CN110796108B - Method, device and equipment for detecting face quality and storage medium - Google Patents
Method, device and equipment for detecting face quality and storage medium Download PDFInfo
- Publication number
- CN110796108B CN110796108B CN201911065479.6A CN201911065479A CN110796108B CN 110796108 B CN110796108 B CN 110796108B CN 201911065479 A CN201911065479 A CN 201911065479A CN 110796108 B CN110796108 B CN 110796108B
- Authority
- CN
- China
- Prior art keywords
- face
- image
- quality detection
- module
- detection model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
Abstract
The embodiment of the invention discloses a method, a device, equipment and a storage medium for detecting face quality. Wherein, the method comprises the following steps: acquiring a target face image to be processed; and taking the target face image as the input of a face quality detection model, and obtaining the image definition output by the face quality detection model and the face attitude value in the target face image as the face quality. According to the embodiment of the invention, the target face image to be processed is obtained and input into the face quality detection model, and the output image definition value and the face attitude value are obtained, so that the judgment on the face image quality is obtained, and the accuracy of the face quality detection in the video is improved.
Description
Technical Field
The embodiment of the invention relates to an artificial intelligence technology, in particular to a method, a device, equipment and a storage medium for detecting face quality.
Background
In recent years, in the field of biometric identification, the face quality detection technology is more and more concerned by research and development personnel in the industry. The method is widely applied to the fields of banks, electronic commerce and the like. Meanwhile, as video acquisition in public places is more and more, manual face detection is more and more difficult, and the face quality detection technology of computers is becoming a trend in video detection at present.
However, the face quality detection is a more complex system, and the faces of the same person in a video can get different scores in a recognition system, and sometimes even can be recognized wrongly. Therefore, it is very important for the recognition accuracy to select an optimal human face image in the video.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for detecting the quality of a human face, which are used for acquiring the definition value and the face posture value of a human face image and improving the precision of human face quality detection.
In a first aspect, an embodiment of the present invention provides a face quality detection method, where the method includes:
acquiring a target face image to be processed;
and taking the target face image as the input of a face quality detection model, and obtaining the image definition output by the face quality detection model and the face attitude value in the target face image as the face quality.
Optionally, the network structure of the face quality detection model has a definition output layer and a face pose output layer; the face pose output layer comprises at least one of: and the human face pitch angle, the human face yaw angle and the human face roll angle.
Optionally, after obtaining the image sharpness output by the face quality detection model and the face pose value in the target face image, the method includes:
and correcting the image definition according to the face attitude value in the target face image to obtain new image definition.
Optionally, the taking the target face image as an input of a face quality detection model to obtain an image definition output by the face quality detection model and a face pose value in the target face image as face quality includes:
performing downsampling processing on the target face image through a downsampling module in the face quality detection model to obtain a downsampled face image;
determining the face pose characteristics of the down-sampling face image through a first detection module in the face quality detection model;
determining the image definition characteristic through a second detection module in the human face quality detection model;
and outputting the image definition and the face pose value in the target face image according to the face pose characteristic and the image definition characteristic through a processing module in the face quality detection model.
In a second aspect, an embodiment of the present invention further provides a face quality detection apparatus, where the apparatus includes:
the target face image acquisition module is used for acquiring a target face image to be processed;
and the target face image input module is used for taking the target face image as the input of a face quality detection model to obtain the image definition output by the face quality detection model and the face pose value in the target face image as the face quality.
Optionally, the target face image input module further includes:
the output layer classification unit is used for providing a definition output layer and a human face posture output layer in a network structure of the human face quality detection model; the face pose output layer comprises at least one of: and the human face pitch angle, the human face yaw angle and the human face roll angle.
Optionally, the apparatus further comprises:
and the image definition correcting module is used for correcting the image definition according to the face attitude value in the target face image to obtain new image definition.
Optionally, the target face image input module is specifically configured to:
performing downsampling processing on the target face image through a downsampling module in the face quality detection model to obtain a downsampled face image;
determining the face pose characteristics of the down-sampling face image through a first detection module in the face quality detection model;
determining the image definition characteristic through a second detection module in the human face quality detection model;
and outputting the image definition and the face pose value in the target face image according to the face pose characteristic and the image definition characteristic through a processing module in the face quality detection model.
In a third aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the face quality detection method according to any embodiment of the present invention.
In a fourth aspect, embodiments of the present invention further provide a storage medium including computer-executable instructions, which when executed by a computer processor, are configured to perform the face quality detection method according to any of the embodiments of the present invention.
According to the embodiment of the invention, the target face image to be processed is acquired, the target face image to be processed is input into the face quality detection model, and the image definition and the face posture are simultaneously recognized to obtain the image quality of the target face image, so that the problem of low face quality detection precision in the prior art is solved, and the accuracy of face quality detection is improved.
Drawings
Fig. 1 is a schematic flow chart of a face quality detection method according to a first embodiment of the present invention;
fig. 2 is a schematic flow chart of a human face quality detection method in a second embodiment of the present invention;
fig. 3 is a block diagram of a structure of a face quality detection model in the second embodiment of the present invention;
FIG. 4 is a block diagram of a face quality detection model according to a second embodiment of the present invention;
fig. 5 is a block diagram of a face quality detection apparatus according to a third embodiment of the present invention;
fig. 6 is a schematic structural diagram of a computer device in the fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a schematic flow chart of a face quality detection method according to an embodiment of the present invention, which is applicable to face quality detection evaluation and can be executed by a face quality detection apparatus. As shown in fig. 1, the method specifically comprises the following steps:
and step 110, acquiring a target face image to be processed.
The target face image can be acquired by image acquisition equipment, and the image acquisition equipment can be equipment such as a camera. And sending the target face image to computer equipment, acquiring the target face image to be processed by the computer equipment, and detecting the target face image, wherein the computer equipment can be equipment such as a computer and the like. The target face image is a face image to be detected.
And step 120, taking the target face image as the input of the face quality detection model, and obtaining the image definition output by the face quality detection model and the face attitude value in the target face image as the face quality.
The face quality detection model is obtained based on Neural Network structure training, the Neural Network structure is not specifically limited in the present application, and for example, a CNN (Convolutional Neural Network) may be used to train the face quality detection model. The output layer of the neural network structure may be a fully connected layer.
Optionally, the network structure of the face quality detection model has a definition output layer and a face pose output layer; the face pose output layer comprises at least one of the following items: and the human face pitch angle, the human face yaw angle and the human face roll angle.
Specifically, the full connection layer of the neural network output is set as a definition output layer and a face posture output layer, the definition output layer is used for outputting the definition value of an image, and the face posture output layer is used for outputting the angle value of a face. The face angle output by the face posture output layer may include a face pitch angle, a face yaw angle and a face roll angle. Before training a face quality detection model, a large number of face images are collected as training samples, and definition values and face posture values are labeled for the sample face images. And continuously outputting the image definition and face posture value results detected by the sample face image in the training process, calculating a loss value between the output result and the labeled value, and successfully training the face quality detection model if the loss value between the output result and the labeled value is within a preset range after iterative training.
Specifically, loss values between the output image definition value, the face pitch angle, the face yaw angle, the face roll angle and the labeled image definition value, the face pitch angle, the face yaw angle and the face roll angle can be respectively determined, and the four loss values are summed to serve as the loss value of the model. For example, the preset range of the loss value is 0.1, the range of the labeled sharpness value can be 0 to 1, the range of the face pose value can be 0 ° to 90 °, and if the summation result of the four loss values is 0.05(0.05<0.1), the training of the face quality detection model is successful.
When the network structure of the human face quality detection model is trained, the image definition is considered, and the influence of the human face posture in the image on the human face image detection is considered. The human face posture is divided into the human face pitch angle, the human face yaw angle and the human face roll angle, so that when the human face image is detected, a picture with a large human face deflection angle is screened, the picture with high image definition and a positive human face posture is reserved, and the accuracy of human face quality detection is improved.
Optionally, the image sharpness is modified according to the face pose value in the target face image, so as to obtain a new image sharpness.
Specifically, the face pose value and the definition value output by the face quality detection model can be weighted and summed to obtain a new image definition value. For example, the original image sharpness is weighted by a, the face pitch angle is weighted by B, the face yaw angle is weighted by C, and the face roll angle is weighted by D. At the output junctionIf the image definition is 7, the face pitch angle is 30 degrees, the face yaw angle is 40 degrees, and the face roll angle is 20 degrees, the final new image definition can be calculated
The final new image definition is obtained by determining the face posture value and combining the face posture value with the image definition value, so that errors caused by different face postures in face quality detection are avoided, and the accuracy of face quality detection is improved.
According to the technical scheme, the target face image to be processed is obtained, and the target face image is input into the face quality detection model, so that the image definition and the face pose value of the target face image are obtained, and the image with high image definition and high face pose value is convenient to retain during face quality detection. The problem of among the prior art to face quality detection accuracy low is solved, reduce the gesture of people face, camera formation of image etc. multiple reasons and to face quality detection cause the influence, improved the precision of face quality detection.
Example two
Fig. 2 is a schematic flow chart of a face quality detection method according to a second embodiment of the present invention, and the present embodiment is further optimized based on the above embodiments. As shown in fig. 2, the method specifically includes the following steps:
and S210, acquiring a target face image to be processed.
S220, the target face image is used as the input of the face quality detection model, and the down-sampling processing is carried out on the target face image through a down-sampling module in the face quality detection model, so that the down-sampling face image is obtained.
The acquired target face image is input into a face quality detection model, and an output result is obtained through the action of each module in the face quality detection model. Fig. 3 is a block diagram of a structure of a face quality detection model according to a second embodiment of the present invention, and as shown in fig. 3, a down-sampling module 301 is connected to a first detection module 302 and a second detection module 303 and is used for performing down-sampling processing on an image. In the trained face quality detection model, the target face image is processed by a downsampling module 301 to obtain a downsampled face image. The downsampling processing is carried out on the target face image, the pooling technology is adopted for realizing, the dimensionality of the features is reduced on the basis of keeping effective information, the image is kept not to be deformed, and the excessive occupation of the image on a memory or a video memory is reduced.
And S230, determining the face pose characteristics of the down-sampled face image through a first detection module in the face quality detection model.
The first detection module 302 is connected to the down-sampling module 301 and the processing module 304, and is configured to perform feature extraction on the down-sampled face image to obtain a local feature. After the down-sampling processing of the down-sampling module 301, the target face image is processed by the first detection module 302 to extract local features, so as to obtain face pose features in the down-sampled face image. A plurality of first detection modules may be employed to perform local feature extraction to improve the accuracy of feature extraction.
And S240, determining the image definition characteristic through a second detection module in the face quality detection model.
Wherein the second detection module 303 is connected to the down-sampling module 301 and the processing module 304, and is configured to extract the local features while preserving the global features. The second detection module 303 receives the down-sampling face image sent by the down-sampling module 301, and performs overall feature extraction on the down-sampling face image to obtain the image definition feature of the down-sampling face image. A plurality of second detection modules may be used to process images at different feature extraction stages, as shown in fig. 4, where fig. 4 is a structural block diagram of a face quality detection model in the second embodiment of the present invention. In fig. 4, a plurality of first detection modules are connected, and a next-stage first detection module performs further feature extraction on an image after feature extraction of a previous-stage first detection module. And a plurality of second detection modules are connected with the down-sampling module or the upper-stage first detection module, and are used for extracting the overall features of the picture after the upper-stage features are extracted, so that accurate local features and overall features are finally obtained, and the features of the overall picture are retained while the local features are extracted.
And S250, outputting the image definition and the face pose value in the target face image according to the face pose feature and the image definition feature through a processing module in the face quality detection model.
The processing module 304 is connected to the first detection module 302 and the second detection module 303, and configured to receive the face pose feature of the target face image of the first detection module 302 and the image sharpness feature of the second detection module 303, and output an image sharpness and a face pose value in the target face image.
The embodiment of the invention obtains a target face image to be processed, performs down-sampling processing on the face image through a down-sampling module in a face quality detection model, and transmits the down-sampling image to a first detection module and a second detection module. The local features of the down-sampling image are obtained through the first detection module, and the overall features of the down-sampling image are obtained through the second detection module. And finally, obtaining the image definition and the face posture value of the face image through a processing module. The method and the device have the advantages that the overall characteristics of the image are kept while the local characteristics are extracted, the phenomenon that the overall characteristics act on the whole face image when the face quality is evaluated after the local characteristics are extracted is avoided, and the accuracy of the evaluation on the face quality is effectively improved.
EXAMPLE III
Fig. 5 is a block diagram of a face quality detection apparatus according to a third embodiment of the present invention, which is capable of executing a face quality detection method according to any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method. As shown in fig. 5, the apparatus specifically includes:
a target face image obtaining module 501, configured to obtain a target face image to be processed;
and a target face image input module 502, configured to use the target face image as an input of the face quality detection model, and obtain the image sharpness output by the face quality detection model and a face pose value in the target face image as face quality.
Optionally, the target face image input module 502 further includes:
the output layer classification unit is used for providing a definition output layer and a human face posture output layer in a network structure of the human face quality detection model; the face pose output layer comprises at least one of the following items: and the human face pitch angle, the human face yaw angle and the human face roll angle.
Optionally, the apparatus further comprises:
and the image definition correcting module is used for correcting the image definition according to the face attitude value in the target face image to obtain new image definition.
Optionally, the target face image input module 502 is specifically configured to:
the method comprises the steps that a down-sampling module in a face quality detection model is used for carrying out down-sampling processing on a target face image to obtain a down-sampled face image;
determining the face pose characteristics of the down-sampled face image through a first detection module in a face quality detection model;
determining the image definition characteristic through a second detection module in the face quality detection model;
and outputting the image definition and a face pose value in a target face image according to the face pose characteristic and the image definition characteristic through a processing module in the face quality detection model.
According to the embodiment of the invention, the image definition and the face posture value of the target face image are obtained by acquiring the target face image to be processed and inputting the target face image into the face quality detection model, so that the problem of low face quality detection accuracy in the prior art is solved, the influence of multiple reasons such as the face posture, camera imaging and the like on the identification is reduced, and the face quality detection accuracy is improved.
Example four
Fig. 6 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. FIG. 6 illustrates a block diagram of an exemplary computer device 600 suitable for use in implementing embodiments of the invention. The computer device 600 shown in fig. 6 is only an example and should not bring any limitations to the function and scope of use of the embodiments of the present invention.
As shown in fig. 6, computer device 600 is in the form of a general purpose computing device. The components of computer device 600 may include, but are not limited to: one or more processors or processing units 601, a system memory 602, and a bus 603 that couples various system components including the system memory 602 and the processing unit 601.
The system memory 602 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)604 and/or cache memory 605. The computer device 600 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 606 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard drive"). Although not shown in FIG. 6, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 603 by one or more data media interfaces. Memory 602 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 608 having a set (at least one) of program modules 607 may be stored, for instance, in the memory 602, such program modules 607 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination of which may comprise an implementation of a network environment. The program modules 607 generally perform the functions and/or methods of the described embodiments of the invention.
The computer device 600 may also communicate with one or more external devices 609 (e.g., keyboard, pointing device, display 610, etc.), with one or more devices that enable a user to interact with the computer device 600, and/or with any devices (e.g., network card, modem, etc.) that enable the computer device 600 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 611. Moreover, the computer device 600 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) via the network adapter 612. As shown, a network adapter 612 communicates with the other modules of the computer device 600 via the bus 603. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the computer device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 601 executes various functional applications and data processing by running a program stored in the system memory 602, for example, implementing a method for detecting face quality provided by an embodiment of the present invention, including:
acquiring a target face image to be processed;
and taking the target face image as the input of the face quality detection model, and obtaining the image definition output by the face quality detection model and the face attitude value in the target face image as the face quality.
EXAMPLE five
The fifth embodiment of the present invention further provides a storage medium including computer-executable instructions, where a computer program is stored on the storage medium, and when the computer program is executed by a processor, the method for detecting human face quality provided by the fifth embodiment of the present invention is implemented, where the method includes:
acquiring a target face image to be processed;
and taking the target face image as the input of the face quality detection model, and obtaining the image definition output by the face quality detection model and the face attitude value in the target face image as the face quality.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, store, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or 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 computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (8)
1. A face quality detection method is characterized by comprising the following steps:
acquiring a target face image to be processed;
the target face image is used as the input of a face quality detection model, and the image definition output by the face quality detection model and the face posture value in the target face image are obtained and used as the face quality;
the step of taking the target face image as the input of a face quality detection model to obtain the image definition output by the face quality detection model and the face attitude value in the target face image as the face quality comprises the following steps:
performing downsampling processing on the target face image through a downsampling module in the face quality detection model to obtain a downsampled face image;
determining the face pose characteristics of the down-sampling face image through a first detection module in the face quality detection model;
determining the image definition characteristic through a second detection module in the human face quality detection model;
outputting image definition and a face pose value in the target face image according to the face pose characteristic and the image definition characteristic through a processing module in the face quality detection model;
the determining, by a first detection module in the face quality detection model, the face pose features of the downsampled face image includes:
through a plurality of first detection modules in the face quality detection model, the next-level first detection module further extracts the features of the image extracted by the previous-level first detection module, and determines the face pose features of the down-sampled face image;
the determining the image definition characteristics through a second detection module in the face quality detection model further comprises:
and adopting a plurality of second detection modules, wherein the input end of a first-stage second detection module is connected with the down-sampling module, the input ends of the other second detection modules at all stages are respectively connected with the output end of a first detection module at the upper stage, and the overall feature extraction is carried out on the picture subjected to feature extraction by the first detection module at the upper stage to obtain the image definition feature of the down-sampling face image.
2. The method according to claim 1, wherein the network structure of the face quality detection model has a definition output layer and a face pose output layer; the face pose output layer comprises at least one of: and the human face pitch angle, the human face yaw angle and the human face roll angle.
3. The method of claim 1, after obtaining the image sharpness output by the face quality detection model and the face pose value in the target face image, comprising:
and correcting the image definition according to the face attitude value in the target face image to obtain new image definition.
4. A face quality detection apparatus, comprising:
the target face image acquisition module is used for acquiring a target face image to be processed;
the target face image input module is used for taking the target face image as the input of a face quality detection model to obtain the image definition output by the face quality detection model and the face pose value in the target face image as the face quality;
the target face image input module is specifically configured to:
performing downsampling processing on the target face image through a downsampling module in the face quality detection model to obtain a downsampled face image;
determining the face pose characteristics of the down-sampling face image through a first detection module in the face quality detection model;
determining the image definition characteristic through a second detection module in the human face quality detection model;
outputting image definition and a face pose value in the target face image according to the face pose characteristic and the image definition characteristic through a processing module in the face quality detection model;
the determining, by a first detection module in the face quality detection model, the face pose features of the downsampled face image includes:
through a plurality of first detection modules in the face quality detection model, the next-level first detection module further extracts the features of the image extracted by the previous-level first detection module, and determines the face pose features of the down-sampled face image;
the determining the image definition characteristic through a second detection module in the face quality detection model further comprises:
and adopting a plurality of second detection modules, wherein the input end of a first-stage second detection module is connected with the down-sampling module, the input ends of the other second detection modules at all stages are respectively connected with the output end of a first detection module at the upper stage, and the overall feature extraction is carried out on the picture subjected to feature extraction by the first detection module at the upper stage to obtain the image definition feature of the down-sampling face image.
5. The apparatus of claim 4, wherein the target face image input module further comprises:
the output layer classification unit is used for providing a definition output layer and a human face posture output layer in a network structure of the human face quality detection model; the face pose output layer comprises at least one of: and the human face pitch angle, the human face yaw angle and the human face roll angle.
6. The apparatus of claim 4, further comprising:
and the image definition correcting module is used for correcting the image definition according to the face attitude value in the target face image to obtain new image definition.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the face quality detection method according to any one of claims 1 to 3 when executing the program.
8. A storage medium comprising computer-executable instructions for performing the method of face quality detection according to any one of claims 1-3 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911065479.6A CN110796108B (en) | 2019-11-04 | 2019-11-04 | Method, device and equipment for detecting face quality and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911065479.6A CN110796108B (en) | 2019-11-04 | 2019-11-04 | Method, device and equipment for detecting face quality and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110796108A CN110796108A (en) | 2020-02-14 |
| CN110796108B true CN110796108B (en) | 2022-05-17 |
Family
ID=69442513
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911065479.6A Active CN110796108B (en) | 2019-11-04 | 2019-11-04 | Method, device and equipment for detecting face quality and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110796108B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111797733A (en) * | 2020-06-22 | 2020-10-20 | 浙江大华技术股份有限公司 | Behavior recognition method, behavior recognition device, behavior recognition equipment and storage medium based on image |
| CN113705650B (en) * | 2021-08-20 | 2023-07-11 | 网易（杭州）网络有限公司 | Face picture set processing method, device, medium and computing equipment |
| CN116740777A (en) * | 2022-09-28 | 2023-09-12 | 荣耀终端有限公司 | Training method of face quality detection model and related equipment thereof |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8542879B1 (en) * | 2012-06-26 | 2013-09-24 | Google Inc. | Facial recognition |
| CN108230293A (en) * | 2017-05-31 | 2018-06-29 | 深圳市商汤科技有限公司 | Determine method and apparatus, electronic equipment and the computer storage media of quality of human face image |
| CN107977639B (en) * | 2017-12-11 | 2020-07-10 | 浙江捷尚视觉科技股份有限公司 | Face definition judgment method |
| CN109034013B (en) * | 2018-07-10 | 2023-06-13 | 腾讯科技（深圳）有限公司 | Face image recognition method, device and storage medium |
| CN110276277A (en) * | 2019-06-03 | 2019-09-24 | 罗普特科技集团股份有限公司 | Method and apparatus for detecting facial image |
-
2019
- 2019-11-04 CN CN201911065479.6A patent/CN110796108B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110796108A (en) | 2020-02-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858555B (en) | Image-based data processing method, device, equipment and readable storage medium | |
| US11321593B2 (en) | Method and apparatus for detecting object, method and apparatus for training neural network, and electronic device | |
| CN109558832B (en) | Human body posture detection method, device, equipment and storage medium | |
| CN108875522B (en) | Face clustering method, device and system and storage medium | |
| WO2018010657A1 (en) | Structured text detection method and system, and computing device | |
| CN110796108B (en) | Method, device and equipment for detecting face quality and storage medium | |
| CN110222703B (en) | Image contour recognition method, device, equipment and medium | |
| CN111400528B (en) | Image compression method, device, server and storage medium | |
| CN112149663A (en) | RPA and AI combined image character extraction method and device and electronic equipment | |
| CN111401309B (en) | CNN training and remote sensing image target identification method based on wavelet transformation | |
| CN113724135A (en) | Image splicing method, device, equipment and storage medium | |
| CN114445904A (en) | Iris segmentation method, apparatus, medium, and device based on full convolution neural network | |
| CN111444807A (en) | Target detection method, device, electronic equipment and computer readable medium | |
| CN111091182A (en) | Data processing method, electronic device and storage medium | |
| US11410016B2 (en) | Selective performance of deterministic computations for neural networks | |
| CN108460335B (en) | Video fine-granularity identification method and device, computer equipment and storage medium | |
| US20170364740A1 (en) | Signal processing | |
| CN112465050A (en) | Image template selection method, device, equipment and storage medium | |
| CN111753736A (en) | Human body posture recognition method, device, equipment and medium based on packet convolution | |
| WO2023109086A1 (en) | Character recognition method, apparatus and device, and storage medium | |
| EP4220552A1 (en) | Image processing method and system | |
| CN113780239B (en) | Iris recognition method, iris recognition device, electronic device and computer readable medium | |
| CN115049546A (en) | Sample data processing method and device, electronic equipment and storage medium | |
| CN114463858A (en) | Signature behavior identification method and system based on deep learning | |
| CN113971830A (en) | Face recognition method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |