CN113688785A - Multi-supervision-based face recognition method and device, computer equipment and storage medium - Google Patents
Multi-supervision-based face recognition method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113688785A CN113688785A CN202111060922.8A CN202111060922A CN113688785A CN 113688785 A CN113688785 A CN 113688785A CN 202111060922 A CN202111060922 A CN 202111060922A CN 113688785 A CN113688785 A CN 113688785A
- Authority
- CN
- China
- Prior art keywords
- face
- loss
- training data
- mask
- training
- 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 42
- 238000012549 training Methods 0.000 claims abstract description 95
- 238000012545 processing Methods 0.000 claims abstract description 28
- 238000013528 artificial neural network Methods 0.000 claims abstract description 23
- 230000003190 augmentative effect Effects 0.000 claims abstract description 18
- 230000006870 function Effects 0.000 claims description 40
- 238000004590 computer program Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000013434 data augmentation Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 230000003416 augmentation Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 14
- 238000010586 diagram Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a face recognition method, a face recognition device, computer equipment and a storage medium based on multi-supervision, wherein the method comprises the following steps: initializing a neural network to obtain a training data set; processing the training data set to obtain augmented training data; inputting the expanded training data into a neural network in batches, and processing to obtain the output of a face ID classification layer and the output of a mask classification layer; calculating to obtain a value of a first loss function, and marking as loss 1; calculating to obtain the value of a second loss function, and marking as loss 2; weighting loss1 and loss2 to obtain the final loss; and training the neural network until loss converges or reaches the preset iteration times, and then extracting the feature model to serve as a final face recognition model. The invention increases the recognition effect of the face of the mask on the basis of not losing the recognition effect of the common face, and can not increase the storage cost and the time cost when training big data.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to a face recognition method, a face recognition device, computer equipment and a storage medium based on multi-supervision.
Background
The existing face recognition method is unsatisfactory in the recognition effect of the face wearing the mask, and the accuracy of the recognition effect of the face wearing the mask is particularly required in many occasions. In addition, at present, two parts of data are required to be provided for identifying the face of the wearing mask, namely normal data and corresponding wearing mask data, certain requirements are required for storage capacity in a big data training process, the training speed is low, and the requirements cannot be met.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a face recognition method and device based on multi-supervision, computer equipment and a storage medium.
In order to solve the technical problems, the invention adopts the following technical scheme:
the face recognition method based on multi-supervision comprises the following steps:
initializing a neural network to obtain a training data set;
on-line data augmentation processing is adopted for the training data set, and augmented training data are obtained;
inputting the expanded training data into a neural network in batches, and processing to obtain the output of a face ID classification layer and the output of a mask classification layer;
calculating to obtain a first loss function value according to the extended training data and the output of the mask classification layer, and recording as loss 1; calculating to obtain a second loss function value according to the extended training data and the output of the face ID classification layer, and recording as loss 2;
weighting loss1 and loss2 to obtain the final loss;
and training the neural network according to the final loss until the loss converges or reaches the preset iteration times, and then extracting a feature model from the training result to be used as a final face recognition model.
The further technical scheme is as follows: the training data set comprises training pictures and corresponding labels; wherein the label includes whether to wear a mask and a face ID.
The further technical scheme is as follows: the augmented training data comprises: mask labels and face ID labels; and in the step of loss2, the value of the first loss function is obtained through calculation according to the output of the mask label and the mask classification layer, and the value of the second loss function is obtained through calculation according to the output of the face ID label and the face classification layer.
The further technical scheme is as follows: in the step of weighting the loss1 and the loss2 to obtain the final loss, the loss is 1 a1+ loss2 a2, wherein a1 and a2 are both weights.
A multi-supervision-based face recognition device comprises: the system comprises an initialization acquisition unit, an augmentation processing unit, an input processing unit, a calculation unit, a weighting unit and a training extraction unit;
the initialization acquisition unit is used for initializing a neural network and acquiring a training data set;
the augmentation processing unit is used for performing online data augmentation processing on the training data set to obtain augmented training data;
the input processing unit is used for inputting the augmented training data into the neural network in batches, and obtaining the output of the face ID classification layer and the output of the mask classification layer after processing;
the calculating unit is used for calculating and obtaining a first loss function value according to the expanded training data and the output of the mask classification layer, and the first loss function value is recorded as loss 1; calculating to obtain a second loss function value according to the extended training data and the output of the face ID classification layer, and recording as loss 2;
the weighting unit is used for weighting loss1 and loss2 to obtain final loss;
and the training extraction unit is used for training the neural network according to the final loss until the loss converges or reaches the preset iteration times, and then extracting a characteristic model from the training result to be used as a final face recognition model.
The further technical scheme is as follows: the training data set comprises training pictures and corresponding labels; wherein the label includes whether to wear a mask and a face ID.
The further technical scheme is as follows: the augmented training data comprises: mask labels and face ID labels; and in the calculation unit, a first loss function value is calculated according to the output of the mask label and the mask classification layer, and a second loss function value is calculated according to the output of the face ID label and the face ID classification layer.
The further technical scheme is as follows: in the weighting unit, loss1 a1+ loss2 a2, wherein a1 and a2 are both weights.
A computer device comprising a memory having a computer program stored thereon and a processor that, when executed, implements a multi-supervised based face recognition method as described above.
A storage medium storing a computer program comprising program instructions which, when executed by a processor, implement a multi-supervised based face recognition method as described above.
Compared with the prior art, the invention has the beneficial effects that: through on traditional face identification method, another supervision task has been introduced, aim at forcing the face identification model to notice more extra information, thereby it is abundanter, diversified face characteristics, help promoting face identification's accuracy and robustness, on the basis of not losing ordinary face identification effect, the discernment effect of wearing gauze mask face has been showing to have increased, obtain gauze mask data and corresponding label in the training process simultaneously, and can not increase storage cost and training time cost when training the big data, the discernment effect of gauze mask face has been improved.
The invention is further described below with reference to the accompanying drawings and specific embodiments.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a multi-supervision-based face recognition method according to an embodiment of the present invention;
fig. 2 is a schematic view of an application scene of the mask extension according to the embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a neural network according to an embodiment of the present invention;
FIG. 4 is a schematic block diagram of a multi-supervised based face recognition apparatus according to an embodiment of the present invention;
FIG. 5 is a schematic block diagram of a computer device provided by an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Referring to the specific embodiments shown in fig. 1 to 5, wherein, referring to fig. 1 to 3, the present invention discloses a face recognition method based on multiple supervision, which includes the following steps:
s1, initializing a neural network, and acquiring a training data set;
wherein initializing the neural network comprises: a feature extraction model, a face ID classification layer and a mask classification layer. The feature extraction model may be, but is not limited to, a convolutional neural network. The face ID classification layer and the mask classification layer may be, but are not limited to, a full connection layer.
Wherein the training data set comprises training pictures and corresponding labels; wherein the label includes whether to wear a mask and a face ID.
S2, performing online data augmentation processing on the training data set to obtain augmented training data;
the method comprises the steps of firstly, automatically labeling the existing data according to the existing model for judging whether a user wears the mask or not to obtain the mask label of the original data. However, only a small part of the data of the mask wearing label in the training data is obtained, and a model with a good effect on the mask face cannot be obtained by training with the original data. The method adopts an online data augmentation mode, obtains the mask label of the randomly augmented data at the same time, and updates the original label. The online data augmentation mode of the mask is that a random cutout simulates the mask, the center of the mask is clicked at (56,112), the width and the height of the mask are randomly sampled within [56,112], as shown in fig. 2, a small frame represents the minimum mask range selected randomly, a large frame represents the maximum mask range selected randomly, only original data need to be stored, mask data can be obtained according to online data augmentation, and meanwhile, a mask label is obtained, wherein the mask label is: the data label of the wearing mask is 1, and the data label of the non-wearing mask is 0.
S3, inputting the augmented training data into a neural network in batches, and processing to obtain the output of a face ID classification layer and the output of a mask classification layer;
s4, calculating to obtain a first loss function value according to the augmented training data and the output of the mask classification layer, and recording as loss 1; calculating to obtain a second loss function value according to the extended training data and the output of the face ID classification layer, and recording as loss 2;
as shown in fig. 3, the augmented training data includes: mask labels and face ID labels; and in the step of loss2, the value of the first loss function is obtained through calculation according to the output of the mask label and the mask classification layer, and the value of the second loss function is obtained through calculation according to the output of the face ID label and the face classification layer. The first loss function selects the cross entropy loss function.
Wherein, the cross entropy loss function is in a dichotomy condition, the final result to be predicted of the model has only two conditions, the probability obtained by prediction of each category is p and 1-p, and the expression at this time is:
wherein, yiA label representing a sample i, the positive class being 1 and the negative class being 0; p is a radical ofiIndicating the probability that sample i is predicted as a positive class.
Wherein the second loss function may be a classification function, such as: a softmax Loss function (normalization function), various types of softmax Loss functions with Margin (interval), and other types of target functions, such as a face recognition algorithm, an ArcFace Loss (Additive Angular interval Loss function) corresponding to the ArcFace algorithm, and the like, may also be used.
S5, weighting the loss1 and the loss2 to obtain the final loss;
wherein, loss1 a1+ loss2 a2, wherein a1 and a2 are both weights.
The importance degree of each loss function to model training can be controlled by adjusting the weight (a1, a2) so as to obtain a face recognition model which meets the actual requirement; for different training requirements and application requirements, the importance degree of each loss function is different, so the weight is specifically analyzed according to specific situations. Typically, during the training process, the weight is set to 1.
And S6, training the neural network according to the final loss until the loss converges or reaches the preset iteration times, and then extracting a feature model from the training result to be used as a final face recognition model.
The preset iteration times are set according to needs, and the range is not limited.
In S6, the feature model with the best effect is selected from the training results and extracted to serve as the final face recognition model, so that the face recognition effect of the mask can be improved while the normal face recognition effect is ensured.
The face recognition model obtained by training according to the method is applied to a face panel machine, and the specific flow is as follows:
1. obtaining snapshot image data with a human face according to an image sensor;
2. performing key point detection on the obtained picture according to the face detection model, and performing affine transformation on a face region by adopting a face alignment method to obtain face image data;
3. inputting the obtained face image data into a face recognition model obtained by training by the method to obtain the feature representation of the face image;
4. comparing the obtained face features with face images in a stored registered face image library to obtain similarity scores;
5. and comparing the obtained similarity score with a threshold value obtained through tests to obtain the ID of the snapshot image data.
The invention adopts a multi-supervision method to train the face recognition model, the face recognition model obtained after training effectively improves the face recognition accuracy of the mask under the condition of ensuring the normal face recognition accuracy, and an online data augmentation method is adopted in the training process, so that mask data are conveniently and simply generated, and no additional data storage requirement exists. Through on traditional face identification method, another supervision task has been introduced, aim at forcing the face identification model to notice more extra information, thereby it is abundanter, diversified face characteristics, help promoting face identification's accuracy and robustness, on the basis of not losing ordinary face identification effect, the discernment effect of wearing gauze mask face has been showing to have increased, obtain gauze mask data and corresponding label in the training process simultaneously, and can not increase storage cost and training time cost when training the big data, the discernment effect of gauze mask face has been improved.
Referring to fig. 4, the present invention also discloses a face recognition device based on multiple surveillance, including: an initialization acquisition unit 10, an augmentation processing unit 20, an input processing unit 30, a calculation unit 40, a weighting unit 50, and a training extraction unit 60;
the initialization obtaining unit 10 is configured to initialize a neural network and obtain a training data set;
the augmentation processing unit 20 is configured to perform online data augmentation processing on the training data set to obtain augmented training data;
the input processing unit 30 is configured to input the augmented training data to the neural network in batches, and obtain an output of the face ID classification layer and an output of the mask classification layer after processing;
the calculating unit 40 is configured to calculate a value of a first loss function according to the extended training data and the output of the mask classification layer, and record the value as loss 1; calculating to obtain a second loss function value according to the extended training data and the output of the face ID classification layer, and recording as loss 2;
the weighting unit 50 is used for weighting the loss1 and the loss2 to obtain the final loss;
the training extraction unit 60 is configured to train the neural network according to the final loss until the loss converges or reaches a preset number of iterations, and then extract a feature model from the training result as a final face recognition model.
Wherein the training data set comprises training pictures and corresponding labels; wherein the label includes whether to wear a mask and a face ID.
Wherein, training data after the increase includes: mask labels and face ID labels; in the calculating unit 40, a first loss function value is calculated according to the output of the mask label and the mask classification layer, and a second loss function value is calculated according to the output of the face ID label and the face ID classification layer.
In the weighting unit 50, loss1 a1+ loss2 a2, where a1 and a2 are both weights.
It should be noted that, as can be clearly understood by those skilled in the art, the specific implementation process of the above-mentioned face recognition device based on multiple supervision and each unit may refer to the corresponding description in the foregoing method embodiment, and for convenience and conciseness of description, no further description is provided herein.
The above-mentioned multi-supervised based face recognition apparatus may be implemented in the form of a computer program which can be run on a computer device as shown in fig. 5.
Referring to fig. 5, fig. 5 is a schematic block diagram of a computer device according to an embodiment of the present application; the computer device 500 may be a terminal or a server, where the terminal may be an electronic device with a communication function, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of a plurality of servers.
Referring to fig. 5, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 comprises program instructions that, when executed, cause the processor 502 to perform a multiple surveillance based face recognition method.
The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503, and when the computer program 5032 is executed by the processor 502, the processor 502 may be enabled to execute a multi-supervision-based face recognition method.
The network interface 505 is used for network communication with other devices. Those skilled in the art will appreciate that the configuration shown in fig. 5 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation of the computer device 500 to which the present application may be applied, and that a particular computer device 500 may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
It should be understood that in the embodiment of the present Application, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will be understood by those skilled in the art that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program instructing associated hardware. The computer program includes program instructions, and the computer program may be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program comprises program instructions that, when executed by a processor, may implement the multi-supervised based face recognition method described above.
The storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, which can store various computer readable storage media.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, various elements or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be merged, divided and deleted according to actual needs. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention.
The above embodiments are preferred implementations of the present invention, and the present invention can be implemented in other ways without departing from the spirit of the present invention.
Claims (10)
1. The face recognition method based on multi-supervision is characterized by comprising the following steps:
initializing a neural network to obtain a training data set;
on-line data augmentation processing is adopted for the training data set, and augmented training data are obtained;
inputting the expanded training data into a neural network in batches, and processing to obtain the output of a face ID classification layer and the output of a mask classification layer;
calculating to obtain a first loss function value according to the extended training data and the output of the mask classification layer, and recording as loss 1; calculating to obtain a second loss function value according to the extended training data and the output of the face ID classification layer, and recording as loss 2;
weighting loss1 and loss2 to obtain the final loss;
and training the neural network according to the final loss until the loss converges or reaches the preset iteration times, and then extracting a feature model from the training result to be used as a final face recognition model.
2. The multi-surveillance based face recognition method of claim 1, wherein the training data set comprises training pictures and corresponding labels; wherein the label includes whether to wear a mask and a face ID.
3. The multi-surveillance based face recognition method of claim 1, wherein the augmented training data comprises: mask labels and face ID labels; and in the step of loss2, the value of the first loss function is obtained through calculation according to the output of the mask label and the mask classification layer, and the value of the second loss function is obtained through calculation according to the output of the face ID label and the face classification layer.
4. The multi-supervised face recognition method as recited in claim 1, wherein the weighting of the loss1 and the loss2 results in a final loss step, wherein the loss is 1 a1+ loss2 a2, and wherein a1 and a2 are both weights.
5. Face recognition device based on supervise more, its characterized in that includes: the system comprises an initialization acquisition unit, an augmentation processing unit, an input processing unit, a calculation unit, a weighting unit and a training extraction unit;
the initialization acquisition unit is used for initializing a neural network and acquiring a training data set;
the augmentation processing unit is used for performing online data augmentation processing on the training data set to obtain augmented training data;
the input processing unit is used for inputting the augmented training data into the neural network in batches, and obtaining the output of the face ID classification layer and the output of the mask classification layer after processing;
the calculating unit is used for calculating and obtaining a first loss function value according to the expanded training data and the output of the mask classification layer, and the first loss function value is recorded as loss 1; calculating to obtain a second loss function value according to the extended training data and the output of the face ID classification layer, and recording as loss 2;
the weighting unit is used for weighting loss1 and loss2 to obtain final loss;
and the training extraction unit is used for training the neural network according to the final loss until the loss converges or reaches the preset iteration times, and then extracting a characteristic model from the training result to be used as a final face recognition model.
6. The multi-surveillance based face recognition device of claim 5, wherein the training data set comprises training pictures and corresponding labels; wherein the label includes whether to wear a mask and a face ID.
7. The multi-surveillance based face recognition device of claim 5, wherein the augmented training data comprises: mask labels and face ID labels; and in the calculation unit, a first loss function value is calculated according to the output of the mask label and the mask classification layer, and a second loss function value is calculated according to the output of the face ID label and the face ID classification layer.
8. The multi-supervision based face recognition device according to claim 5, characterized in that in the weighting unit, loss is 1 a1+ loss2 a2, wherein a1 and a2 are both weights.
9. A computer device, characterized in that the computer device comprises a memory, on which a computer program is stored, and a processor, which when executing the computer program, implements the multiple surveillance based face recognition method according to any of claims 1-4.
10. A storage medium, characterized in that the storage medium stores a computer program comprising program instructions which, when executed by a processor, implement the multiple surveillance-based face recognition method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111060922.8A CN113688785A (en) | 2021-09-10 | 2021-09-10 | Multi-supervision-based face recognition method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111060922.8A CN113688785A (en) | 2021-09-10 | 2021-09-10 | Multi-supervision-based face recognition method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113688785A true CN113688785A (en) | 2021-11-23 |
Family
ID=78585905
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111060922.8A Pending CN113688785A (en) | 2021-09-10 | 2021-09-10 | Multi-supervision-based face recognition method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113688785A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114120430A (en) * | 2022-01-26 | 2022-03-01 | 杭州魔点科技有限公司 | Mask face recognition method based on double-branch weight fusion homology self-supervision |
| CN114694231A (en) * | 2022-04-18 | 2022-07-01 | 深圳市同为数码科技股份有限公司 | Face recognition method, device, equipment and medium based on off-line class center |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111553230A (en) * | 2020-04-21 | 2020-08-18 | 东南大学 | Feature enhancement based progressive cascade face detection method under unconstrained scene |
| CN112052789A (en) * | 2020-09-03 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Face recognition method and device, electronic equipment and storage medium |
| CN112818969A (en) * | 2021-04-19 | 2021-05-18 | 南京烽火星空通信发展有限公司 | Knowledge distillation-based face pose estimation method and system |
| CN113033328A (en) * | 2021-03-05 | 2021-06-25 | 杭州追猎科技有限公司 | Personnel mask wearing state detection and identification method based on deep learning |
-
2021
- 2021-09-10 CN CN202111060922.8A patent/CN113688785A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111553230A (en) * | 2020-04-21 | 2020-08-18 | 东南大学 | Feature enhancement based progressive cascade face detection method under unconstrained scene |
| CN112052789A (en) * | 2020-09-03 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Face recognition method and device, electronic equipment and storage medium |
| CN113033328A (en) * | 2021-03-05 | 2021-06-25 | 杭州追猎科技有限公司 | Personnel mask wearing state detection and identification method based on deep learning |
| CN112818969A (en) * | 2021-04-19 | 2021-05-18 | 南京烽火星空通信发展有限公司 | Knowledge distillation-based face pose estimation method and system |
Non-Patent Citations (1)
| Title |
|---|
| 刘文如: "《零基础入门Python深度学习》", 31 January 2020, pages: 70 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114120430A (en) * | 2022-01-26 | 2022-03-01 | 杭州魔点科技有限公司 | Mask face recognition method based on double-branch weight fusion homology self-supervision |
| CN114694231A (en) * | 2022-04-18 | 2022-07-01 | 深圳市同为数码科技股份有限公司 | Face recognition method, device, equipment and medium based on off-line class center |
| CN114694231B (en) * | 2022-04-18 | 2024-09-06 | 深圳市同为数码科技股份有限公司 | Face recognition method, device, equipment and medium based on offline class center |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022033150A1 (en) | Image recognition method, apparatus, electronic device, and storage medium | |
| US10635890B2 (en) | Facial recognition method and apparatus, electronic device, and storage medium | |
| CN108229322B (en) | Video-based face recognition method and device, electronic equipment and storage medium | |
| WO2021026805A1 (en) | Adversarial example detection method and apparatus, computing device, and computer storage medium | |
| WO2020155518A1 (en) | Object detection method and device, computer device and storage medium | |
| WO2022027912A1 (en) | Face pose recognition method and apparatus, terminal device, and storage medium. | |
| CN110532866B (en) | Video data detection method, device, computer equipment and storage medium | |
| CN109359214A (en) | Video presentation generation method, storage medium and terminal device neural network based | |
| CN107958230B (en) | Facial expression recognition method and device | |
| CN108229673B (en) | Convolutional neural network processing method and device and electronic equipment | |
| WO2021136027A1 (en) | Similar image detection method and apparatus, device and storage medium | |
| JP6633476B2 (en) | Attribute estimation device, attribute estimation method, and attribute estimation program | |
| US10922535B2 (en) | Method and device for identifying wrist, method for identifying gesture, electronic equipment and computer-readable storage medium | |
| CN112990318B (en) | Continuous learning method, device, terminal and storage medium | |
| WO2021027329A1 (en) | Image recognition-based information push method and apparatus, and computer device | |
| CN113688785A (en) | Multi-supervision-based face recognition method and device, computer equipment and storage medium | |
| WO2022127333A1 (en) | Training method and apparatus for image segmentation model, image segmentation method and apparatus, and device | |
| CN111444807A (en) | Target detection method, device, electronic equipment and computer readable medium | |
| CN110598732B (en) | Plant health detection method and device based on image recognition | |
| CN105224957A (en) | A kind of method and system of the image recognition based on single sample | |
| CN112069885A (en) | Face attribute identification method and device and mobile terminal | |
| CN110059180A (en) | Author identification and assessment models training method, device and storage medium | |
| CN110458024A (en) | Biopsy method and device and electronic equipment | |
| CN113591916B (en) | Data processing method and device based on classification model | |
| CN116663648B (en) | Model training method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |