CN117372405A - Face image quality evaluation method, device, storage medium and equipment - Google Patents
Face image quality evaluation method, device, storage medium and equipment Download PDFInfo
- Publication number
- CN117372405A CN117372405A CN202311444281.5A CN202311444281A CN117372405A CN 117372405 A CN117372405 A CN 117372405A CN 202311444281 A CN202311444281 A CN 202311444281A CN 117372405 A CN117372405 A CN 117372405A
- Authority
- CN
- China
- Prior art keywords
- face
- face image
- quality
- model
- image quality
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000013441 quality evaluation Methods 0.000 title claims abstract description 31
- 238000001303 quality assessment method Methods 0.000 claims abstract description 30
- 238000012549 training Methods 0.000 claims abstract description 15
- 239000013598 vector Substances 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a face image quality assessment method, a device, a storage medium and equipment, wherein the method comprises the following steps: generating labels of quality scores of face images based on a pre-trained face recognition model and a corresponding face image dataset, wherein the face image dataset comprises a plurality of different people, and each person comprises a plurality of face images with different qualities; and taking the face image as a training sample, and combining the corresponding quality score labels to train a face quality assessment model. According to the invention, the output face image quality fraction directly reflects the probability that the face can be correctly recognized, so that compared with the traditional face quality evaluation method irrelevant to face recognition, the method can greatly improve the reliability of face recognition.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a storage medium, and a device for evaluating quality of a face image.
Background
Face recognition technology is widely applied to aspects in society, but in practical application, factors such as illumination, lens parameters, shooting angles and distances, motion blur, shielding, facial expression, makeup and the like can influence the quality of face images, and low-quality face images can greatly reduce the accuracy of face recognition, so that the quality of face images is evaluated, and the elimination of low-quality face images in face recognition is crucial to the improvement of face recognition reliability.
The existing face image quality judging method mainly calculates the definition of a face image according to a general image quality evaluating method, or calculates face angles and shielding conditions according to face key points by using a face key point detecting method, or judges the face image quality through manual subjective scoring. A big problem common to all the aforementioned methods is that the face image quality scores calculated by these methods are independent of the face recognition model, because only some factors affecting the face recognition effect can be considered, and thus the face image quality scores are inconsistent with the face recognition model, in other words, the face quality scores generated by these methods cannot well reflect the reliability of face recognition.
Disclosure of Invention
In view of the above technical problems, the invention provides a face image quality evaluation method, a device, a storage medium and equipment, wherein the similarity relation between a face image calculated by a face recognition model and different images of the same person of the face is utilized to infer the face quality score, the face image quality score directly reflects the probability that the face can be correctly recognized, the problem that the face quality score is inconsistent with the face recognition in the traditional face recognition independent method is solved, and therefore the reliability of the face recognition is greatly improved.
Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure.
According to an aspect of the present invention, a face image quality evaluation method is provided, the evaluation method includes:
generating labels of quality scores of face images based on a pre-trained face recognition model and a corresponding face image dataset, wherein the face image dataset comprises a plurality of different people, and each person comprises a plurality of face images with different qualities;
and taking the face image as a training sample, and combining the corresponding quality score labels to train a face quality assessment model.
Further, the generating a label of the quality score of the face image based on the pre-trained face recognition model and the corresponding face image dataset includes:
inputting a plurality of face images of the same person into a face recognition model to obtain a feature vector corresponding to each face image;
calculating the similarity between any two feature vectors, and normalizing the similarity to be between 0 and 1;
and obtaining the quality score of any face image based on the similarity.
Further, the mass fraction is expressed as:wherein T is a threshold set manually, s (I, I i ) For the similarity between any two of the feature vectors, a function C (x) indicates that 1 is output when the condition is true and 0 is output when the condition is not true.
Further, the mass fraction is expressed ass(I,I i ) Is the similarity between any two of the feature vectors.
Further, the similarity is represented by an angle cosine value or a Euclidean distance between the two feature vectors.
Further, the face quality assessment model is embedded in the face identification model.
According to a second aspect of the present disclosure, there is provided a face image quality evaluation apparatus including:
the quality score acquisition module is used for generating labels of quality scores of face images based on a pre-trained face recognition model and a corresponding face image data set, wherein the face image data set comprises a plurality of different people, and each person comprises a plurality of face images with different qualities;
the model generation module is used for taking the face image as a training sample and combining the corresponding quality score marks to train a face quality evaluation model.
According to a third aspect of the present disclosure, there is provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements a face image quality assessment method as described above.
According to a fourth aspect of the present disclosure, there is provided a face image quality evaluation apparatus including: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the facial image quality assessment method described above.
The technical scheme of the present disclosure has the following beneficial effects:
the method for evaluating the quality of the face image has the advantages that the output quality score of the face image directly reflects the probability that the face can be correctly recognized, so that compared with the traditional face quality evaluating method irrelevant to face recognition, the method for evaluating the quality of the face image can greatly improve the reliability of face recognition. In addition, the face quality evaluation network can be embedded into the existing face recognition network, and face recognition and face quality evaluation can be simultaneously carried out only by adding a little calculation power.
Drawings
Fig. 1 is a flowchart of a face image quality evaluation method in an embodiment of the present disclosure;
fig. 2 is a block diagram of a face image quality evaluation apparatus in the embodiment of the present specification;
fig. 3 is a terminal device for implementing a face image quality evaluation method in an embodiment of the present disclosure;
fig. 4 is a computer readable storage medium storing a face image quality evaluation method according to an embodiment of the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present disclosure. One skilled in the relevant art will recognize, however, that the aspects of the disclosure may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
Furthermore, the drawings are only schematic illustrations of the present disclosure. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.
The invention provides a product face image quality assessment method. Referring to fig. 1, a flow chart of a face image quality evaluation method of a product according to an embodiment of the invention is shown. The method can be applied to electronic equipment such as personal computers, servers and the like. The method may be performed by an apparatus, which may be implemented in software and/or hardware, and the method may specifically include the following steps S101 to S103:
in step S101, labels of quality scores of face images are generated based on a pre-trained face recognition model and a corresponding face image dataset, the face image dataset comprising a plurality of different persons, each person comprising a plurality of face images of different quality.
Wherein a trained face recognition model based on a deep neural network is first selected. The model can be a model which is previously trained and verified on a large scale, such as VGGFace, faceNet or deep, and the like, and can also be a model which is obtained by self-training. A face image dataset comprising a plurality of different persons is then selected. This dataset should contain multiple face images for each person and the quality of these images may vary. Face image data sets are determined according to the selected face recognition model, and can be LFW, celebA, CASIA-WebFace or MS-Celeb-1M, when a plurality of different face images of the same person are selected in the data sets, images with different postures, expressions, illumination conditions and shielding can be selected according to requirements. Of course, the face image dataset may be a gallery employed when self-training a face recognition model.
Specifically, a trained face recognition model based on a deep neural network and a face image dataset are selected, wherein the dataset comprises a plurality of different people, and each person comprises a plurality of face images with different qualities.
The face images are input into a face recognition model to obtain feature vectors of each face, the similarity among the vectors reflects the similarity of the faces in the corresponding images, the similarity among the vectors can be measured by cosine values or Euclidean distances of included angles of the two, the similarity between any two face images A, B is s (A, B), and s (A, B) is normalized to be between 0 and 1. In practical face recognition applications, a threshold T is generally selected, and when the similarity of two faces is greater than the threshold T, the two faces are considered to be the same person, otherwise, the two faces are different persons. For one face image I In the training set, selecting n different faces of the same person as I1-In the face training set, and obtaining the quality score label of the image I by the following two methods:
it can be observed that the higher the quality of the face image, the higher the probability of being correctly recognized, based on which we use the probability of being correctly recognized to represent the quality score of the face image, so that the quality score of image I is:
for function C (x), the function is 1 when x is true, and 0 otherwise. The above expression therefore expresses the proportion of all face images of the same person that can be correctly identified as the same person with I, n should be large enough to ensure the reliability of the quality score.
In another method for expressing the quality score, the average similarity between the high-quality face image and other faces of the same person can be known to be higher, otherwise, the quality score of the face can be expressed as:
the definition reflects the average similarity of the face image to different face images of the same person, the higher the average similarity, the higher the face quality score.
The two face quality score obtaining methods can be replaced by each other, any one of the two methods is selected, and the face quality score corresponding to each face image in the face image data set is calculated.
In step S102, the face image is used as a training sample, and the corresponding label of the quality score is combined to train a face quality evaluation model.
For any face image, it is generally difficult to obtain multiple different face images of the same person, and the quality score of the face image cannot be obtained by using the step S101, so that a face image quality evaluation model is trained by using the face image quality score obtained in S101, and the quality score of any face image is obtained by using the trained face image quality evaluation model. Face image quality assessment networks can be divided into two forms:
the first is a single neural network, the input of the network is a face image, the output is a corresponding face quality score, and therefore the network is a single-output regression model, and the advantages of the form are flexible use scene, custom network structure, common network structure VGG, resnet, mobilenet and the like.
In many scenarios, face recognition and face quality evaluation are required to be performed simultaneously, and the first form is required to operate the face recognition network and the face quality evaluation network simultaneously, so that the operation efficiency is low. Because face recognition and face quality assessment are two very similar tasks, a face image quality model can be embedded into a face recognition model, one branch of the model is used for face recognition, the other branch outputs face quality scores, and the two branches share a face recognition framework part with large calculation amount, so that face recognition and face quality assessment can be simultaneously carried out by only one network, the face recognition and face quality assessment are simpler in practical application, and the operation efficiency is greatly improved. When training the network, only the face quality assessment branch needs to be fine-tuned, and other parts of the network are fixed, so that the training is more efficient.
Based on the same idea, as shown in fig. 2, a face image quality evaluation device is provided, which includes:
the quality score obtaining module 201 is configured to generate a label of quality scores of face images based on a pre-trained face recognition model and a corresponding face image dataset, where the face image dataset includes a plurality of different people, and each person includes a plurality of face images with different quality;
the model generating module 202 is configured to use the face image as a training sample, and combine the corresponding labels of the quality scores to train a face quality assessment model.
By adopting the face image quality evaluation device, the output face image quality score can directly reflect the probability that the face can be correctly recognized, so that compared with the traditional face quality evaluation method irrelevant to face recognition, the method can greatly improve the reliability of face recognition. In addition, the face quality evaluation network can be embedded into the existing face recognition network, and face recognition and face quality evaluation can be simultaneously carried out only by adding a little calculation power.
The specific details of each module/unit in the above apparatus are already described in the method section embodiments, and the details not disclosed may refer to the method section embodiments, so that they will not be described in detail.
Based on the same thought, the embodiment of the present disclosure further provides a face image quality evaluation device, as shown in fig. 3.
The face image quality evaluation device may be a terminal device or a server provided in the above embodiment.
The face image quality assessment apparatus may have a relatively large difference due to different configurations or performances, and may include one or more processors 301, a memory 302, and a bus, where one or more storage applications or data may be stored in the memory 302. The memory 302 may include a readable medium in the form of a volatile memory unit, such as a Random Access Memory (RAM) and/or a cache memory unit, i.e., a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) and the like, which are provided on an electronic device, for example, and may further include a read-only memory unit. The application programs stored in memory 302 may include one or more program modules (not shown), including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Still further, the processor 301 may be arranged to communicate with the memory 302, executing a series of computer executable instructions in the memory 302 on the face image quality assessment device. The face image quality assessment device may also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more I/O interfaces (input/output interfaces) 305, one or more external devices 306 (e.g., a keyboard), and may also communicate with one or more devices that enable a user to interact with the device, and/or with any device that enables the device to communicate with one or more other computing devices (e.g., a router, a network switch, etc.). Such communication may occur through the I/O interface 305. Also, the device may communicate with one or more networks, such as a Local Area Network (LAN), via a wired or wireless interface 304.
The processor 301 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, various control chips, and the like. The processor 301 is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, executes programs or modules (e.g., a product face image quality evaluation program, etc.) stored in the memory 11 by running or executing the programs or modules, and invokes data stored in the memory 11 to perform various functions of the processing device and process the data.
The bus may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 302 and at least one processor 301 or the like.
The power supply may be logically connected to the at least one processor 301 through a power management device, so that functions such as charge management, discharge management, and power consumption management are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
Optionally, the processing device may further comprise a user interface, which may be a Display (Display), and optionally, a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. Wherein the display may also be appropriately referred to as a display screen or display unit for displaying information processed in the electronic device 1 and for displaying a visualized user interface
Fig. 3 shows only a face image quality assessment apparatus having components, and it will be understood by those skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the face image quality assessment apparatus, and may include fewer or more components than illustrated, or may combine certain components, or may be arranged in a different arrangement of components.
In particular, in this embodiment, the face image quality assessment apparatus includes a memory, and one or more programs, where the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions for the face image quality assessment apparatus, and execution of the one or more programs by the one or more processors includes computer executable instructions for:
generating labels of quality scores of face images based on a pre-trained face recognition model and a corresponding face image dataset, wherein the face image dataset comprises a plurality of different people, and each person comprises a plurality of face images with different qualities;
and taking the face image as a training sample, and combining the corresponding quality score labels to train a face quality assessment model.
Based on the same idea, exemplary embodiments of the present invention also provide a computer-readable storage medium on which a program product capable of implementing the method described in the present specification is stored. In some possible implementations, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the disclosure as described in the "exemplary methods" section of this specification, when the program product is run on the terminal device.
Referring to fig. 4, a program 400 for implementing the above-described method according to an exemplary embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a 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.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a 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 for carrying out operations of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++, CSS, HTML and the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the exemplary embodiments of the present disclosure.
Furthermore, the above-described figures are only schematic illustrations of processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily appreciated that the processes shown in the above figures do not indicate or limit the temporal order of these processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, for example, among a plurality of modules.
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with exemplary embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (9)
1. A face image quality assessment method, characterized in that the assessment method comprises:
generating labels of quality scores of face images based on a pre-trained face recognition model and a corresponding face image dataset, wherein the face image dataset comprises a plurality of different people, and each person comprises a plurality of face images with different qualities;
and taking the face image as a training sample, and combining the corresponding quality score labels to train a face quality assessment model.
2. The face image quality assessment method according to claim 1, wherein the generating a label of the quality score of the face image based on the pre-trained face recognition model and the corresponding face image dataset comprises:
inputting a plurality of face images of the same person into a face recognition model to obtain a feature vector corresponding to each face image;
calculating the similarity between any two feature vectors, and normalizing the similarity to be between 0 and 1;
and obtaining the quality score of any face image based on the similarity.
3. The face image quality assessment method according to claim 2, wherein the quality score is expressed as:wherein T is a threshold set manually, s (I, I i ) For the similarity between any two of the feature vectors, a function C (x) indicates that 1 is output when the condition is true and 0 is output when the condition is not true.
4. The face image quality evaluation method according to claim 2, wherein the quality score is expressed ass(I,I i ) Is the similarity between any two of the feature vectors.
5. The face image quality evaluation method according to claim 1, wherein the similarity is represented by an angle cosine value or a euclidean distance between the two feature vectors.
6. The face image quality assessment method according to claim 1, wherein the face quality assessment model is embedded in the face recognition model.
7. A face image quality evaluation apparatus, characterized by comprising:
the quality score acquisition module is used for generating labels of quality scores of face images based on a pre-trained face recognition model and a corresponding face image data set, wherein the face image data set comprises a plurality of different people, and each person comprises a plurality of face images with different qualities;
the model generation module is used for taking the face image as a training sample and combining the corresponding quality score marks to train a face quality evaluation model.
8. A face image quality assessment apparatus, the apparatus comprising:
a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to:
generating labels of quality scores of face images based on a pre-trained face recognition model and a corresponding face image dataset, wherein the face image dataset comprises a plurality of different people, and each person comprises a plurality of face images with different qualities;
and taking the face image as a training sample, and combining the corresponding quality score labels to train a face quality assessment model.
9. A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the face image quality assessment method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311444281.5A CN117372405A (en) | 2023-10-31 | 2023-10-31 | Face image quality evaluation method, device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311444281.5A CN117372405A (en) | 2023-10-31 | 2023-10-31 | Face image quality evaluation method, device, storage medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117372405A true CN117372405A (en) | 2024-01-09 |
Family
ID=89392643
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311444281.5A Pending CN117372405A (en) | 2023-10-31 | 2023-10-31 | Face image quality evaluation method, device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117372405A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107609493A (en) * | 2017-08-25 | 2018-01-19 | 广州视源电子科技股份有限公司 | Method and device for optimizing human face image quality evaluation model |
| US20190205620A1 (en) * | 2017-12-31 | 2019-07-04 | Altumview Systems Inc. | High-quality training data preparation for high-performance face recognition systems |
| CN111814620A (en) * | 2020-06-28 | 2020-10-23 | 浙江大华技术股份有限公司 | Face image quality evaluation model establishing method, optimization method, medium and device |
| CN111967381A (en) * | 2020-08-16 | 2020-11-20 | 云知声智能科技股份有限公司 | Face image quality grading and labeling method and device |
| CN112215822A (en) * | 2020-10-13 | 2021-01-12 | 北京中电兴发科技有限公司 | Face image quality evaluation method based on lightweight regression network |
| CN112686234A (en) * | 2021-03-22 | 2021-04-20 | 杭州魔点科技有限公司 | Face image quality evaluation method, electronic device and storage medium |
| CN113792682A (en) * | 2021-09-17 | 2021-12-14 | 平安科技（深圳）有限公司 | Human face quality evaluation method, device, equipment and medium based on human face image |
-
2023
- 2023-10-31 CN CN202311444281.5A patent/CN117372405A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107609493A (en) * | 2017-08-25 | 2018-01-19 | 广州视源电子科技股份有限公司 | Method and device for optimizing human face image quality evaluation model |
| US20190205620A1 (en) * | 2017-12-31 | 2019-07-04 | Altumview Systems Inc. | High-quality training data preparation for high-performance face recognition systems |
| CN111814620A (en) * | 2020-06-28 | 2020-10-23 | 浙江大华技术股份有限公司 | Face image quality evaluation model establishing method, optimization method, medium and device |
| CN111967381A (en) * | 2020-08-16 | 2020-11-20 | 云知声智能科技股份有限公司 | Face image quality grading and labeling method and device |
| CN112215822A (en) * | 2020-10-13 | 2021-01-12 | 北京中电兴发科技有限公司 | Face image quality evaluation method based on lightweight regression network |
| CN112686234A (en) * | 2021-03-22 | 2021-04-20 | 杭州魔点科技有限公司 | Face image quality evaluation method, electronic device and storage medium |
| CN113792682A (en) * | 2021-09-17 | 2021-12-14 | 平安科技（深圳）有限公司 | Human face quality evaluation method, device, equipment and medium based on human face image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11610384B2 (en) | Zero-shot object detection | |
| WO2021212682A1 (en) | Knowledge extraction method, apparatus, electronic device, and storage medium | |
| CN112541122A (en) | Recommendation model training method and device, electronic equipment and storage medium | |
| CN113378970B (en) | Sentence similarity detection method and device, electronic equipment and storage medium | |
| CN113435499B (en) | Label classification method, device, electronic equipment and storage medium | |
| CN115546488B (en) | Information segmentation method, information extraction method and training method of information segmentation model | |
| CN113963186A (en) | Training method of target detection model, target detection method and related device | |
| CN111950279A (en) | Entity relationship processing method, device, equipment and computer readable storage medium | |
| CN114267064A (en) | Face recognition method and device, electronic equipment and storage medium | |
| CN112308802A (en) | Image analysis method and system based on big data | |
| CN113743721A (en) | Marketing strategy generation method and device, computer equipment and storage medium | |
| CN115221276A (en) | Chinese image-text retrieval model training method, device, equipment and medium based on CLIP | |
| CN114021582A (en) | Spoken language understanding method, device, equipment and storage medium combined with voice information | |
| CN116701574A (en) | Text semantic similarity calculation method, device, equipment and storage medium | |
| CN111738009B (en) | Entity word label generation method, entity word label generation device, computer equipment and readable storage medium | |
| CN109657127B (en) | Answer obtaining method, device, server and storage medium | |
| CN117390213A (en) | Training method of image-text retrieval model based on OSCAR and method for realizing image-text retrieval | |
| Nguyen-Tat et al. | Automating attendance management in human resources: A design science approach using computer vision and facial recognition | |
| CN116863116A (en) | Image recognition method, device, equipment and medium based on artificial intelligence | |
| CN116578925A (en) | Behavior prediction method, device and storage medium based on feature images | |
| WO2023178798A1 (en) | Image classification method and apparatus, and device and medium | |
| CN116187341A (en) | Semantic recognition method and device | |
| CN117372405A (en) | Face image quality evaluation method, device, storage medium and equipment | |
| CN114548114B (en) | Text emotion recognition method, device, equipment and storage medium | |
| CN115205758A (en) | Intelligent conversion method and device based on video and text, electronic equipment and 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 |