CN116052251A - Face image optimization method, device, equipment and storage medium - Google Patents

Face image optimization method, device, equipment and storage medium Download PDF

Info

Publication number
CN116052251A
CN116052251A CN202211733151.9A CN202211733151A CN116052251A CN 116052251 A CN116052251 A CN 116052251A CN 202211733151 A CN202211733151 A CN 202211733151A CN 116052251 A CN116052251 A CN 116052251A
Authority
CN
China
Prior art keywords
face
image
feature
identification
images
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
Application number
CN202211733151.9A
Other languages
Chinese (zh)
Inventor
陈稳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Jiadu Technology Software Development Co ltd
PCI Technology Group Co Ltd
PCI Technology and Service Co Ltd
Original Assignee
Guangzhou Jiadu Technology Software Development Co ltd
PCI Technology Group Co Ltd
PCI Technology and Service Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Jiadu Technology Software Development Co ltd, PCI Technology Group Co Ltd, PCI Technology and Service Co Ltd filed Critical Guangzhou Jiadu Technology Software Development Co ltd
Priority to CN202211733151.9A priority Critical patent/CN116052251A/en
Publication of CN116052251A publication Critical patent/CN116052251A/en
Pending legal-status Critical Current

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
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53—Querying
    • G06F16/535—Filtering based on additional data, e.g. user or group profiles
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The embodiment of the application provides a face image optimization method, a device, equipment and a storage medium, and relates to the technical field of image recognition, wherein the method comprises the following steps: selecting face images recorded in a preset screening period from a face image library as identification images, wherein a plurality of successfully identified face images corresponding to each user are recorded in the face image library; acquiring feature scores corresponding to feature factors of the identification image; acquiring a first index score associated with the identification image according to the feature scores corresponding to the feature factors and the corresponding weight combinations; acquiring the number of times of comparing the identification images to determine a second index score; and determining the recognition rate score of the corresponding recognition image according to the first index score, the second index score and the corresponding evaluation weight, and taking the recognition image with the highest recognition rate score as the preferable image. The scheme realizes the periodical automatic updating of the images in the face image library, and effectively improves the recognition success rate of the system.

Description

Face image optimization method, device, equipment and storage medium
Technical Field
The embodiment of the application relates to the technical field of image recognition, in particular to a face image optimization method, a face image optimization device, face image optimization equipment and a face image storage medium.
Background
Along with the development, popularization and popularization of the face recognition technology, the face recognition technology is more and more widely applied to business scenes such as face attendance, face payment, gate access, person verification and the like. Of course, in the service system using the face recognition technology, it is necessary to first establish a face image library of the user of the system, where the source of the face image library of the system is generally a face image provided when the user registers, and the service system stores the face image of the user into the database and establishes the face image library at the same time. When the user uses the face recognition function, the face acquisition device acquires a snap image of the face of the user and compares the snap image with face images in a face image library to determine whether the user successfully recognizes.
However, as the user ages, the appearance of the user may change, or the use scene is different, so that factors such as the snapping angle and light of the face collecting device when the user uses the face recognition function cause great differences between the snapping image and the face image when the user registers, and multiple recognition failures may occur when the user performs face recognition, so that the situations of high recognition rejection rate and poor experience are caused.
In the related technology, a timing reminding user is adopted to re-register or update the face image registered in the business system according to related requirements, but the method is complex in operation for the user, the user is required to update the picture automatically and at a specified time, so that the use experience of the user is poor, the method of the user for updating automatically for the business system is uncontrollable, and the business system is difficult to provide an effective face recognition function.
Disclosure of Invention
The embodiment of the application provides a face image optimization method, device, equipment and storage medium, which solve the problems of high rejection rate and poor experience caused by incapability of updating images in a library in time, can effectively screen out high-quality face images and update the high-quality face images into a face image library without active updating of users, realize periodical automatic updating of the images in the face image library, and effectively improve the recognition success rate of a system.
In a first aspect, an embodiment of the present application provides a face image optimization method, including:
selecting face images recorded in a preset screening period from a face image library as identification images, wherein a plurality of successfully identified face images corresponding to each user are recorded in the face image library;
acquiring feature scores corresponding to feature factors of the identification image;
acquiring a first index score associated with the identification image according to the feature scores corresponding to the feature factors and the corresponding weight combinations;
acquiring the number of times of comparing the identification images to determine a second index score;
and determining the recognition rate score of the corresponding recognition image according to the first index score, the second index score and the corresponding evaluation weight, and taking the recognition image with the highest recognition rate score as the preferable image.
In a second aspect, an embodiment of the present application provides a face image preference apparatus, including:
the image acquisition module is configured to select face images recorded in a preset screening period from a face image library as identification images, wherein a plurality of successfully identified face images corresponding to each user are recorded in the face image library;
the feature score determining module is configured to acquire feature scores corresponding to feature factors of the identification image;
the first score determining module is configured to acquire a first index score associated with the identification image according to the feature scores corresponding to the feature factors and the corresponding weight combinations;
the second score determining module is configured to acquire the number of times of comparison of the identification images so as to determine a second index score;
the image selecting module is configured to determine the recognition rate score of the corresponding recognition image according to the first index score, the second index score and the corresponding evaluation weight, and take the recognition image with the highest recognition rate score as the preferable image.
In a third aspect, an embodiment of the present application provides an electronic device, including:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the face image optimization method described in the embodiment of the first aspect.
In a fourth aspect, embodiments of the present application further provide a storage medium storing computer-executable instructions, which when executed by a processor are configured to perform the face image optimization method according to the embodiments of the first aspect.
According to the face image identification method and device based on the characteristic factors, the face images successfully identified in each screening period are scored based on the characteristic factors to obtain corresponding first index scores, the face images selected in the face images are identified and compared by taking the face images as compared target images, corresponding second index scores are obtained, the first index scores and the second index scores are combined, so that the identification rate score corresponding to each face image is obtained, the optimal images are selected from all face images and added into a face image library, periodic automatic updating of the images in the face image library is achieved, and the identification success rate of a system is effectively improved.
Drawings
Fig. 1 is a flowchart of steps of a face image optimization method provided in an embodiment of the present application;
FIG. 2 is a flowchart illustrating steps for determining the number of times in a ratio according to an embodiment of the present application;
fig. 3 is a schematic diagram of a face image optimization device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in further detail below with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the embodiments of the application and are not limiting of the embodiments of the application. It should be further noted that, for convenience of description, only some, but not all of the structures related to the embodiments of the present application are shown in the drawings.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type and not limited to the number of objects, e.g., the first object may be one or more. In the description of the specification and claims, "a plurality" means two or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.
The face image optimization method can be applied to a service system adopting face recognition technology, and can realize service scenes such as face attendance, face passing and the like. It is conceivable that the business system may be loaded in the electronic device in the form of application software.
Fig. 1 is a flowchart of steps of a face image optimization method according to an embodiment of the present application, as shown in the drawing, the face image optimization method includes the following steps:
step S110, selecting face images recorded in a preset screening period from a face image library as identification images.
It can be understood that the face image library records a plurality of face images which are successfully identified and correspond to each user, that is, in the face image library, for each user registered in the service system, the service system stores the face image which is currently captured after each successful identification, for example, the face images corresponding to different users are identified by the system ID (Identity Document, identification number) of the user, so as to facilitate the subsequent screening process.
For the identification image, the service system selects a face image from the face image library, and the selected face image corresponds to the same user, for example, the service system selects a corresponding face image according to the system ID of the user; in addition, the selected face image corresponds to a preset screening period. It should be appreciated that the screening period is a duration preset in the business system, such as a week, a month, etc., during which the business system stores the currently captured face image after each successful recognition and also associates it with the current screening period.
It should be noted that, after screening is completed for all the identification images in each screening period, that is, after selecting the preferred image corresponding to the screening period, the service system may delete other identification images recorded in the screening period, so as to restart the timing of a new screening period.
Step S120, obtaining feature scores corresponding to feature factors of the identification image.
For each identified image, the business system calculates the same to obtain feature scores corresponding to different feature factors, such as face angles, light brightness, face occlusion, facial expression, and face duty cycle in some embodiments, so that the business system calculates the scores of each identified image separately to obtain corresponding feature scores corresponding to each feature factor.
For example, a first feature score corresponding to a face angle may be determined by calculating that a face in a face image corresponds to an angle of inclination (e.g., euler angle), and for the calculation of the angle of inclination, the corresponding euler angle may be calculated based on OpenCV and from key points of the face, such that the smaller the angle of inclination, the greater the feature score of the term.
For the second feature value of the light brightness, the corresponding brightness can be calculated according to the RGB components in the face image, for example, the brightness value is calculated by using RGB three-color light according to the preset proportion.
The third feature score of the face occlusion can be obtained by calculating the size of the occlusion range of the face, for example, the feature score of the item is the ratio of the occlusion range of the key parts (such as eyes, nose, mouth and face) of the face to the whole face image.
For the fourth feature score of the facial expression, the corresponding facial expression (such as happy, surprise or normal) may be determined according to the motion recognition of facial features (such as eyes, nose, mouth and eyebrows), and for different facial expressions, different scores may be preset to determine the fourth feature score.
For the fifth feature score of the face duty ratio, the fifth feature score may be determined according to the duty ratio of the face in the entire image.
It should be noted that, for the calculation of the feature scores corresponding to the feature factors, reference may also be made to the technical schemes described in other existing documents, which will not be described in detail in the embodiments of the present application. In addition, to facilitate calculation of the first index score, the actual value of the feature score may also be normalized into interval [0,1 ].
Step S130, according to the feature scores corresponding to the feature factors and the corresponding weight combinations, a first index score associated with the identification image is obtained.
The number of terms of the feature weights in the weight combination is the same as the number of the feature factors, the feature weights are preset by the service system, the service system configures corresponding feature weights corresponding to the feature factors, and the sum of all the feature weights is 1. The first index score is a numerical value associated with the first index score and the second index score, namely the product cumulative sum of all the characteristic factors and the corresponding characteristic weights.
It should be noted that, the first feature weight and the third feature weight have the largest values among all feature weights, that is, the face angle and the face shielding are used as the parameter items with the largest proportion in the first index score, which is helpful for screening higher quality images.
Step S140, the number of times of comparing the identification images is acquired to determine a second index score.
For the selected identification image, a second index score corresponding to the number of times of comparison is also acquired. It can be understood that after the identification images recorded in the screening period are selected, statistics needs to be performed on the number of times of comparing each identification image, for example, the images are compared in pairs, if the similarity of the two images reaches 90% (the threshold can be set according to the requirement), the number of times of comparing can be determined to be one, so that all the identification images are traversed, and the number of times of comparing each identification image with all the identification images is determined to obtain the second index number of each identification image.
It will be appreciated that, for the acquisition of the first index score and the second index score, the two scores are not sequential, and in some embodiments, the second index score may be calculated first and then the first index score may be calculated, and further, the calculation of the first index score and the second index score may be performed simultaneously.
And step S150, determining the recognition rate score of the corresponding recognition image according to the first index score, the second index score and the corresponding evaluation weight, and taking the recognition image with the highest recognition rate score as the preferable image.
Similarly, for the evaluation weight, a first evaluation weight is set corresponding to the first index score, a second evaluation weight is set corresponding to the second index score, and the first evaluation weight and the second evaluation weight are preset in the service system. The recognition rate score is divided into the sum of products of the first index score, the second index score and the corresponding evaluation weight, so that the recognition rate score corresponding to each recognition image is obtained, and the image with the highest recognition rate score in all the recognition images is taken as the preferable image.
It should be noted that, in some embodiments, the first evaluation weight is smaller than the second evaluation weight, so that the second index score has the largest proportion in the recognition rate score, so that the number of times of proportion is used as an important reference index for selecting the preferred image, which is helpful for improving the recognition rate.
According to the scheme, the business system applying the face image optimization method provided by the application can calculate the corresponding recognition rate score for the recorded recognition images after each screening period is finished, so that the recognition image with the highest recognition rate score is selected from a plurality of recognition images as the optimization image and is added into the face image library, periodic automatic updating of the images in the face image library is realized, and the recognition success rate of the system can be effectively improved.
Fig. 2 is a flowchart of steps for determining the number of times in the comparison, and as shown in fig. 2, the face image optimization method further includes the following steps:
step S210, extracting the characteristic value data of all the identification images.
And step 220, based on the characteristic value data, respectively carrying out pairwise comparison on all the identification images, and recording the comparison result as the comparison times.
It will be appreciated that for each recognition image, the extracted feature value data may be the recognition data associated with the face features acquired during the face recognition process. After extracting the characteristic value data of all the identification images, comparing the identification images based on the characteristic value data.
For example, there are 4 face images recorded in the filtering period, i.e., four recognition images, including, for example, recognition image I, recognition image II, recognition image III, and recognition image IV. And extracting characteristic value data for each identification image so as to facilitate comparison based on the characteristic value data. And comparing the currently selected identification image I with the identification image II, the identification image III and the identification image IV respectively, and if the similarity of the feature value data of the two compared images is greater than or equal to 90%, determining that the number of times of comparison is increased by one in the two images, so that all the images are traversed, and determining the number of times of comparison corresponding to the identification image I.
For the identification image II, it can be compared with the identification image I, the identification image III and the identification image IV, and it is conceivable that if the previous identification image I and the identification image II have been compared, in the present round of comparison, the last comparison result can be adopted, so as to reduce the calculation workload of the service system.
Therefore, the second index score corresponding to each identification image is obtained by comparing the selected identification images and obtaining the number of times of comparison in each identification image, for example, the ratio of the number of times of comparison to the number of times of comparison is used as the second index score.
It should be noted that in some embodiments, the identification image itself is also compared, that is, the number of times of comparison and the number of times of comparison are both accumulated and added by one.
According to the scheme, the service system can determine the comparison times of the images by comparing the recorded identification images, and screen the images by combining the first index score, so that the service system is beneficial to selecting the images which can more represent the recorded results in the screening period.
In some embodiments, the screening period is a preset duration, and the number of face recognition operations performed by the user during the screening period is unlimited, so that the number of recognition images recorded during the screening period corresponding to different users is different. And when the number of the identification images is larger than the preset number, selecting the preset number of the identification images for feature extraction.
For example, in the case that the number of the identification images recorded in the screening period is greater than the preset number, the service system may select the identification images satisfying the preset number from the identification images to screen, that is, select a preferred image from the preset number of identification images. It is conceivable that, for the selection manner of the identification image, it may be a random selection manner, a selection manner according to the order of recording, or the like, and the selected number may satisfy the preset number.
It should be noted that, for the case that the number of the identification images recorded in the screening period is less than or equal to the preset number, the service system may select all the identification images recorded in the screening period.
Therefore, by setting the upper limit of the number of the selected identification images, the electronic device loading the business system can reduce the calculation workload increased by the excessive number of the identification images recorded in the screening period.
In an application scenario, for example, the business system is applied to the business scenario of face attendance, enterprise staff is taken as a target user, and the target users are registered in the business system. In each screening period, the service system stores the currently acquired face image in a face image library when the target user performs attendance checking by using the face recognition function each time. If the screening period is set to four weeks in the service system, the target user checks the work attendance at least twice in the working day, and at least 40 successfully identified face images are stored in the face image library corresponding to each target user in the screening period.
The service system selects the face images as the identification images, and performs feature score calculation corresponding to each feature factor, such as feature score calculation corresponding to five feature factors including face angle, light brightness, face shielding, face expression and face occupation ratio, on each identification image. The service system is configured with corresponding characteristic weights for the characteristic factors, such as a first characteristic weight theta corresponding to the face angle 1 Second characteristic weight value theta corresponding to light brightness 2 Third characteristic weight value theta corresponding to face shielding 3 Fourth characteristic weight value theta corresponding to facial expression 4 And a fifth characteristic weight value theta corresponding to the face duty ratio 5 Wherein θ 1 、θ 2 、θ 3 、θ 4 And theta 5 Can take on the values of 0.3, 0.1, 0.3, 0.1 and 0.2. Thus, a first index score is calculated for the identification image, e.g., the first index score is calculated according to the following formula:
Q＝θ 1 A+θ 2 B+θ 3 O+θ 4 E+θ 5 P
wherein Q is a first index score, A is a first characteristic score corresponding to a face angle, B is a second characteristic score corresponding to light brightness, O is a third characteristic score corresponding to face shielding, E is a fourth characteristic score corresponding to a face expression, and P is a fifth characteristic score corresponding to a face occupation ratio.
And extracting the characteristics of each identification image so as to compare the recorded identification images, thereby obtaining the times of comparing each identification image and determining the corresponding second index score T. In addition, according to the first index score Q and the second index score T, the business system is further configured with corresponding evaluation weights, such as a first evaluation weight S corresponding to the first index score Q 1 And a second evaluation weight S corresponding to the second index score T 2 Wherein S is 1 And S is 2 The corresponding value can be given. The service system calculates an identification rate score for each identification image, for example, the identification rate score W is calculated by adopting the following calculation formula:
W＝S 1 Q+S 2 T
after the recognition rate score of each recognition image is obtained, the service system can store the recognition image with the highest recognition rate score in the face image library to be used as an image for comparison in the face recognition process, so that the image update of the face image library is realized, the manual update of a user is not needed, the service system screens out the face image with the highest recognition rate score from the face images acquired by the multiple face recognition functions and automatically updates the face image into the face image library of the system, the high recognition rate of the image quality and the image is ensured, the user experience effect is improved, and the recognition success rate of the system is also effectively improved.
Fig. 3 is a schematic diagram of a face image optimization device provided in an embodiment of the present application, where the device is configured to execute the face image optimization method provided in the foregoing embodiment, and includes corresponding functional modules and beneficial effects of the execution method, and as shown in the figure, the device includes: an image acquisition module 301, a feature score determination module 302, a first score determination module 303, a second score determination module 304, and an image selection module 305.
The image acquisition module 301 is configured to select face images recorded in a preset screening period from a face image library as identification images, wherein a plurality of successfully identified face images corresponding to each user are recorded in the face image library;
the feature score determining module 302 is configured to obtain feature scores corresponding to feature factors of the identification image;
the first score determining module 303 is configured to obtain a first index score associated with the identification image according to the feature scores corresponding to the feature factors and the corresponding weight combinations;
the second score determination module 304 is configured to obtain the number of times the identified image is compared to determine a second index score;
the image selection module 305 is configured to determine an identification rate score of the corresponding identification image according to the first index score, the second index score and the corresponding evaluation weight, and take the identification image with the highest identification rate score as the preferred image.
On the basis of the embodiment, the characteristic factors include face angle, light brightness, face shielding, face expression and face occupation ratio.
On the basis of the above embodiment, the weight combination includes the same number of feature weights as the number of feature factors, and the first index score is a product cumulative sum of all feature factors and corresponding feature weights.
On the basis of the embodiment, the face angle, the light brightness, the face shielding, the face expression and the face occupation ratio sequentially correspond to the first feature weight, the second feature weight, the third feature weight, the fourth feature weight and the fifth feature weight; the first feature weight and the third feature weight take the largest value among all the feature weights.
Based on the above embodiment, the identifying image has at least two, and the second score determining module 304 is further configured to:
extracting the characteristic value data of all the identification images;
and based on the characteristic value data, respectively carrying out pairwise comparison on all the identification images, and recording the comparison result as the comparison times.
On the basis of the above embodiment, the second score determination module 304 is further configured to:
and when the number of the identification images recorded in the screening period is larger than the preset number, selecting the identification images meeting the preset number.
On the basis of the above embodiment, the first evaluation weight corresponding to the first index score is smaller than the second evaluation weight corresponding to the second index score.
It should be noted that, in the embodiment of the face image preferred apparatus, each included functional module is only divided according to the functional logic, but not limited to the above-mentioned division, so long as the corresponding function can be implemented; in addition, the specific names of the functional modules are only for distinguishing from each other, and are not used for limiting the protection scope of the application.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application, where the device includes a processor 401, a memory 402, an input device 403, and an output device 404, where the number of the processors 401 in the device may be one or more, and one processor 401 is illustrated in the figure as an example; the processor 401, memory 402, input means 403 and output means 404 in the device may be connected by a bus or by other means, in the figure by way of example. The memory 402 is used as a computer readable storage medium for storing a software program, a computer executable program, and modules, such as program instructions/modules corresponding to the face image optimization method in the embodiment of the present application. The processor 401 executes various functional applications of the device and data processing by running software programs, instructions and modules stored in the memory 402, i.e., implements the face image preference method described above.
Memory 402 may include primarily a program storage area and a data storage area, wherein the program storage area may store an operating system, at least one application program required for functionality; the storage data area may store data created according to the use of the electronic device, etc., such as a face image, a first index score, a second index score, etc. In addition, memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, memory 402 may further include memory remotely located with respect to processor 401, which may be connected to the terminal device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 403 may be used to receive entered numeric or character information and to generate key signal inputs related to user settings and function control of the device. The output means 404 may be used to send or display key signal outputs related to user settings of the device and function control, such as outputting a preferred image.
Embodiments of the present application also provide a storage medium storing computer-executable instructions that, when executed by a processor, are configured to perform related operations in the face image preference method provided in any of the embodiments of the present application.
Computer-readable storage media, including both permanent and non-permanent, removable and non-removable media, may be implemented in any method or technology for storage of information. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
Note that the above is only a preferred embodiment of the present application and the technical principle applied. Those skilled in the art will appreciate that the present application is not limited to the particular embodiments described herein, but is capable of numerous obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the present application. Therefore, while the present application has been described in connection with the above embodiments, the present application is not limited to the above embodiments, but may include many other equivalent embodiments without departing from the spirit of the present application, the scope of which is defined by the scope of the appended claims.

Claims (10)

1. A face image optimization method, the method comprising:
selecting face images recorded in a preset screening period from a face image library as identification images, wherein a plurality of successfully identified face images corresponding to each user are recorded in the face image library;
acquiring feature scores corresponding to feature factors of the identification image;
acquiring a first index score associated with the identification image according to the feature scores and the corresponding weight combinations corresponding to the feature factors;
acquiring the number of times of comparison of the identification images to determine a second index score;
and determining the recognition rate score of the corresponding recognition image according to the first index score, the second index score and the corresponding evaluation weight, and taking the recognition image with the highest recognition rate score as a preferable image.
2. The face image optimization method of claim 1 wherein the characteristic factors include face angle, light brightness, face occlusion, face expression, and face duty cycle.
3. The face image optimization method according to claim 1 or 2, wherein the weight combination includes feature weights equal to the number of feature factors, and the first index score is a product cumulative sum of all the feature factors and the corresponding feature weights.
4. The face image optimization method according to claim 2, wherein the face angle, the light brightness, the face occlusion, the face expression, and the face duty ratio correspond to a first feature weight, a second feature weight, a third feature weight, a fourth feature weight, and a fifth feature weight in this order; the first feature weight and the third feature weight take the largest value among all feature weights.
5. The face image optimization method of claim 1, wherein the identification images are at least two, and the obtaining the number of times of comparing the identification images to determine the second index score comprises:
extracting the characteristic value data of all the identification images;
and respectively carrying out pairwise comparison on all the identification images based on the characteristic value data, and recording comparison results as the comparison times.
6. The face image optimization method according to claim 5, further comprising, before extracting the feature value data of all the identification images:
and when the number of the identification images recorded in the screening period is larger than a preset number, selecting the identification images meeting the preset number.
7. The face image preference method of claim 1, wherein a first evaluation weight corresponding to the first index score is smaller than a second evaluation weight corresponding to the second index score.
8. A face image preference apparatus, the apparatus comprising:
the image acquisition module is configured to select face images recorded in a preset screening period from a face image library as identification images, wherein a plurality of face images which are successfully identified and correspond to each user are recorded in the face image library;
the feature score determining module is configured to acquire feature scores corresponding to feature factors of the identification image;
the first score determining module is configured to acquire a first index score associated with the identification image according to the feature scores corresponding to the feature factors and the corresponding weight combinations;
a second score determining module configured to obtain the number of times of comparison of the identification image to determine a second index score;
the image selecting module is configured to determine an identification rate score of the corresponding identification image according to the first index score, the second index score and the corresponding evaluation weight, and take the identification image with the highest identification rate score as a preferred image.
9. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs which when executed by one or more of the processors cause the one or more processors to implement the face image preference method of any one of claims 1 to 7.
10. A storage medium storing computer executable instructions which, when executed by a processor, are adapted to carry out the face image preference method of any one of claims 1 to 7.
CN202211733151.9A 2022-12-30 2022-12-30 Face image optimization method, device, equipment and storage medium Pending CN116052251A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211733151.9A CN116052251A (en) 2022-12-30 2022-12-30 Face image optimization method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211733151.9A CN116052251A (en) 2022-12-30 2022-12-30 Face image optimization method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN116052251A true CN116052251A (en) 2023-05-02

Family

ID=86123166

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211733151.9A Pending CN116052251A (en) 2022-12-30 2022-12-30 Face image optimization method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116052251A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116383795A (en) * 2023-06-01 2023-07-04 杭州海康威视数字技术股份有限公司 Biological feature recognition method and device and electronic equipment

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116383795A (en) * 2023-06-01 2023-07-04 杭州海康威视数字技术股份有限公司 Biological feature recognition method and device and electronic equipment
CN116383795B (en) * 2023-06-01 2023-08-25 杭州海康威视数字技术股份有限公司 Biological feature recognition method and device and electronic equipment

Similar Documents

Publication Publication Date Title
US8873845B2 (en) Contextual dominant color name extraction
US9972113B2 (en) Computer-readable recording medium having stored therein album producing program, album producing method, and album producing device for generating an album using captured images
US11317139B2 (en) Control method and apparatus
US8958662B1 (en) Methods and systems for automating insertion of content into media-based projects
CA3111097C (en) Bounding box doubling as redaction boundary
US9329762B1 (en) Methods and systems for reversing editing operations in media-rich projects
US9665959B2 (en) Composite image creation assist apparatus using images of users other than target user, and non-transitory computer readable recording medium
WO2020077871A1 (en) Event prediction method and apparatus based on big data, computer device, and storage medium
US20230044146A1 (en) Video processing method, video searching method, terminal device, and computer-readable storage medium
US20160110070A1 (en) Photo collection display method and apparatus
US20220417417A1 (en) Content Operation Method and Device, Terminal, and Storage Medium
CN110832583A (en) System and method for generating a summary storyboard from a plurality of image frames
CN112199530B (en) Multi-dimensional face library picture automatic updating method, system, equipment and medium
US11297027B1 (en) Automated image processing and insight presentation
US9549162B2 (en) Image processing apparatus, image processing method, and program
CN106815803B (en) Picture processing method and device
CN111144950B (en) Model screening method and device, electronic equipment and storage medium
US20170169062A1 (en) Method and electronic device for recommending video
CN110929063A (en) Album generating method, terminal device and computer readable storage medium
EP2864906A2 (en) Searching for events by attendants
CN116052251A (en) Face image optimization method, device, equipment and storage medium
EP3693920A1 (en) Candidate image determination device, candidate image determination method, program for control of candidate image determination device, and recording medium for storing said program
CN112383824A (en) Video advertisement filtering method, device and storage medium
CN113542833A (en) Video playing method, device and equipment based on face recognition and storage medium
CN115438261A (en) Touch task management method and device, terminal equipment and readable storage medium

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