WO2022160202A1

WO2022160202A1 - Method and apparatus for inspecting mask wearing, terminal device and readable storage medium

Info

Publication number: WO2022160202A1
Application number: PCT/CN2021/074221
Authority: WO
Inventors: 韩永刚; 郭之先; 黄凯明
Original assignee: 深圳市锐明技术股份有限公司
Priority date: 2021-01-28
Filing date: 2021-01-28
Publication date: 2022-08-04
Also published as: CN112912893A

Abstract

The present application discloses a method and apparatus for inspecting mask wearing, a terminal device and a readable storage medium. Said method comprises: acquiring an image to be recognized; processing said image to obtain a mask image comprising a face contour; and processing the mask image to obtain an inspection result in respect of whether a user corresponding to the face contour is wearing a mask in a standard way. According to the present invention, an image to be recognized is processed to obtain a mask image comprising a face contour, and the mask image is inspected by means of a mask wearing inspection network model to obtain the probability of whether a user wears a mask in a standard way, thereby determining an inspection result in respect of whether the user wears the mask in the standard way, reducing the amount of calculation, and improving the inspection efficiency and the precision of the inspection result.

Description

Detection method, device, terminal device and readable storage medium for wearing a mask

technical field

The present application relates to the technical field of image processing, and in particular to a detection method, device, terminal device and readable storage medium for wearing a mask.

Background technique

In the process of the spread of respiratory infectious diseases, wearing a mask is a very significant measure to prevent respiratory infectious diseases. Therefore, it has become an important task to detect whether people wear masks and whether to wear masks in a standardized way.

In real life, the related methods of detecting whether people wear masks in a standardized way require a lot of human resources or computing resources, the detection efficiency is low, and the accuracy of the detection results is not high.

technical problem

One of the purposes of the embodiments of the present application is to provide a detection method, device, terminal device and readable storage medium for wearing a mask, aiming to solve the method for detecting whether people wear masks in a standard manner, which requires a large amount of human resources or computing. resources, low detection efficiency and low accuracy of detection results.

technical solutions

In order to solve the above-mentioned technical problems, the technical solutions adopted in the embodiments of the present application are:

In a first aspect, a detection method for wearing a mask is provided, including:

Get the image to be recognized;

Process the image to be recognized to obtain a mask image containing the outline of the face;

The mask image is processed to obtain a detection result of whether the user corresponding to the face contour is wearing a mask in a standard manner.

In one embodiment, the described to-be-recognized image is processed to obtain a mask image containing the outline of a human face, including:

The to-be-recognized image is input into the face segmentation network model for processing to obtain a mask image containing the outline of the face.

In one embodiment, the process of processing the mask image to obtain a detection result of whether the user corresponding to the face profile is wearing a mask according to regulations includes:

The mask image is processed by the mask-wearing recognition network model to obtain the output result of the mask-wearing recognition network model;

According to the output result, the detection result of whether the user corresponding to the face contour is wearing a mask is determined.

In one embodiment, the output result includes a first probability value corresponding to the face contour that the user wears a mask according to regulations, a second probability value corresponding to the face contour that the user does not wear a mask according to regulations, and a second probability value corresponding to the face contour. the third probability value that the user corresponding to the face profile does not wear a mask;

The detection result of determining whether the user corresponding to the profile of the human face is wearing a mask according to the output result, including:

When it is detected that in the output result, the first probability value is greater than the second probability value and the third probability value, it is determined that the detection result is that the user is wearing a mask according to specification;

When it is detected that in the output result, the second probability value is greater than the first probability value and the third probability value, it is determined that the detection result is that the user does not wear a mask properly;

When it is detected that in the output result, the third probability value is greater than the first probability value and the second probability value, it is determined that the detection result is that the user does not wear a mask.

In one embodiment, the method further includes:

Acquiring a plurality of face image data; wherein, the face image data includes face image data for wearing a mask, face image data for not wearing a mask, and face image data for not wearing a mask;

Process the face image data according to the face segmentation network model to obtain corresponding mask image training data;

The convolutional neural network model is pre-trained according to the mask image training data to obtain the mask-wearing recognition network model.

In one embodiment, the method further includes:

Acquiring training image data; wherein, the training image data is image data comprising a human face;

The semantic segmentation model is pre-trained through the training image data to obtain the face segmentation network model.

In one embodiment, after the processing of the mask image to obtain a detection result of whether the user corresponding to the face contour is wearing a mask in a standard manner, the method further includes:

When it is detected that the detection result is that the user does not wear a mask in a standard manner or that the user does not wear a mask, face recognition is performed on the to-be-recognized image, and a face recognition result of the user is determined.

In a second aspect, a detection device for wearing a mask is provided, including:

a first acquisition module, used for acquiring the image to be recognized;

The image processing module is used to process the to-be-recognized image to obtain a mask image containing the outline of the face;

The detection module is configured to process the mask image to obtain a detection result of whether the user corresponding to the face contour is wearing a mask in a standard manner.

In a third aspect, a terminal device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the first method described above when the processor executes the computer program. The detection method of wearing a mask described in any one of the aspects.

In a fourth aspect, a computer-readable storage medium is provided, the computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the mask-wearing method according to any one of the above-mentioned first aspects is realized. Detection method.

A fifth aspect provides a computer program product that, when the computer program product runs on a terminal device, enables the terminal device to execute the method for detecting wearing a mask according to any one of the first aspects above.

beneficial effect

The beneficial effect of the detection method for wearing a mask provided by the embodiment of the present application is that: by processing the image to be recognized, a mask image containing the outline of a human face is obtained, and the mask image is detected by a mask-wearing detection network model to obtain whether the user is The probability of wearing a mask is standardized, so as to determine whether the user wears a mask in a standardized manner, which reduces the amount of calculation and improves the detection efficiency and the accuracy of the detection results.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that are used in the description of the embodiments or exemplary technologies. Obviously, the drawings in the following description are only for the present application. In some embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without any creative effort.

Fig. 1 is the schematic flow sheet of the detection method of wearing a mask provided by the embodiment of the present application;

2 is a schematic flowchart of step S103 of the detection method for wearing a mask provided by the embodiment of the present application;

3 is a schematic flowchart of step S1032 of the detection method for wearing a mask provided by the embodiment of the present application;

Fig. 4 is another schematic flow chart of the detection method of wearing a mask provided by the embodiment of the present application;

5 is a schematic structural diagram of a detection device for wearing a mask provided by an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a terminal device provided by an embodiment of the present application.

Embodiments of the present invention

In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present application.

The terms "first" and "second" are only used for the purpose of description, and should not be understood as indicating or implying relative importance or implying indicating the number of technical features. "Plurality" means two or more, unless expressly specifically limited otherwise.

In order to illustrate the technical solutions provided in the present application, the following detailed description is given in conjunction with the specific drawings and embodiments.

Some embodiments of the present application provide a detection method for wearing a mask, which can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, and notebook computers. The embodiments of the present application do not impose any restrictions on the specific types of terminal devices.

FIG. 1 shows a schematic flow chart of the detection method for wearing a mask provided by the present application. As an example and not a limitation, the method can be applied to the above-mentioned notebook computer.

S101. Acquire an image to be recognized.

In a specific application, the user is photographed by a preset camera, and the to-be-recognized image data including the user's face is obtained.

S102. Process the to-be-recognized image to obtain a mask image containing the outline of a human face.

In a specific application, a face segmentation network model is used to process a to-be-recognized image containing a human face, and a mask image containing the user's face contour output by the face segmentation network model is obtained.

S103: Process the mask image to obtain a detection result corresponding to the face contour of whether the user wears a mask in a standard manner.

In a specific application, the mask image containing the user's face contour is processed by the mask-wearing recognition network model, and the detection result of whether the user corresponding to the face contour output by the mask-wearing recognition network model is standard wearing a mask is obtained. In order to improve the detection accuracy, the detection results are set to include the probability values of the user wearing a mask, the user wearing a mask, and the user not wearing a mask. Among them, the user's standard wearing of a mask refers to the situation where the user wears a mask according to medical regulations, and the user's non-standard wearing of a mask refers to the user wearing a mask, but not covering important parts such as the mouth and nose in accordance with medical regulations.

In one embodiment, the step S102 includes:

In a specific application, the to-be-recognized image obtained by shooting is input into a face segmentation network model, and the to-be-recognized image is processed by the face segmentation network model to obtain a mask image containing the user's face contour. The face segmentation network model includes but is not limited to a semantic segmentation (semantic segmentation) network model.

In a specific application, the area of the face contour included in the mask image can be set according to actual needs. For example, the above-mentioned face contour may refer to the contour of the entire face area, or only include the contour of a part of the face area that is used to identify whether the user is wearing a mask properly (generally, the area that identifies whether the user is wearing a mask is under the eyes). face area).

As shown in FIG. 2, in one embodiment, the step S103 includes:

S1031, processing the mask image by wearing a mask recognition network model to obtain an output result of the mask wearing recognition network model;

S1032. Determine, according to the output result, a detection result of whether the user corresponding to the face contour is wearing a mask in a standard manner.

In the specific application, the mask map containing the face contour is processed through the mask-wearing recognition network model to obtain the probability value of whether the user outputted by the mask-wearing recognition network wears a mask and whether the mask is regulated. The detection result of whether the face contour corresponds to the standard wearing of the mask. Among them, the wearing mask recognition network model includes but is not limited to the convolutional neural network model (Convolutional Neural Network model). Networks, CNN).

In the present embodiment, the detection result of whether the user corresponding to the face contour is regulated wearing a mask is determined according to the output result, including:

Determine the maximum probability value in the output result of the mask-wearing recognition network model, and determine whether the user corresponding to the face contour is wearing a mask according to the maximum probability value.

In one embodiment, the output result includes a first probability value corresponding to the face contour that the user wears a mask according to regulations, a second probability value corresponding to the face contour that the user does not wear a mask according to regulations, and a second probability value corresponding to the face contour. The third probability value that the user corresponding to the face contour does not wear a mask.

In a specific application, the output result of the mask-wearing recognition network model includes a first probability value corresponding to the face contour that the user wears a mask according to regulations, a second probability value corresponding to the face contour that the user does not wear a mask according to regulations, and a face contour corresponding to the user wearing a mask. The third probability value of the user not wearing a mask corresponding to the contour. The sum of the first probability value, the second probability value and the third probability value is 1.

As shown in FIG. 3, in one embodiment, the step S1032 includes:

S10321. When it is detected that in the output result, the first probability value is greater than the second probability value and the third probability value, determine that the detection result is that the user is wearing a mask according to specification;

S10322. When detecting that the second probability value is greater than the first probability value and the third probability value in the output result, determine that the detection result is that the user does not wear a mask in a standard manner;

S10323. When it is detected that in the output result, the third probability value is greater than the first probability value and the second probability value, determine that the detection result is that the user does not wear a mask.

In a specific application, when it is detected that the output of the mask-wearing recognition network model, the first probability value is greater than the second probability value and the third probability value (that is, the first probability value is detected to be the largest), the detection result is determined to be the user Standardize wearing of masks; in the detected output results, when the second probability value is greater than the first probability value and the third probability value (that is, the second probability value is about to be detected to be the largest), it is determined that the test result is that the user does not wear masks properly; In the output result, when the third probability value is greater than the first probability value and the second probability value (that is, the third probability value is detected to be the largest), it is determined that the detection result is that the user does not wear a mask.

For example, when it is detected that the output result of the mask-wearing recognition network model is [0.1, 0.8, 0.1], it is determined that the detection result is that the user does not wear a mask properly.

In one embodiment, the method further includes:

In a specific application, a large amount of face image data is obtained, the face image data is processed according to the face segmentation network model, and the corresponding mask image training data containing the face contour is obtained. The neural network model is pre-trained to obtain a mask-wearing recognition network model, so that the mask-wearing recognition network model can process the input image, and obtain the corresponding first probability value of wearing a mask, the second probability value of non-standard wearing a mask, and The third probability value for not wearing a mask. Among them, the face image data includes the face image data of standard wearing masks, the face image data of non-standard wearing masks, and the face image data of not wearing masks.

In this embodiment, after processing the face image data according to the face segmentation network model and obtaining the corresponding mask image training data, the method includes: adding a corresponding mask image training data according to the type of each face image data labels to facilitate pre-training of convolutional neural network models based on face segmentation image data. For example, when processing the face image data that is regulated wearing masks according to the face segmentation network model, and obtaining the corresponding mask image training data, the mask image training data should be labeled as "regular wearing masks"; The face segmentation network model processes the face image data that does not wear masks in a standardized manner, and when obtaining the corresponding mask image training data, the mask image training data should be labeled as "non-standard wearing masks"; The model processes the face image data without a mask, and when the corresponding mask image training data is obtained, the mask image training data should be labeled "without a mask".

In one embodiment, pre-training the semantic segmentation network model includes: calculating the loss through a segmentation loss function (such as a segmentation loss function based on cross entropy), and performing gradient backpropagation on the loss through a gradient descent algorithm to update the computational semantics The weight parameters of each layer in the segmentation network model are obtained until the entire semantic segmentation network model converges, and the pre-trained face segmentation network model is obtained.

In one embodiment, the method further includes:

In a specific application, a large amount of image data containing faces is obtained as training image data, and the semantic segmentation network model is pre-trained through the above training image data to obtain a face segmentation network model, so that the face segmentation network model is used for input After processing the image data of , the mask image containing the outline of the face is output.

In one embodiment, it is set after pre-training the semantic segmentation network model, obtaining the face segmentation network model, and pre-training the convolutional neural network, and obtaining the mask-wearing recognition network model and the face segmentation network model. , graft the mask-wearing recognition network model to the face segmentation network model, and merge into one network model. It should be noted that the size of the output of the face-segmentation network model should be the same as the size of the input data of the mask-wearing recognition network model. . Among them, in the pre-training process, the loss function of the set face segmentation network model includes but is not limited to the segmentation loss function and the classification loss function, and the loss function of the mask-wearing recognition network model includes but is not limited to the classification loss function.

In one embodiment, it is set that the semantic segmentation network model and the convolutional neural network model are pre-integrated into a network model, and then the semantic segmentation network model in the model is pre-trained, and after the face segmentation network model is obtained, then The convolutional neural network model in the model is pre-trained to obtain the convolutional neural network model.

As shown in FIG. 4, in one embodiment, after the step S103, it further includes:

S104, when the detection result is that the user does not wear a mask according to regulations or the user does not wear a mask, perform face recognition on the to-be-recognized image, and determine a face recognition result of the user.

In specific applications, when it is detected that the user does not wear a mask in a standard manner or the user does not wear a mask, the face recognition algorithm is used to perform face recognition on the image to be recognized, and the face recognition result of the user in the image to be recognized is determined to facilitate notification. The user wears a mask according to regulations, and carries out corresponding follow-up treatment.

In this embodiment, a mask image containing the outline of a human face is obtained by processing the image to be recognized, and the mask image is detected by a mask-wearing detection network model to obtain the probability of whether the user wears a mask properly, so as to determine whether the user wears a mask properly The detection result is reduced, the calculation amount is reduced, and the detection efficiency and the detection result accuracy are improved.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Corresponding to the detection method for wearing a mask described in the above embodiment, FIG. 5 shows a structural block diagram of the detection device for wearing a mask provided by the embodiment of the present application. part.

In this embodiment, the detection device for wearing a mask includes: a processor, wherein the processor is used to execute the following program modules stored in the memory: a first acquisition module, used to acquire an image to be recognized; an image processing module, used to treat The identification image is processed to obtain a mask image containing the outline of the face; the detection module is used to process the mask image to obtain a detection result of whether the user corresponding to the face outline is wearing a mask in a standard manner.

5, the detection device 100 wearing a mask includes:

The first acquisition module 101 is used to acquire the image to be recognized;

The image processing module 102 is used for processing the image to be recognized to obtain a mask image containing the outline of the human face;

The detection module 103 is configured to process the mask image to obtain a detection result of whether the user corresponding to the face contour is wearing a mask in a standard manner.

In one embodiment, the image processing module 102 includes:

The first processing unit is configured to input the to-be-recognized image into a face segmentation network model for processing, and obtain a mask image including a face contour.

In one embodiment, the detection module 103 includes:

a second processing unit, configured to process the mask image through the mask-wearing recognition network model to obtain an output result of the mask-wearing recognition network model;

A determination unit, configured to determine, according to the output result, a detection result of whether the user corresponding to the face contour is wearing a mask in a standard manner.

In one embodiment, the determining unit includes:

a first detection subunit, configured to determine that the detection result is the user's standard wearing when it is detected that the first probability value is greater than the second probability value and the third probability value in the output result Face mask;

A second detection subunit, configured to determine that the detection result is that the user is not standardized when the second probability value is greater than the first probability value and the third probability value in the output result wear a mask;

A third detection sub-unit, configured to determine that the detection result is that the user is not wearing when the third probability value is greater than the first probability value and the second probability value in the output result Face mask.

In one embodiment, the detection device 100 for wearing a mask further includes:

The second acquisition module is used to acquire a plurality of face image data; wherein, the face image data includes face image data of standard wearing masks, face image data of non-standard wearing masks, and face image data of not wearing masks ;

a preprocessing module, configured to process the face image data according to the face segmentation network model to obtain corresponding mask image training data;

The first training module is used to pre-train the convolutional neural network model according to the mask image training data to obtain the mask-wearing recognition network model.

The third acquisition module is used for acquiring training image data; wherein, the training image data is image data including human faces;

The second training module is used for pre-training the semantic segmentation model through the training image data to obtain the face segmentation network model.

The face recognition module is configured to perform face recognition on the to-be-recognized image and determine the user's face recognition result when the detection result is that the user does not wear a mask in a standard manner or the user does not wear a mask.

It should be noted that the information exchange, execution process and other contents between the above-mentioned devices/units are based on the same concept as the method embodiments of the present application. For specific functions and technical effects, please refer to the method embodiments section. It is not repeated here.

FIG. 6 is a schematic structural diagram of a terminal device provided by an embodiment of the present application. As shown in FIG. 6 , the terminal device 6 in this embodiment includes: at least one processor 60 (only one is shown in FIG. 6 ), a processor, a memory 61 , and a processor stored in the memory 61 and can be processed in the at least one processor The computer program 62 running on the processor 60, when the processor 60 executes the computer program 62, implements the steps in any of the above-mentioned embodiments of the detection method for wearing a mask.

The terminal device 6 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The terminal device may include, but is not limited to, a processor 60 and a memory 61 . Those skilled in the art can understand that FIG. 6 is only an example of the terminal device 6, and does not constitute a limitation on the terminal device 6, and may include more or less components than the one shown, or combine some components, or different components , for example, may also include input and output devices, network access devices, and the like.

The so-called processor 60 may be a central processing unit (Central Processing Unit, CPU), and the processor 60 may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSP), application specific integrated circuits (Application Specific Integrated Circuits) Integrated Circuit, ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 61 may be an internal storage unit of the terminal device 6 in some embodiments, such as a hard disk or a memory of the terminal device 6 . In other embodiments, the memory 61 may also be an external storage device of the terminal device 6, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital Card (Secure Digital, SD), Flash Card (Flash Card), etc. The memory 61 may also include both an internal storage unit of the terminal device 6 and an external storage device. The memory 61 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as program codes of the computer program. The memory 61 can also be used to temporarily store data that has been output or will be output.

Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned functions can be allocated to different functional units, Module completion, that is, dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit, and the above-mentioned integrated units may adopt hardware. It can also be realized in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing from each other, and are not used to limit the protection scope of the present application. For the specific working processes of the units and modules in the above-mentioned system, reference may be made to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

Embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps in the foregoing method embodiments can be implemented.

The embodiments of the present application provide a computer program product, when the computer program product runs on a mobile terminal, the steps in the foregoing method embodiments can be implemented when the mobile terminal executes the computer program product.

The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can be implemented by a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium, and the computer program When executed by the processor, the steps of the above-mentioned various method embodiments may be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, and the like. The computer-readable medium may include at least: any entity or device capable of carrying computer program codes to the photographing device/terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signals, telecommunication signals, and software distribution media. For example, U disk, mobile hard disk, disk or CD, etc. In some jurisdictions, under legislation and patent practice, computer readable media may not be electrical carrier signals and telecommunications signals.

In the foregoing embodiments, the description of each embodiment has its own emphasis. For parts that are not described or described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

In the embodiments provided in this application, it should be understood that the disclosed apparatus/network device and method may be implemented in other manners. For example, the apparatus/network device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units. Or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

The above are only optional embodiments of the present application, and are not intended to limit the present application. Various modifications and variations of this application are possible for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the scope of the claims of this application.

Claims

A detection method for wearing a mask, comprising:

Get the image to be recognized;

Process the image to be recognized to obtain a mask image containing the outline of the face;

The mask image is processed to obtain a detection result of whether the user corresponding to the face contour is wearing a mask in a standard manner.
The detection method of wearing a mask as claimed in claim 1, wherein the described image to be recognized is processed to obtain a mask image comprising the outline of a human face, comprising:

The to-be-recognized image is input into the face segmentation network model for processing to obtain a mask image containing the outline of the face.
The detection method of wearing a mask as claimed in claim 1, wherein the processing of the mask image to obtain a detection result of whether the user corresponding to the face profile is standard wearing a mask, comprising:

The mask image is processed by the mask-wearing recognition network model to obtain the output result of the mask-wearing recognition network model;

According to the output result, the detection result of whether the user corresponding to the face contour is wearing a mask is determined.
The method for detecting wearing a mask according to claim 3, wherein the output result includes a first probability value of a user's standard wearing a mask corresponding to the face contour, and a user's unidentified mask corresponding to the face contour. Standardize the second probability value of wearing a mask and the third probability value of the user not wearing a mask corresponding to the face profile;

The detection result of determining whether the user corresponding to the profile of the human face is wearing a mask according to the output result, including:

When it is detected that in the output result, the first probability value is greater than the second probability value and the third probability value, it is determined that the detection result is that the user is wearing a mask according to specification;

When it is detected that in the output result, the second probability value is greater than the first probability value and the third probability value, it is determined that the detection result is that the user does not wear a mask properly;

When it is detected that in the output result, the third probability value is greater than the first probability value and the second probability value, it is determined that the detection result is that the user does not wear a mask.
The detection method of wearing a mask as claimed in any one of claims 1 to 4, wherein the method further comprises:

Acquiring a plurality of face image data; wherein, the face image data includes face image data for wearing a mask, face image data for not wearing a mask, and face image data for not wearing a mask;

Process the face image data according to the face segmentation network model to obtain corresponding mask image training data;

The convolutional neural network model is pre-trained according to the mask image training data to obtain the mask-wearing recognition network model.
The detection method of wearing a mask as claimed in any one of claims 1 to 4, wherein the method further comprises:

Acquiring training image data; wherein, the training image data is image data comprising a human face;

The semantic segmentation model is pre-trained through the training image data to obtain the face segmentation network model.
The detection method for wearing a mask according to any one of claims 1 to 4, wherein the mask image is processed to obtain a detection result of whether the user corresponding to the face contour is wearing a mask in a standard way After that, also include:

When it is detected that the detection result is that the user does not wear a mask in a standard manner or that the user does not wear a mask, face recognition is performed on the to-be-recognized image, and a face recognition result of the user is determined.
A detection device for wearing a mask, comprising:

a first acquisition module, used for acquiring the image to be recognized;

The image processing module is used to process the to-be-recognized image to obtain a mask image containing the outline of the face;

The detection module is configured to process the mask image to obtain a detection result of whether the user corresponding to the face contour is wearing a mask in a standard manner.
The detection device for wearing a mask as claimed in claim 8, wherein the image processing module comprises:

The first processing unit is configured to input the to-be-recognized image into a face segmentation network model for processing, and obtain a mask image containing the outline of the face.
The detection device for wearing a mask as claimed in claim 8, wherein the detection module comprises:

a second processing unit, configured to process the mask image by using a mask-wearing recognition network model to obtain an output result of the mask-wearing recognition network model;

A determination unit, configured to determine a detection result of whether the user corresponding to the face contour is wearing a mask in a standard manner according to the output result.
The detection device for wearing a mask according to claim 10, wherein the output result includes a first probability value of the user's standard wearing a mask corresponding to the face contour, and a user's unidentified mask corresponding to the face contour. Standardize the second probability value of wearing a mask and the third probability value of the user not wearing a mask corresponding to the face profile;

The determining unit includes:

a first detection subunit, configured to determine that the detection result is the user's standard wearing when it is detected that the first probability value is greater than the second probability value and the third probability value in the output result Face mask;

A second detection subunit, configured to determine that the detection result is that the user is not standardized when the second probability value is greater than the first probability value and the third probability value in the output result wear a mask;

A third detection sub-unit, configured to determine that the detection result is that the user is not wearing when the third probability value is greater than the first probability value and the second probability value in the output result Face mask.
The detection device for wearing a mask as claimed in claim 8, wherein the device further comprises:

The second acquisition module is used to acquire a plurality of face image data; wherein, the face image data includes face image data of standard wearing masks, face image data of non-standard wearing masks, and face image data of not wearing masks ;

a preprocessing module, configured to process the face image data according to the face segmentation network model to obtain corresponding mask image training data;

The first training module is used to pre-train the convolutional neural network model according to the mask image training data to obtain the mask-wearing recognition network model.
The detection device for wearing a mask as claimed in claim 8, wherein the device further comprises:

The third acquisition module is used to acquire training image data; wherein, the training image data is image data including human faces;

The second training module is used for pre-training the semantic segmentation model through the training image data to obtain the face segmentation network model.
A terminal device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, when the processor executes the computer program, the process according to claim 1 to 7. The method of any one.
A computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.