CN112686145A - Facial skin type identification method and intelligent terminal thereof - Google Patents
Facial skin type identification method and intelligent terminal thereof Download PDFInfo
- Publication number
- CN112686145A CN112686145A CN202011599559.2A CN202011599559A CN112686145A CN 112686145 A CN112686145 A CN 112686145A CN 202011599559 A CN202011599559 A CN 202011599559A CN 112686145 A CN112686145 A CN 112686145A
- Authority
- CN
- China
- Prior art keywords
- model
- facial
- skin
- intelligent terminal
- user
- 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
- 230000001815 facial effect Effects 0.000 title claims abstract description 64
- 230000036555 skin type Effects 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 8
- 238000002372 labelling Methods 0.000 claims abstract description 5
- 238000003062 neural network model Methods 0.000 claims abstract description 4
- 238000012216 screening Methods 0.000 claims abstract description 4
- 206010000496 acne Diseases 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 208000002874 Acne Vulgaris Diseases 0.000 claims description 3
- 206010013786 Dry skin Diseases 0.000 claims description 3
- 206010039792 Seborrhoea Diseases 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000037336 dry skin Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000037312 oily skin Effects 0.000 claims description 3
- 238000013138 pruning Methods 0.000 claims description 3
- 230000037310 combination skin Effects 0.000 claims description 2
- 230000008439 repair process Effects 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 241000282414 Homo sapiens Species 0.000 description 11
- 238000011161 development Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000013145 classification model Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005055 memory storage Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000005808 skin problem Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a method for identifying facial skin types and an intelligent terminal thereof, which relate to the technical field of image identification and comprise the steps of collecting historical facial images of users in a database; screening the collected facial images and carrying out manual labeling and classification; performing feature engineering processing on the collected face image; building a ResNet deep neural network model based on a convolutional neural network, wherein the model comprises 50 layers, training the model by using a GPU (graphics processing unit), iterating for 10000 times, outputting model parameters, and optimizing the model; and compressing the model parameters to integrate the model parameters into the intelligent terminal, checking the identification accuracy of the model, and identifying the facial image input model to be identified to obtain an identification result. The invention has the beneficial effects that: the facial skin type identification method is used for identifying the facial skin type of the user, is high in accuracy, can generate corresponding skin care product recommendation according to the identification result, and improves the satisfaction degree of the user for purchasing the skin care product on line.
Description
Technical Field
The invention belongs to the technical field of image recognition, and particularly relates to a facial skin type recognition method and an intelligent terminal thereof.
Background
The image recognition technology is widely applied to various fields of life such as finance, aerospace, electric power, industry, education, medical treatment and the like, and particularly, with the rapid development of deep learning methods such as a convolutional neural network and the like, the accuracy of image recognition in the application fields such as human faces, medical treatment and the like is higher than that of human beings.
With the development of the times, people increasingly rely on shopping through an online shopping mall, and the development of economy prompts women to pay more and more attention to the image management of the women, wherein the attention is particularly paid to the facial care. Traditional women buy facial skin care products, mainly through the test of line sales counter special person carrying out the skin type, and then recommend corresponding skin care product. However, this conventional approach causes inconvenience to the user who is shopping online.
Disclosure of Invention
The invention provides a facial skin type identification method and an intelligent terminal thereof, and solves the problems that a user cannot conveniently know the skin type of the user when shopping online in the prior art.
In a first aspect of the present invention, there is provided a method for identifying facial skin types, comprising the steps of:
(1) collecting historical facial images of users in a database;
(2) screening the collected facial images and carrying out manual labeling and classification;
(3) performing feature engineering processing on the collected face image;
(4) building a ResNet deep neural network model based on a convolutional neural network, wherein the model comprises 50 layers, training the model by using a GPU (graphics processing unit), iterating for 10000 times, outputting model parameters, and optimizing the model;
(5) and compressing the model parameters to integrate the model parameters into the intelligent terminal, checking the identification accuracy of the model, and identifying the facial image input model to be identified to obtain an identification result.
The content for labeling the face image in the step (2) of the invention comprises the following steps: oily skin, dry skin, combination skin, acne, and blackheads.
The content of performing feature engineering processing on the collected face image in the step (3) of the invention comprises the following steps: and (4) clipping, scaling, gray scale conversion, overexposure area repair and contrast adjustment are carried out on the picture.
The 50 layers in the step (4) of the invention comprise a convolutional neural network layer, a batch normalization layer, a max _ posing layer and an activation function layer.
In the step (6), model parameters are compressed by a pruning and parameter sharing method or a lightweight model is adopted to replace the original model, so that a huge parameter model can be operated on an intelligent terminal with limited memory storage.
In a second aspect of the present invention, there is provided a facial skin type recognition intelligent terminal, comprising:
the face recognition module is used for recognizing and collecting facial images of users;
the image processing module is used for processing the collected face image of the user;
the model training module is used for training and classifying the facial head portraits of the historical users in the database;
and the skin type identification module is used for classifying the facial skin types of the user to be classified.
The face recognition module of the invention adopts a camera to shoot and obtain the face image of a user.
In a third aspect of the invention, an electronic device is provided. The electronic device includes: a memory having a computer program stored thereon and a processor implementing the method according to the first aspect of the invention when executing the program.
In a fourth aspect of the invention, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the method according to the first aspect of the invention.
It should be understood that the statements herein reciting aspects are not intended to limit the critical or essential features of any embodiment of the invention, nor are they intended to limit the scope of the invention. Other features of the present invention will become apparent from the following description.
The invention has the beneficial effects that: the invention provides a method for identifying facial skin and an intelligent terminal thereof, which are used for identifying the facial skin of a user, have high accuracy, can generate corresponding skin care product recommendation according to an identification result, and improve the satisfaction degree of purchasing skin care products on line by the user.
Drawings
Fig. 1 is an overall flowchart of a facial skin type identification method according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
Fig. 1 shows an overall flow diagram of a method for identifying facial skin types.
A method for identifying and processing human facial skin comprises the following steps:
(1) collecting historical facial images of users in a database;
(2) screening the collected facial images and carrying out manual marking, such as skin type classification of oily skin, dry skin, mixed skin, acne, blackhead and other facial skin and some common skin problems;
(3) performing characteristic engineering on the collected picture, including but not limited to clipping, scaling, gray level conversion, repairing an overexposed area, adjusting contrast and the like on the picture;
(4) building a ResNet deep neural network model based on a convolutional neural network, wherein the model comprises 50 layers, and each layer comprises a convolutional neural network layer, a batch normalization layer, a max _ posing layer, an activation function layer and the like; using a GPU (graphics processing Unit) to train the model, iterating for 10000 times, outputting model parameters, and optimizing the model;
(5) training other models, such as VGGNet, AlexNet and other common models as baseline, comparing the models, and selecting a model which has good performance and better generalization capability on a testing machine;
(6) compressing the model parameters to enable the model parameters to be integrated into codes of the intelligent terminal, checking the identification accuracy of the model, and storing the model parameters into the intelligent terminal for program calling;
(7) and acquiring a facial image of a user to be identified and inputting the facial image into a model for identification to obtain an identification result.
In the step (3), the acquired picture has incomplete photographed facial parts or is blurred due to reasons such as excessively slow shutter speed, and the like, so that the picture needs to be repaired by feature engineering.
In the step (6), a model can be compressed by adopting methods such as pruning and parameter sharing, or a lightweight model is adopted to replace the original model under the condition of not influencing the accuracy and generalization capability of prediction, so that the model with huge parameters can be operated on an intelligent terminal with limited memory storage.
The method for acquiring the facial image to be identified in the step (7) comprises the steps of triggering the intelligent terminal to identify the face of a person through a camera; in order to ensure the definition of the acquired picture, the exposure value of the corresponding self-exposure window is configured in a self-adaptive manner according to the intensity of the background light, so that the corresponding exposure is carried out, a clear face image is finally obtained, and when the posture of the user is incorrect and the human face cannot be recognized, the user side is prompted to correct the posture.
In the step (7), if the face recognition fails, the step of triggering the face recognition is returned until the first condition, the second condition, the third condition, the fourth condition and the fifth condition are met. Wherein the first condition is: the frequency of continuously triggering the face recognition exceeds a threshold value of preset frequency; the second condition is: the time length of single-time triggering of the face recognition exceeds the preset time length; the third condition is: the detected image is not a human face; the fourth condition is that: detecting that the brightness of the environment is too high; the fifth condition is: detecting that the brightness of the environment is too low; a sixth condition: the face recognition is successful.
When the first condition is met, outputting first prompt information indicating face recognition failure;
when the second condition is met, outputting second prompt information indicating face recognition failure;
when the third condition is met, outputting third prompt information indicating face recognition failure;
when the fourth condition is met, outputting fourth prompt information for prompting the failure of face recognition;
when the fifth condition is met, outputting fifth prompt information for prompting face recognition failure;
when the sixth condition is met, outputting sixth prompt information indicating that the face recognition is successful;
the first prompt information prompts the user that the identification frequency is too many, and the user tries the test later; the second prompt message prompts the user to identify too long and retry later; the third prompt message prompts the user that the detected image is not the human face, and asks the user to aim the human face at the camera of the intelligent terminal; the fourth prompt message prompts the user that the detected environment brightness is too high and the brightness of the environment needs to be reduced; the fifth prompt message prompts the user that the detected environment brightness is too low and the environment brightness needs to be increased; the sixth prompt message prompts that the user has succeeded in facial recognition and is analyzing the skin of the user's face.
A facial skin type discernment intelligent terminal includes:
the face recognition module is used for recognizing and collecting facial images of users;
the image processing module is used for processing the collected face image of the user;
the model training module is used for training and classifying the facial head portraits of the historical users in the database;
and the skin type identification module is used for classifying the facial skin types of the user to be classified.
The embodiment of the application provides a commodity recommendation method based on a knowledge graph, which comprises the following steps:
identifying the facial skin of the user based on the identification method of the facial skin and the intelligent terminal thereof, and generating a recommended commodity id through a knowledge map and a knowledge base;
if the model cannot identify the facial skin type of the user, the identification is repeated until a seventh condition or an eighth condition is met. Wherein the seventh condition is: the execution times exceed a preset threshold; the eighth condition is: the recommendation was successful.
Outputting seventh prompt information for prompting that the facial skin identification fails when the seventh condition is met;
when the eighth condition is met, outputting eighth prompt information for prompting that the facial skin type identification is successful, and displaying the skin type of the user;
and (4) sorting through a sorting algorithm to obtain an optimal top10 recommendation result, and outputting the optimal top10 recommendation result to an intelligent terminal display screen.
Example 1
1. And triggering the intelligent terminal to perform face recognition. When a user clicks an intelligent terminal application identification button, the intelligent terminal is triggered to perform face identification, and the intelligent terminal calls a camera of the terminal.
2. And (4) carrying out human face recognition, entering the next step if the recognition is successful, otherwise, repeating the steps until the conditions 1-6 are met, and outputting a corresponding prompt. In this embodiment, an intelligent terminal user acquires a face image of the user through a camera, determines whether the acquired image is a human face through image recognition, if the image is the human face, the step 3 is performed, otherwise, the reason of the recognition failure is determined, and if the calling exceeds a specified number of times or is overtime, the user is prompted to fail in recognition, and the user is requested to retry.
3. And after the facial image is successfully identified, facial skin type identification is carried out, the facial image is predicted according to the model, and skin type classification is obtained. And (3) performing characteristic processing such as gray scale, contrast, scaling and the like on the image according to the facial image of the user obtained in the step (2), inputting the processed data into a local model, and predicting the image through the model to obtain a classification result of the skin of the user.
4. Training, optimizing and updating the human facial skin type classification model. The training of the facial skin type classification model is carried out in the server in an optimized mode, local model data are updated regularly through networking so as to obtain a better classification result, and meanwhile, the model is adjusted and optimized according to data returned by the intelligent terminal to the server.
5. And generating top10 commodity recommendation through the knowledge map and the knowledge base. After the skin type classification of the user is obtained, a knowledge base constructed by expert knowledge, the skin characteristics of the user, the attribute characteristics of the user and the like are used, corresponding commodity id is output through a knowledge map, and top10 is selected through a sequencing model to recommend the user.
Program code for implementing the methods of the present invention may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on 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.
Further, while operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the invention. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims (9)
1. A method for identifying facial skin types is characterized by comprising the following steps:
(1) collecting historical facial images of users in a database;
(2) screening the collected facial images and carrying out manual labeling and classification;
(3) performing feature engineering processing on the collected face image;
(4) building a ResNet deep neural network model based on a convolutional neural network, wherein the model comprises 50 layers, training the model by using a GPU (graphics processing unit), iterating for 10000 times, outputting model parameters, and optimizing the model;
(5) and compressing the model parameters to integrate the model parameters into the intelligent terminal, checking the identification accuracy of the model, and identifying the facial image input model to be identified to obtain an identification result.
2. The method for identifying facial skin according to claim 1, wherein the labeling of the facial image in step (2) comprises: oily skin, dry skin, combination skin, acne, and blackheads.
3. The method for identifying facial skin according to claim 1, wherein the step (3) of performing feature engineering processing on the collected facial image comprises: and (4) clipping, scaling, gray scale conversion, overexposure area repair and contrast adjustment are carried out on the picture.
4. The method for identifying facial skin types according to claim 1, wherein 50 layers in the step (4) comprise a convolutional neural network layer, a batch normalization layer, a max _ posing layer and an activation function layer.
5. A method of facial skin identification as claimed in claim 1 wherein: in the step (6), model parameters are compressed by adopting a pruning and parameter sharing method or a lightweight model is adopted to replace the original model so that a model with huge parameters can be operated on an intelligent terminal with limited memory.
6. The utility model provides a facial skin type discernment intelligent terminal which characterized in that includes:
the face recognition module is used for recognizing and collecting facial images of users;
the image processing module is used for processing the collected face image of the user;
the model training module is used for training and classifying the facial head portraits of the historical users in the database;
and the skin type identification module is used for classifying the facial skin types of the user to be classified.
7. The intelligent terminal for facial skin type recognition according to claim 6, wherein the face recognition module adopts a camera to shoot and acquire a facial image of the user.
8. An electronic device comprising a memory and a processor, the memory having stored thereon a computer program, wherein the processor, when executing the program, implements the method of any of claims 1-5.
9. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011599559.2A CN112686145A (en) | 2020-12-29 | 2020-12-29 | Facial skin type identification method and intelligent terminal thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011599559.2A CN112686145A (en) | 2020-12-29 | 2020-12-29 | Facial skin type identification method and intelligent terminal thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112686145A true CN112686145A (en) | 2021-04-20 |
Family
ID=75454194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011599559.2A Pending CN112686145A (en) | 2020-12-29 | 2020-12-29 | Facial skin type identification method and intelligent terminal thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112686145A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113160224A (en) * | 2021-05-18 | 2021-07-23 | 中国医学科学院皮肤病医院(中国医学科学院皮肤病研究所) | Artificial intelligence-based skin aging degree identification method, system and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107984092A (en) * | 2017-12-29 | 2018-05-04 | 江苏金海创科技有限公司 | A kind of laser marking network system and its method |
| CN108780497A (en) * | 2017-11-14 | 2018-11-09 | 深圳和而泰智能控制股份有限公司 | A kind of skin blemishes point sorting technique and electronic equipment |
| CN109344921A (en) * | 2019-01-03 | 2019-02-15 | 湖南极点智能科技有限公司 | A kind of image-recognizing method based on deep neural network model, device and equipment |
| CN109376625A (en) * | 2018-10-10 | 2019-02-22 | 东北大学 | A kind of human facial expression recognition method based on convolutional neural networks |
| CN110533634A (en) * | 2019-07-26 | 2019-12-03 | 深圳壹账通智能科技有限公司 | Proposal recommending method, device, computer equipment and storage medium based on artificial intelligence |
| CN110543906A (en) * | 2019-08-29 | 2019-12-06 | 彭礼烨 | Skin type automatic identification method based on data enhancement and Mask R-CNN model |
| US20200065563A1 (en) * | 2018-08-21 | 2020-02-27 | Software Ag | Systems and/or methods for accelerating facial feature vector matching with supervised machine learning |
| CN112101487A (en) * | 2020-11-17 | 2020-12-18 | 深圳感臻科技有限公司 | Compression method and device for fine-grained recognition model |
-
2020
- 2020-12-29 CN CN202011599559.2A patent/CN112686145A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108780497A (en) * | 2017-11-14 | 2018-11-09 | 深圳和而泰智能控制股份有限公司 | A kind of skin blemishes point sorting technique and electronic equipment |
| CN107984092A (en) * | 2017-12-29 | 2018-05-04 | 江苏金海创科技有限公司 | A kind of laser marking network system and its method |
| US20200065563A1 (en) * | 2018-08-21 | 2020-02-27 | Software Ag | Systems and/or methods for accelerating facial feature vector matching with supervised machine learning |
| CN109376625A (en) * | 2018-10-10 | 2019-02-22 | 东北大学 | A kind of human facial expression recognition method based on convolutional neural networks |
| CN109344921A (en) * | 2019-01-03 | 2019-02-15 | 湖南极点智能科技有限公司 | A kind of image-recognizing method based on deep neural network model, device and equipment |
| CN110533634A (en) * | 2019-07-26 | 2019-12-03 | 深圳壹账通智能科技有限公司 | Proposal recommending method, device, computer equipment and storage medium based on artificial intelligence |
| CN110543906A (en) * | 2019-08-29 | 2019-12-06 | 彭礼烨 | Skin type automatic identification method based on data enhancement and Mask R-CNN model |
| CN112101487A (en) * | 2020-11-17 | 2020-12-18 | 深圳感臻科技有限公司 | Compression method and device for fine-grained recognition model |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113160224A (en) * | 2021-05-18 | 2021-07-23 | 中国医学科学院皮肤病医院(中国医学科学院皮肤病研究所) | Artificial intelligence-based skin aging degree identification method, system and device |
| CN113160224B (en) * | 2021-05-18 | 2021-11-26 | 中国医学科学院皮肤病医院(中国医学科学院皮肤病研究所) | Artificial intelligence-based skin aging degree identification method, system and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107679507B (en) | Facial pore detection system and method | |
| US20210174072A1 (en) | Microexpression-based image recognition method and apparatus, and related device | |
| CN113159147B (en) | Image recognition method and device based on neural network and electronic equipment | |
| CN111738243B (en) | Method, device and equipment for selecting face image and storage medium | |
| CN101075872B (en) | Registration device, collation device and extraction method | |
| CN112183482A (en) | Dangerous driving behavior recognition method, device and system and readable storage medium | |
| CN110827236B (en) | Brain tissue layering method, device and computer equipment based on neural network | |
| WO2020056995A1 (en) | Method and device for determining speech fluency degree, computer apparatus, and readable storage medium | |
| CN113449704B (en) | Face recognition model training method and device, electronic equipment and storage medium | |
| CN114067431A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN111401339A (en) | Method and device for identifying age of person in face image and electronic equipment | |
| CN112446322A (en) | Eyeball feature detection method, device, equipment and computer-readable storage medium | |
| CN112686145A (en) | Facial skin type identification method and intelligent terminal thereof | |
| CN111815606A (en) | Image quality evaluation method, storage medium, and computing device | |
| CN112613425B (en) | Target identification system for small sample underwater image | |
| CN112633074B (en) | Pedestrian information detection method and device, storage medium and electronic equipment | |
| CN113160475A (en) | Access control method, device, equipment and computer readable storage medium | |
| WO2019071663A1 (en) | Electronic apparatus, virtual sample generation method and storage medium | |
| CN112365441A (en) | Information processing method and device for jadeite evaluation | |
| CN111427456A (en) | Real-time interaction method, device and equipment based on holographic imaging and storage medium | |
| CN116363732A (en) | Face emotion recognition method, device, equipment and storage medium | |
| CN113017634B (en) | Emotion evaluation method, emotion evaluation device, electronic device, and computer-readable storage medium | |
| CN115526254A (en) | Scene recognition system, method, electronic device, and storage medium | |
| CN112329736B (en) | Face recognition method and financial system | |
| CN113033250A (en) | Facial muscle state analysis and evaluation method |
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 |