face base according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a main flow of a method of optimizing a face base according to a referential embodiment of the present invention;
FIG. 3 is a schematic diagram of a main flow of a method of optimizing a face base according to another referential embodiment of the present invention;
FIG. 4 is a schematic diagram of the main modules of an apparatus for optimizing a human face base library according to an embodiment of the present invention;
FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 6 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 present 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.
Fig. 1 is a schematic diagram of a main flow of a method for optimizing a face base according to an embodiment of the present invention. As an embodiment of the present invention, as shown in fig. 1, the method for optimizing a face base library may include:
step 101, collecting a plurality of face images of a user, respectively calculating the quality score of each face image, and screening out one face image from the face images as an identity checking face image.
Optionally, before acquiring a plurality of facial images of the user, the method further includes: acquiring identity information and a face video of a user; and performing living body detection on the user according to the face video. The identity information may include a name, a certificate number, an account name, and the like. In the embodiment, a face video of a user is collected firstly, and living body detection is carried out on the face video; if the living body detection is passed, continuously acquiring a plurality of face images of the user; and finally, screening the facial images with the highest quality scores from the facial images to serve as the identity checking facial images. The collected face image can be ensured to be of the user through living body detection.
Optionally, when the face image of the user is collected, it is further necessary to determine whether the target face is sharp according to the pixels and positions of the face, and if the target face is not sharp, the face image is discarded and collected again. Moreover, when the face image of the user is collected, only one face in the collected image needs to be ensured, otherwise, the face image is collected again.
Optionally, a score threshold may be preset, and if the quality scores of all the facial images are less than the score threshold, multiple facial images of the user are collected again until the quality score of one facial image is greater than or equal to the score threshold. Optionally, step 101 may comprise: respectively calculating the quality score of each face image according to the image characteristics and the weight corresponding to each image characteristic; screening a face image with the highest quality score from the plurality of face images, and judging whether the quality score of the screened face image is greater than or equal to a preset score threshold value or not; and if so, taking the screened face image as an identity checking face image. Wherein the image features include at least two of: face integrity, face definition, face resolution, face brightness, face angle, and face expression. That is to say, the quality score of the screened face image is not only the highest, but also greater than or equal to the preset score threshold value, so as to ensure the photo quality of the registered face image.
Alternatively, the following method can be adopted to obtain the image characteristics of each face image:
1) and (4) checking whether a plurality of target faces exist, judging whether the target faces are clear or not according to the pixels and the positions of the faces, and if the target faces are not obvious, snapping again.
2) Based on a human key point alignment algorithm, checking the integrity of a target face, such as whether the edge of the target face completely contains the whole face or not, whether the forehead, eyes, nose, mouth, chin and the like exist on the target face or not, and ensuring that key points are in a face image;
3) checking the definition of the target face through a Laplacian operator to ensure the picture to be clear;
4) checking the resolution of the target face through a pixel ratio to ensure that the target face picture and the interpupillary distance meet preset conditions;
5) the brightness of the target face is checked through the brightness mean square error, and overexposure or over darkness is avoided;
6) checking the angle of the target face through spatial modeling, and ensuring that the up-down angle, the left-right angle and the pitching angle meet the preset quality requirement;
7) the target facial expression is checked through a multi-classification algorithm based on CNN, so that the natural expression is ensured, and the situation that the expression is exaggerated or stiff is avoided;
and (3) allocating corresponding weight values to each item by each item of the check items, adding the items to obtain a quality score, screening out the face image with the maximum quality score, and taking the face image as an identity checking face image for subsequent identity checking when the quality score is greater than or equal to a preset score threshold. When the quality score is calculated, in addition to some judgment of the face image, detection items such as whether multiple targets of faces exist in the image and whether the expression is natural are introduced, interference factors which can cause misidentification are eliminated, high definition of the registered face image which is put in storage for the first time is ensured and is close to the face image in the identification photo, and therefore identification accuracy is improved and misidentification rate is reduced.
It should be noted that, in the embodiment of the present invention, the inspection conditions of the integrated quality inspection and the threshold, weight, etc. of each condition are summarized according to the standard of the certificate photo, and the photo obtained by the standard is the recent photo closest to the certificate photo. The quality score is adopted to comprehensively evaluate the face image, so that the target face is clear and has no conflict, the base warehouse-in image is close to the certificate photo, the subsequent face search is facilitated, and the problems of front and back faces and left and right faces during subway passage are prevented.
And 102, performing identity verification on the identity verification face image and the identity face image of the user in the identity verification system.
After identity verification face images are screened out from a plurality of face images, the identity verification face images are compared with the identity face images of the user in an identity verification system. Optionally, the identity information input by the user can be associated with the identity face image of the user in the identity verification system. In this step, identity verification may be performed through face recognition calculation, specifically, face features in an identity verification face image and an identity verification face image (for example, a face image on an identity card) are respectively extracted, and then similarity between the identity verification face image and the identity verification face image is calculated through the face features, so as to determine whether the identity verification face image is the same person, thereby ensuring that the user is the principal to perform a registration operation. The implementation of the face recognition technology is mainly divided into flows of face positioning, local feature extraction, coding, feature comparison and the like.
And 103, if the identity verification is passed, taking the identity verification face image as a registered face image of the user in a face bottom library.
And if the identity verification is passed, the identity verification face image is consistent with the identity face image in the identity verification system, and the identity verification face image is used as the registered face image of the user in the face bottom library.
Optionally, after step 103, the method further comprises: and storing the identity information of the user, the registered face image, and the face key point, the registration time and the quality score of the registered face image in a face bottom library. The information stored in the face bottom library can be used for subsequent face recognition, image updating and the like. When a user needs to brush faces, such as subway face brushing gate passing, face brushing payment and the like, the face passing rate is required to be high, the error recognition rate is low, the recognition speed is high, and the method does not depend on the non-sensitive passing of any certificate, so that certificate comparison cannot be carried out, the resolution of a photo in a certificate chip is low, the possibility of the long-term passing is low, the identity authentication of security check can be conducted reluctantly, and the method cannot be applied to the non-sensitive passing scene which relates to payment and has high response requirement.
When brushing the face, the embodiment of the invention analyzes and identifies the face image acquired in real time based on the registered face image after passing the verification, thereby not only improving the passing rate and the identification speed and reducing the false identification rate, but also realizing the non-inductive passing without depending on any certificate, and being particularly suitable for the non-inductive passing scene which relates to payment and has high response requirement.
According to the various embodiments, the invention can be seen that the technical problems of high false recognition rate and low response speed in the prior art are solved by screening a facial image with the highest quality score from a plurality of facial images and using the facial image as a technical means for registering the facial image after the identity verification is passed. The embodiment of the invention calculates the quality score of each facial image through a plurality of dimensional information, screens out the facial image with the highest quality score, and then takes the facial image as the registered facial image after the identity verification is passed, thereby optimizing the facial base. The registered face image obtained by screening in the embodiment of the invention can improve the quality of the photos in the base, and is beneficial to further improving the passing rate of face recognition and reducing the false recognition rate. And only one registered face image is in the bottom library, so that the face brushing speed can be obviously improved, and the method is particularly suitable for traffic travel scenes or payment scenes.
Fig. 2 is a schematic diagram of a main flow of a method for optimizing a face base according to a referential embodiment of the invention. The method for optimizing the human face base library comprises the following steps:
step 201, collecting identity information and a face video of a user.
Step 202, performing living body detection on the user according to the face video;
step 203, checking whether the living body detection is passed; if yes, go to step 204; if not, go to step 201
Step 204, collecting a plurality of face images of the user, respectively calculating the quality score of each face image, and screening out a face image with the highest quality score.
Step 205, judging whether the face image with the highest quality score is larger than or equal to a preset score threshold value; if yes, go to step 206; if not, go to step 201.
And step 206, taking the face image with the highest quality score as an identity checking face image, and performing identity checking on the identity checking face image and the identity face image of the user in the identity checking system.
Step 207, judging whether the identity check is passed; if yes, go to step 208; if not, go to step 201.
And step 208, taking the identity verification face image as a registered face image of the user in a face bottom library.
Step 209, storing the identity information of the user, the registered face image, and the face key point, the registration time and the quality score of the registered face image in a face base.
The embodiment of the invention calculates the quality score of each facial image through a plurality of dimensional information, screens out the facial image with the highest quality score, and then takes the facial image as the registered facial image after the identity verification is passed, thereby optimizing the facial base. The registered face image obtained by screening in the embodiment of the invention can improve the quality of the photos in the base, and is beneficial to further improving the passing rate of face recognition and reducing the false recognition rate. And only one registered face image is in the bottom library, so that the face brushing speed can be obviously improved, and the method is particularly suitable for traffic travel scenes or payment scenes.
In addition, in a reference embodiment of the present invention, the detailed implementation content of the method for optimizing the face base library is already described in detail in the above method for optimizing the face base library, so that the repeated content is not described herein.
Fig. 3 is a schematic diagram of a main flow of a method for optimizing a face base according to another referential embodiment of the present invention. After the user completes the registration of the face image according to step 201 and step 209, the user may perform face brushing verification based on the registered face image, and after the verification is passed, the face image in the base library may be further updated. Specifically, the method comprises the following steps:
step 301, collecting a face image to be verified of a user.
Step 302, judging whether the face image to be verified passes the verification based on the registered face image; if yes, go to step 303; if not, the process is ended.
Step 303, calculating the quality score of the face image to be verified.
Step 304, judging that the difference value between the quality score of the facial image to be verified and the quality score of the registered facial image is smaller than a preset difference threshold value; if yes, go to step 305; if not, go to 307.
305, the difference value between the acquisition time of the face image to be checked and the registration time of the registered face image is more than or equal to a preset time threshold; if yes, go to step 306; if not, go to 307.
Step 306, using the face image to be verified as the registered face image of the user.
And 307, taking the face image with high quality score as a registered face image.
In the embodiment, the newly acquired face image to be verified is compared with the registered face image in the bottom library, and if the comparison is passed, the quality score of the face image to be verified is further calculated. The calculation method is similar to step 101 and will not be described again. And then, comprehensive evaluation is carried out based on the quality scores and the acquisition time of the face image to be checked and the registered face image, and whether the face image in the base library needs to be updated or not is judged, so that the base library photo which is put in storage can be ensured to be the latest high-quality close shot of the user.
Therefore, after the face image registration is completed, the embodiment of the invention can further comprehensively judge whether the face image in the base needs to be updated or not by combining the quality score and the acquisition time so as to ensure that the base photo put in storage is the latest high-quality close shot of the user, thereby improving the success rate of search comparison and reducing the false recognition rate.
In addition, in another embodiment of the present invention, the detailed implementation of the method for optimizing a face base library is already described in detail in the above method for optimizing a face base library, and therefore, the repeated content will not be described again.
Fig. 4 is a schematic diagram of main modules of an apparatus for optimizing a human face base library according to an embodiment of the present invention, and as shown in fig. 4, the apparatus 400 for optimizing a human face base library includes a calculation module 401, a checking module 402 and an optimization module 403. The computing module 401 is configured to collect multiple face images of a user, respectively compute a quality score of each face image, and screen out one face image from the quality scores as an identity verification face image; the checking module 402 is configured to perform identity checking on the identity checking face image and the identity face image of the user in the identity checking system; the optimization module 403 is configured to, if the identity verification is passed, use the identity verification face image as a registered face image of the user in a face base library.
Optionally, the calculation module 401 is further configured to:
before collecting a plurality of face images of a user, collecting identity information and a face video of the user;
and performing living body detection on the user according to the face video.
Optionally, the calculation module 401 is further configured to:
respectively calculating the quality score of each face image according to the image characteristics and the weight corresponding to each image characteristic;
screening a face image with the highest quality score from the plurality of face images, and judging whether the quality score of the screened face image is greater than or equal to a preset score threshold value or not; if so, taking the screened face image as an identity checking face image;
wherein the image features include at least two of: face integrity, face definition, face resolution, face brightness, face angle, and face expression.
Optionally, the optimizing module 403 is further configured to:
and after the identity verification face image is used as a registered face image of the user in a face base library, storing the identity information of the user, the registered face image, and face key points, registration time and quality scores of the registered face image in the face base library.
Optionally, the optimizing module 403 is further configured to:
after the identity information of the user, the registered face image, and the face key points, the registration time and the quality scores of the registered face image are stored in a face base, acquiring a face image to be verified of the user, and calculating the quality score of the face image to be verified;
and if the difference value between the acquisition time of the face image to be verified and the registration time of the registered face image is greater than or equal to a preset time threshold value, and the difference value between the quality score of the face image to be verified and the quality score of the registered face image is smaller than a preset difference threshold value, taking the face image to be verified as the registered face image of the user.
According to the various embodiments, the invention can be seen that the technical problems of high false recognition rate and low response speed in the prior art are solved by screening a facial image with the highest quality score from a plurality of facial images and using the facial image as a technical means for registering the facial image after the identity verification is passed. The embodiment of the invention calculates the quality score of each facial image through a plurality of dimensional information, screens out the facial image with the highest quality score, and then takes the facial image as the registered facial image after the identity verification is passed, thereby optimizing the facial base. The registered face image obtained by screening in the embodiment of the invention can improve the quality of the photos in the base, and is beneficial to further improving the passing rate of face recognition and reducing the false recognition rate. And only one registered face image is in the bottom library, so that the face brushing speed can be obviously improved, and the method is particularly suitable for traffic travel scenes or payment scenes.
It should be noted that, in the implementation of the apparatus for optimizing a face base library according to the present invention, the above method for optimizing a face base library has been described in detail, and therefore, the repeated content is not described herein.
Fig. 5 illustrates an exemplary system architecture 500 of a method for optimizing a face base or an apparatus for optimizing a face base to which an embodiment of the present invention may be applied.
As shown in fig. 5, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. The network 504 serves to provide a medium for communication links between the terminal devices 501, 502, 503 and the server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 501, 502, 503 to interact with a server 505 over a network 504 to receive or send messages or the like. The terminal devices 501, 502, 503 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 501, 502, 503 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 505 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 501, 502, 503. The background management server may analyze and otherwise process the received data such as the item information query request, and feed back a processing result (for example, target push information, item information — just an example) to the terminal device.
It should be noted that the method for optimizing the face base library provided by the embodiment of the present invention is generally executed by the server 505, and accordingly, the apparatus for optimizing the face base library is generally disposed in the server 505. The method for optimizing the face base library provided by the embodiment of the invention can also be executed by the terminal equipment 501, 502 and 503, and correspondingly, the device for optimizing the face base library can be arranged in the terminal equipment 501, 502 and 503.
It should be understood that the number of terminal devices, networks, and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 6, a block diagram of a computer system 600 suitable for use with a terminal device implementing an embodiment of the invention is shown. The terminal device shown in fig. 6 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. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 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 article 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 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 601.
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 articles 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 modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes a calculation module, a verification module, and an optimization module, where the names of the modules do not in some cases constitute a limitation on the module itself.
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: collecting a plurality of face images of a user, respectively calculating the quality score of each face image, and screening out one face image as an identity checking face image; carrying out identity verification on the identity verification face image and the identity face image of the user in the identity verification system; and if the identity verification is passed, taking the identity verification face image as a registered face image of the user in a face bottom library.
According to the technical scheme of the embodiment of the invention, because a face image with the highest quality score is screened from a plurality of face images and is used as a technical means for registering the face image after the identity verification is passed, the technical problems of high false recognition rate and low response speed in the prior art are solved. The embodiment of the invention calculates the quality score of each facial image through a plurality of dimensional information, screens out the facial image with the highest quality score, and then takes the facial image as the registered facial image after the identity verification is passed, thereby optimizing the facial base. The registered face image obtained by screening in the embodiment of the invention can improve the quality of the photos in the base, and is beneficial to further improving the passing rate of face recognition and reducing the false recognition rate. And only one registered face image is in the bottom library, so that the face brushing speed can be obviously improved, and the method is particularly suitable for traffic travel scenes or payment scenes.
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 (12)
1. A method for optimizing a face base, comprising:
collecting a plurality of face images of a user, respectively calculating the quality score of each face image, and screening out one face image as an identity checking face image;
carrying out identity verification on the identity verification face image and the identity face image of the user in the identity verification system;
and if the identity verification is passed, taking the identity verification face image as a registered face image of the user in a face bottom library.
2. The method of claim 1, prior to acquiring the plurality of facial images of the user, further comprising:
acquiring identity information and a face video of a user;
and performing living body detection on the user according to the face video.
3. The method of claim 1, wherein the step of calculating the quality score of each face image and screening out one face image from the quality scores as the identity checking face image comprises:
respectively calculating the quality score of each face image according to the image characteristics and the weight corresponding to each image characteristic;
screening a face image with the highest quality score from the plurality of face images, and judging whether the quality score of the screened face image is greater than or equal to a preset score threshold value or not; if so, taking the screened face image as an identity checking face image;
wherein the image features include at least two of: face integrity, face definition, face resolution, face brightness, face angle, and face expression.
4. The method of claim 2, further comprising, after taking the identity verification face image as a registered face image of the user in a face base library:
and storing the identity information of the user, the registered face image, and the face key point, the registration time and the quality score of the registered face image in a face bottom library.
5. The method of claim 4, further comprising, after storing the identity information of the user, the registered face images, and face keypoints, registration times, and quality scores for the registered face images in a face base, further comprising:
acquiring a face image to be checked of a user;
judging whether the face image to be verified passes verification or not based on the registered face image, if so, calculating the quality score of the face image to be verified;
and if the difference value between the acquisition time of the face image to be verified and the registration time of the registered face image is greater than or equal to a preset time threshold value, and the difference value between the quality score of the face image to be verified and the quality score of the registered face image is smaller than a preset difference threshold value, taking the face image to be verified as the registered face image of the user.
6. An apparatus for optimizing a human face base library, comprising:
the computing module is used for collecting a plurality of face images of a user, respectively computing the quality score of each face image, and screening out one face image from the face images to serve as an identity checking face image;
the verification module is used for performing identity verification on the identity verification face image and the identity face image of the user in the identity verification system;
and the optimization module is used for taking the identity checking face image as a registered face image of the user in a face bottom library if the identity checking passes.
7. The apparatus of claim 6, wherein the computing module is further configured to:
before collecting a plurality of face images of a user, collecting identity information and a face video of the user;
and performing living body detection on the user according to the face video.
8. The apparatus of claim 6, wherein the computing module is further configured to:
respectively calculating the quality score of each face image according to the image characteristics and the weight corresponding to each image characteristic;
screening a face image with the highest quality score from the plurality of face images, and judging whether the quality score of the screened face image is greater than or equal to a preset score threshold value or not; if so, taking the screened face image as an identity checking face image;
wherein the image features include at least two of: face integrity, face definition, face resolution, face brightness, face angle, and face expression.
9. The apparatus of claim 8, wherein the optimization module is further configured to:
and after the identity verification face image is used as a registered face image of the user in a face base library, storing the identity information of the user, the registered face image, and face key points, registration time and quality scores of the registered face image in the face base library.
10. The apparatus of claim 9, wherein the optimization module is further configured to:
after the identity information of the user, the registered face image, and the face key points, the registration time and the quality scores of the registered face image are stored in a face base, acquiring a face image to be verified of the user, and calculating the quality score of the face image to be verified;
and if the difference value between the acquisition time of the face image to be verified and the registration time of the registered face image is greater than or equal to a preset time threshold value, and the difference value between the quality score of the face image to be verified and the quality score of the registered face image is smaller than a preset difference threshold value, taking the face image to be verified as the registered face image of the user.
11. An electronic device, 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 1-5.
12. 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 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910822620.6A CN110647823A (en) | 2019-09-02 | 2019-09-02 | Method and device for optimizing human face base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910822620.6A CN110647823A (en) | 2019-09-02 | 2019-09-02 | Method and device for optimizing human face base |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110647823A true CN110647823A (en) | 2020-01-03 |
Family
ID=68991473
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910822620.6A Pending CN110647823A (en) | 2019-09-02 | 2019-09-02 | Method and device for optimizing human face base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110647823A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111680175A (en) * | 2020-05-15 | 2020-09-18 | 浙江大华技术股份有限公司 | Face database building method, computer equipment and computer readable storage medium |
| CN111814570A (en) * | 2020-06-12 | 2020-10-23 | 深圳禾思众成科技有限公司 | Face recognition method, system and storage medium based on dynamic threshold |
| CN112084903A (en) * | 2020-08-26 | 2020-12-15 | 武汉普利商用机器有限公司 | Method and system for updating face recognition base photo |
| CN112419528A (en) * | 2020-10-27 | 2021-02-26 | 安徽山巅电力科技有限公司 | Self-service all-in-one machine for meeting new needs and working method |
| CN113077574A (en) * | 2021-04-09 | 2021-07-06 | 上海云从企业发展有限公司 | Passing method, system, equipment and medium based on face recognition |
| CN114429663A (en) * | 2022-01-28 | 2022-05-03 | 北京百度网讯科技有限公司 | Updating method of human face base, human face recognition method, device and system |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593598A (en) * | 2013-11-25 | 2014-02-19 | 上海骏聿数码科技有限公司 | User online authentication method and system based on living body detection and face recognition |
| US20160104034A1 (en) * | 2014-10-09 | 2016-04-14 | Sensory, Incorporated | Continuous enrollment for face verification |
| CN105913014A (en) * | 2016-04-08 | 2016-08-31 | 上海逗点科技股份有限公司 | Identity card chip photograph and video-based identity authenticating method and system |
| CN105938552A (en) * | 2016-06-29 | 2016-09-14 | 北京旷视科技有限公司 | Face recognition method capable of realizing base image automatic update and face recognition device |
| CN106101136A (en) * | 2016-07-22 | 2016-11-09 | 飞天诚信科技股份有限公司 | The authentication method of a kind of biological characteristic contrast and system |
| KR20170132914A (en) * | 2016-05-20 | 2017-12-05 | (주)휴메인시스템 | A system and a method for identifying based on matching of images |
| CN108038179A (en) * | 2017-12-07 | 2018-05-15 | 泰康保险集团股份有限公司 | Identity information authentication method and device |
| CN108229330A (en) * | 2017-12-07 | 2018-06-29 | 深圳市商汤科技有限公司 | Face fusion recognition methods and device, electronic equipment and storage medium |
| CN108446387A (en) * | 2018-03-22 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for updating face registration library |
| CN109063691A (en) * | 2018-09-03 | 2018-12-21 | 武汉普利商用机器有限公司 | A kind of recognition of face bottom library optimization method and system |
| CN109660509A (en) * | 2018-10-29 | 2019-04-19 | 北京旷视科技有限公司 | Login method, device, system and storage medium based on recognition of face |
| CN109670436A (en) * | 2018-12-13 | 2019-04-23 | 北京旷视科技有限公司 | Vehicle operator's auth method, device and electronic equipment |
-
2019
- 2019-09-02 CN CN201910822620.6A patent/CN110647823A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593598A (en) * | 2013-11-25 | 2014-02-19 | 上海骏聿数码科技有限公司 | User online authentication method and system based on living body detection and face recognition |
| US20160104034A1 (en) * | 2014-10-09 | 2016-04-14 | Sensory, Incorporated | Continuous enrollment for face verification |
| CN105913014A (en) * | 2016-04-08 | 2016-08-31 | 上海逗点科技股份有限公司 | Identity card chip photograph and video-based identity authenticating method and system |
| KR20170132914A (en) * | 2016-05-20 | 2017-12-05 | (주)휴메인시스템 | A system and a method for identifying based on matching of images |
| CN105938552A (en) * | 2016-06-29 | 2016-09-14 | 北京旷视科技有限公司 | Face recognition method capable of realizing base image automatic update and face recognition device |
| CN106101136A (en) * | 2016-07-22 | 2016-11-09 | 飞天诚信科技股份有限公司 | The authentication method of a kind of biological characteristic contrast and system |
| CN108038179A (en) * | 2017-12-07 | 2018-05-15 | 泰康保险集团股份有限公司 | Identity information authentication method and device |
| CN108229330A (en) * | 2017-12-07 | 2018-06-29 | 深圳市商汤科技有限公司 | Face fusion recognition methods and device, electronic equipment and storage medium |
| CN108446387A (en) * | 2018-03-22 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for updating face registration library |
| CN109063691A (en) * | 2018-09-03 | 2018-12-21 | 武汉普利商用机器有限公司 | A kind of recognition of face bottom library optimization method and system |
| CN109660509A (en) * | 2018-10-29 | 2019-04-19 | 北京旷视科技有限公司 | Login method, device, system and storage medium based on recognition of face |
| CN109670436A (en) * | 2018-12-13 | 2019-04-23 | 北京旷视科技有限公司 | Vehicle operator's auth method, device and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| WEN-HUNG LIAO: "A framework for attention-based personal photo manager", 《2009 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS》 * |
| 樊涛 等: "人脸识别技术在国网电商的应用", 《数字中国 能源互联——2018电力行业信息化年会论文集》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111680175A (en) * | 2020-05-15 | 2020-09-18 | 浙江大华技术股份有限公司 | Face database building method, computer equipment and computer readable storage medium |
| CN111680175B (en) * | 2020-05-15 | 2023-04-25 | 浙江大华技术股份有限公司 | Face database construction method, computer equipment and computer readable storage medium |
| CN111814570A (en) * | 2020-06-12 | 2020-10-23 | 深圳禾思众成科技有限公司 | Face recognition method, system and storage medium based on dynamic threshold |
| CN111814570B (en) * | 2020-06-12 | 2024-04-30 | 深圳禾思众成科技有限公司 | Face recognition method, system and storage medium based on dynamic threshold |
| CN112084903A (en) * | 2020-08-26 | 2020-12-15 | 武汉普利商用机器有限公司 | Method and system for updating face recognition base photo |
| CN112419528A (en) * | 2020-10-27 | 2021-02-26 | 安徽山巅电力科技有限公司 | Self-service all-in-one machine for meeting new needs and working method |
| CN113077574A (en) * | 2021-04-09 | 2021-07-06 | 上海云从企业发展有限公司 | Passing method, system, equipment and medium based on face recognition |
| CN114429663A (en) * | 2022-01-28 | 2022-05-03 | 北京百度网讯科技有限公司 | Updating method of human face base, human face recognition method, device and system |
| CN114429663B (en) * | 2022-01-28 | 2023-10-20 | 北京百度网讯科技有限公司 | Updating method of face base, face recognition method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647823A (en) | Method and device for optimizing human face base | |
| CN110825765B (en) | Face recognition method and device | |
| CN107945198B (en) | Method and device for marking point cloud data | |
| WO2019109526A1 (en) | Method and device for age recognition of face image, storage medium | |
| CN108229419B (en) | Method and apparatus for clustering images | |
| CN111242097B (en) | Face recognition method and device, computer readable medium and electronic equipment | |
| WO2022041830A1 (en) | Pedestrian re-identification method and device | |
| CN107220652B (en) | Method and device for processing pictures | |
| CN108108711B (en) | Face control method, electronic device and storage medium | |
| CN108229375B (en) | Method and device for detecting face image | |
| CN108932774B (en) | Information detection method and device | |
| CN112954450A (en) | Video processing method and device, electronic equipment and storage medium | |
| CN110941978A (en) | Face clustering method and device for unidentified personnel and storage medium | |
| CN109871791A (en) | Image processing method and device | |
| CN110879986A (en) | Face recognition method, apparatus and computer-readable storage medium | |
| CN114627526A (en) | Fusion duplicate removal method and device based on multi-camera snapshot image and readable medium | |
| CN110852193A (en) | Face recognition method and device | |
| CN113627361B (en) | Training method and device for face recognition model and computer program product | |
| CN111428590A (en) | Video clustering segmentation method and system | |
| CN116524206B (en) | Target image identification method and device | |
| CN113822110A (en) | Target detection method and device | |
| CN111783677A (en) | Face recognition method, face recognition device, server and computer readable medium | |
| US20220309763A1 (en) | Method for identifying traffic light, device, cloud control platform and vehicle-road coordination system | |
| TWI789128B (en) | Face recognition method, device, equipment and storage medium | |
| CN110634155A (en) | Target detection method and device based on deep learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200103 |