CN112417986A - Semi-supervised online face recognition method and system based on deep neural network model - Google Patents
Semi-supervised online face recognition method and system based on deep neural network model Download PDFInfo
- Publication number
- CN112417986A CN112417986A CN202011191914.2A CN202011191914A CN112417986A CN 112417986 A CN112417986 A CN 112417986A CN 202011191914 A CN202011191914 A CN 202011191914A CN 112417986 A CN112417986 A CN 112417986A
- Authority
- CN
- China
- Prior art keywords
- training
- model
- face recognition
- data
- online
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a semi-supervised online face recognition method and system based on a deep neural network model, wherein the face recognition method comprises offline training and online training, and the offline training is used for generating a basic face recognition feature extraction model; the online training is realized by acquiring and uploading a recognition result through front-end face recognition equipment; the data preprocessing platform carries out preprocessing according to the recognition result and the image data; selecting on-line supervision training or self-supervision training according to the preprocessing result, and when the data reach a set amount, transferring the data into a training machine for training; and (4) finishing the automatic test model after training, comparing the test precision with the precision of the model generated by off-line training, and selecting whether to update the model. By the offline training and online training provided by the invention, the accuracy of the face recognition model can be consistent between a laboratory and an application environment model, and the accuracy of the face recognition model in an actual application scene is greatly improved.
Description
Technical Field
The invention relates to the field of face recognition, in particular to a semi-supervised online face recognition method and system based on a deep neural network model.
Background
The face recognition is a biological feature recognition technology for identity authentication based on human physiognomic feature information, and the maximum feature of the technology is that personal information can be prevented from being leaked and the technology is used for recognition in a non-contact mode. Face recognition and fingerprint recognition, palm print recognition, retina recognition, skeleton recognition, heartbeat recognition and the like belong to human body biological feature recognition technologies, and are generated along with the rapid development of technologies such as a photoelectric technology, a microcomputer technology, an image processing technology, pattern recognition and the like. The face recognition is widely applied to a plurality of important industries and fields such as public security, safety, customs, finance, army, airports, frontier port, security and the like, and civil markets such as intelligent entrance guard, door lock, attendance, mobile phones, digital cameras, intelligent toys and the like.
However, the existing face recognition model training exists: the model training needs a large amount of labels, the labeling cost is high, and the model training mode belongs to supervised learning; the model effect has high precision in the laboratory environment and low precision in the actual application scene; the model can not be trained on line, and the application scene data can not be utilized. Therefore, how to implement unsupervised learning of face recognition model training and improve the accuracy of the face recognition model in practical application scenarios is a technical problem which needs to be solved urgently.
Disclosure of Invention
In order to solve the above problems, a first aspect of the present invention provides a semi-supervised online face recognition method based on a deep neural network model, which is characterized in that the semi-supervised online face recognition method includes an offline training step and an online training step, a basic face recognition feature extraction model is generated through offline training, and the precision of the face recognition model in an actual application scene is improved through online iterative training coupled with application scene data; wherein:
the off-line training comprises the following steps:
preparing training data, including labeled data and unlabeled data;
constructing a deep neural network;
designing and calculating a Loss function;
training an integral model architecture to obtain a feature extraction model;
the online training comprises the following steps:
building a training machine environment, and deploying an offline training model in the training machine;
the front-end face recognition equipment uploads a recognition result to a data preprocessing platform;
the data preprocessing platform carries out preprocessing according to the recognition result and the image data;
selecting on-line supervision training or self-supervision training according to the preprocessing result, and when the data reach a set amount, transferring the data into a training machine for training;
and (5) training to finish the automatic test model.
Preferably, a semi-supervised online face recognition method based on a deep neural network model is adopted, and an automatic supervision training module is added in the offline training for realizing unsupervised learning.
Preferably, the design of the Loss function comprises an insight face Loss of supervised learning and an MSE Loss of self-supervised learning.
Preferably, the Loss calculation is that Loss1= insight face Loss + MSE Loss for labeled data, Loss2= MSE Loss for unlabeled sample data, incremental Loss = lamda Loss1 + (1-lamda) × Loss2, and the range of values of lamda is [0.5,1 ].
Preferably, a semi-supervised online face recognition method based on a deep neural network model is used for establishing a class label for a recognized face, and selecting online supervised training if the class picture collection is more than 5; adding the unidentified face into a training set, and selecting self-supervision training; and when the data reach the set amount, triggering an online training request, and transferring the data meeting the training conditions to a training machine for training.
Preferably, the semi-supervised online face recognition method based on the deep neural network model automatically tests the model after training is completed, and if the test precision is higher than that of the original offline model, the model is updated to the front-end face recognition equipment.
In a second aspect of the present invention, a semi-supervised online face recognition system based on a deep neural network model is provided, which is characterized in that the face recognition system comprises:
front-end face recognition equipment: acquiring and uploading an identification result;
a data preprocessing unit: preprocessing according to the recognition result and the image data;
an image training unit: selecting on-line supervision training or self-supervision training according to the preprocessing result; when the data reach the set amount, the data are put into a training machine for training;
a model test unit: and testing the off-line training model and the on-line training model, and updating the model with high precision to the front-end face recognition equipment.
The invention has the beneficial effects that: by adopting the semi-supervised online face recognition method and system based on the deep neural network model, unsupervised learning can be realized, the accuracy of the face recognition model in a laboratory is consistent with that of an application environment model by adopting offline training and online training, and the accuracy of the face recognition model in an actual application scene is greatly improved.
Drawings
FIG. 1 is a schematic diagram of an online training model provided by the present invention;
FIG. 2 is a schematic diagram of an off-line training model structure provided by the present invention.
Detailed Description
For the purpose of describing the embodiments of the present invention in detail, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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 should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention mainly aims to provide a semi-supervised online face recognition method and system based on a deep neural network model, aiming at solving the problems that the existing face recognition model training needs a large amount of labels, the labeling cost is high, and the model training mode belongs to supervised learning; the model effect is high in precision in a laboratory environment, but is low in precision in an actual application scene; the model can not be trained on line, and the technical problem of application scene data can not be utilized.
In order to achieve the purpose, the invention provides a semi-supervised online face recognition method and a system based on a deep neural network model, wherein the semi-supervised online face recognition method obtains and uploads a recognition result through front-end face recognition equipment; the data preprocessing platform carries out preprocessing according to the recognition result and the image data; selecting on-line supervision training or self-supervision training according to the preprocessing result, and when the data reach a set amount, transferring the data into a training machine for training; training to complete the automatic test model; in the embodiment, a basic face recognition feature extraction model is generated through offline training, and coupled application scene data with better recognition effect is generated through online iterative training; by adopting the off-line training and the on-line training provided by the invention, the accuracy of the face recognition model can be consistent with that of the model in the laboratory and the application environment, and the accuracy of the face recognition model in the actual application scene is greatly improved.
The present invention provides an embodiment, as shown in fig. 2, fig. 2 is a schematic structural diagram of an offline training model provided by the present invention, where the offline training includes: inputting accurate training data, constructing a deep neural network, designing a Loss function, calculating the Loss, training an overall model architecture, and obtaining a feature extraction model.
Specifically, accurate training data is input, including labeled data and unlabeled data.
Specifically, a Loss function is designed, wherein the Loss function comprises an insight face Loss of supervised learning and an MSE Loss of self-supervised learning.
Specifically, Loss calculation is performed, wherein Loss1= insight face Loss + MSE Loss is given to labeled data, Loss2= MSE Loss is given to unlabeled sample data, Loss = lamda Loss1 + (1-lamda) × Loss2 is given to lamda, and the value range of lamda is [0.5,1 ].
In another embodiment, as shown in fig. 1, fig. 1 is a schematic structural diagram of an online training model provided by the present invention, where the online training includes: building a training machine environment, acquiring and uploading a recognition result, preprocessing image data, selecting a training mode and updating a model.
Specifically, a training machine environment is set up: the offline training model is deployed in a training machine.
Specifically, the front-end face recognition device uploads the recognition result to the data processing platform.
Specifically, the data preprocessing platform performs preprocessing according to the recognition result and the image data.
Specifically, a category label is established for the recognized face, and if the collection of the category pictures is more than 5, the category meets the online supervision training condition; and adding the unidentified human faces into a training set to meet the self-supervision training condition.
Specifically, the number of image data satisfying the above training conditions is recorded periodically.
Specifically, after the data reaches a certain amount, an online training request can be triggered, and the data meeting the training conditions of the data preprocessing platform are transferred to a training machine for training.
Specifically, the model is automatically tested after training is completed, and if the testing precision is higher than that of the original offline model, the model is updated to the front-end face recognition equipment.
And generating a basic face recognition feature extraction model through offline training, and then performing online iterative training to enable the coupled application scene data with better recognition effect. The precision of the face recognition model training in practical application scenes is improved to a great extent.
It should be noted that the above-mentioned preferred embodiments are only illustrative and should not be construed as limiting the scope of the invention, and that modifications and variations can be made by those skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (7)
1. A semi-supervised online face recognition method based on a deep neural network model is characterized by comprising an offline training step and an online training step, wherein a basic face recognition feature extraction model is generated through offline training, and the precision of the face recognition model in an actual application scene is improved through online iterative training coupled with application scene data; wherein:
the off-line training comprises the following steps:
preparing training data, including labeled data and unlabeled data;
constructing a deep neural network;
designing and calculating a Loss function;
training an integral model architecture to obtain a feature extraction model;
the online training comprises the following steps:
building a training machine environment, and deploying an offline training model in the training machine;
the front-end face recognition equipment uploads a recognition result to a data preprocessing platform;
the data preprocessing platform carries out preprocessing according to the recognition result and the image data;
selecting on-line supervision training or self-supervision training according to the preprocessing result, and when the data reach a set amount, transferring the data into a training machine for training;
and (5) training to finish the automatic test model.
2. The semi-supervised online face recognition method based on the deep neural network model as claimed in claim 1, wherein the offline training is added with an auto-supervised training module for implementing unsupervised learning.
3. The semi-supervised online face recognition method based on the deep neural network model as claimed in claim 1, wherein the designed Loss function comprises supervised learning insight Loss and self-supervised learning MSE Loss.
4. The semi-supervised online face recognition method based on the deep neural network model as claimed in claim 1, wherein the Loss calculation is performed, for the labeled data, Loss1= insight face Loss + MSE Loss, for the unlabeled sample data, Loss2= MSE Loss, augmented Loss = lamda Loss1 + (1-lamda) Loss2, and the value range of lamda is [0.5,1 ].
5. The semi-supervised online face recognition method based on the deep neural network model as claimed in claim 1, wherein the face recognition method is characterized in that a category label is established for the recognized face, and if the category picture is collected by more than 5 pictures, online supervised training is selected; adding the unidentified face into a training set, and selecting self-supervision training; and when the data reach the set amount, triggering an online training request, and transferring the data meeting the training conditions to a training machine for training.
6. The semi-supervised online face recognition method based on the deep neural network model as claimed in claim 1, wherein the face recognition method automatically tests the model after training is completed, and if the test precision is higher than that of the original offline model, the model is updated to a front-end face recognition device.
7. A semi-supervised online face recognition system based on a deep neural network model, the face recognition system comprising:
front-end face recognition equipment: acquiring and uploading an identification result;
a data preprocessing unit: preprocessing according to the recognition result and the image data;
an image training unit: selecting on-line supervision training or self-supervision training according to the preprocessing result; when the data reach the set amount, the data are put into a training machine for training;
a model test unit: and testing the off-line training model and the on-line training model, and updating the model with high precision to the front-end face recognition equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011191914.2A CN112417986B (en) | 2020-10-30 | 2020-10-30 | Semi-supervised online face recognition method and system based on deep neural network model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011191914.2A CN112417986B (en) | 2020-10-30 | 2020-10-30 | Semi-supervised online face recognition method and system based on deep neural network model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112417986A true CN112417986A (en) | 2021-02-26 |
| CN112417986B CN112417986B (en) | 2023-03-10 |
Family
ID=74828069
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011191914.2A Active CN112417986B (en) | 2020-10-30 | 2020-10-30 | Semi-supervised online face recognition method and system based on deep neural network model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112417986B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966601A (en) * | 2021-03-05 | 2021-06-15 | 上海深硅信息科技有限公司 | Method for artificial intelligence teachers and apprentices to learn by semi-supervision |
| CN115830652A (en) * | 2023-01-11 | 2023-03-21 | 山西清众科技股份有限公司 | Deep palm print recognition device and method |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268484A (en) * | 2013-06-06 | 2013-08-28 | 温州大学 | Design method of classifier for high-precision face recognitio |
| CN103793713A (en) * | 2012-10-31 | 2014-05-14 | 中国科学院沈阳自动化研究所 | Low-rank constraint online self-supervised learning scene classification method |
| CN107533649A (en) * | 2015-03-27 | 2018-01-02 | 西门子公司 | Use the automatic brain tumor diagnosis method and system of image classification |
| CN108416370A (en) * | 2018-02-07 | 2018-08-17 | 深圳大学 | Image classification method, device based on semi-supervised deep learning and storage medium |
| CN108846357A (en) * | 2018-06-13 | 2018-11-20 | 蔡竞 | A kind of face identification method based on improvement increment type Non-negative Matrix Factorization |
| CN109102005A (en) * | 2018-07-23 | 2018-12-28 | 杭州电子科技大学 | Small sample deep learning method based on shallow Model knowledge migration |
| CN109766954A (en) * | 2019-01-31 | 2019-05-17 | 北京市商汤科技开发有限公司 | A kind of target object processing method, device, electronic equipment and storage medium |
| CN109886422A (en) * | 2019-02-01 | 2019-06-14 | 深圳绿米联创科技有限公司 | Model configuration method, device, electronic equipment and read/write memory medium |
| CN110009003A (en) * | 2019-03-14 | 2019-07-12 | 北京旷视科技有限公司 | Training method, the device and system of image procossing and image comparison model |
| CN110046583A (en) * | 2019-04-18 | 2019-07-23 | 南京信息工程大学 | Color face recognition method based on semi-supervised multiple view increment dictionary learning |
| CN110472533A (en) * | 2019-07-31 | 2019-11-19 | 北京理工大学 | A kind of face identification method based on semi-supervised training |
| CN110909803A (en) * | 2019-11-26 | 2020-03-24 | 腾讯科技（深圳）有限公司 | Image recognition model training method and device and computer readable storage medium |
| CN111222648A (en) * | 2020-01-15 | 2020-06-02 | 深圳前海微众银行股份有限公司 | Semi-supervised machine learning optimization method, device, equipment and storage medium |
| CN111414888A (en) * | 2020-03-31 | 2020-07-14 | 杭州博雅鸿图视频技术有限公司 | Low-resolution face recognition method, system, device and storage medium |
| CN111540109A (en) * | 2020-05-13 | 2020-08-14 | 四川天翼网络服务有限公司 | Face recognition system |
| US20200265218A1 (en) * | 2019-02-20 | 2020-08-20 | Peng Dai | Semi-supervised hybrid clustering/classification system |
-
2020
- 2020-10-30 CN CN202011191914.2A patent/CN112417986B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103793713A (en) * | 2012-10-31 | 2014-05-14 | 中国科学院沈阳自动化研究所 | Low-rank constraint online self-supervised learning scene classification method |
| CN103268484A (en) * | 2013-06-06 | 2013-08-28 | 温州大学 | Design method of classifier for high-precision face recognitio |
| CN107533649A (en) * | 2015-03-27 | 2018-01-02 | 西门子公司 | Use the automatic brain tumor diagnosis method and system of image classification |
| CN108416370A (en) * | 2018-02-07 | 2018-08-17 | 深圳大学 | Image classification method, device based on semi-supervised deep learning and storage medium |
| CN108846357A (en) * | 2018-06-13 | 2018-11-20 | 蔡竞 | A kind of face identification method based on improvement increment type Non-negative Matrix Factorization |
| CN109102005A (en) * | 2018-07-23 | 2018-12-28 | 杭州电子科技大学 | Small sample deep learning method based on shallow Model knowledge migration |
| CN109766954A (en) * | 2019-01-31 | 2019-05-17 | 北京市商汤科技开发有限公司 | A kind of target object processing method, device, electronic equipment and storage medium |
| CN109886422A (en) * | 2019-02-01 | 2019-06-14 | 深圳绿米联创科技有限公司 | Model configuration method, device, electronic equipment and read/write memory medium |
| US20200265218A1 (en) * | 2019-02-20 | 2020-08-20 | Peng Dai | Semi-supervised hybrid clustering/classification system |
| CN110009003A (en) * | 2019-03-14 | 2019-07-12 | 北京旷视科技有限公司 | Training method, the device and system of image procossing and image comparison model |
| CN110046583A (en) * | 2019-04-18 | 2019-07-23 | 南京信息工程大学 | Color face recognition method based on semi-supervised multiple view increment dictionary learning |
| CN110472533A (en) * | 2019-07-31 | 2019-11-19 | 北京理工大学 | A kind of face identification method based on semi-supervised training |
| CN110909803A (en) * | 2019-11-26 | 2020-03-24 | 腾讯科技（深圳）有限公司 | Image recognition model training method and device and computer readable storage medium |
| CN111222648A (en) * | 2020-01-15 | 2020-06-02 | 深圳前海微众银行股份有限公司 | Semi-supervised machine learning optimization method, device, equipment and storage medium |
| CN111414888A (en) * | 2020-03-31 | 2020-07-14 | 杭州博雅鸿图视频技术有限公司 | Low-resolution face recognition method, system, device and storage medium |
| CN111540109A (en) * | 2020-05-13 | 2020-08-14 | 四川天翼网络服务有限公司 | Face recognition system |
Non-Patent Citations (7)
| Title |
|---|
| FABIO ROLI 等: "Semi-supervised PCA-Based Face Recognition Using Self-training", 《SSPR/SPR 20065》 * |
| JIANKANG DENG 等: "ArcFace: Additive Angular Margin Loss for Deep Face Recognition", 《CVPR 2019》 * |
| XIAOHUA ZHAI 等: "S4L: Self-Supervised Semi-Supervised Learning", 《ICCV 2019》 * |
| 吴永斌 等: "学生宿舍人脸识别考勤系统设计", 《软件导刊》 * |
| 章之星 等: "基于深度学习的人脸识别智能引导系统", 《信息技术与信息化》 * |
| 钟锐 等: "基于局部融合特征与分层增量树的快速人脸识别算法", 《计算机科学》 * |
| 陈守阳 等: "基于深度学习的人脸识别课堂考勤系统", 《中国新通信》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966601A (en) * | 2021-03-05 | 2021-06-15 | 上海深硅信息科技有限公司 | Method for artificial intelligence teachers and apprentices to learn by semi-supervision |
| CN115830652A (en) * | 2023-01-11 | 2023-03-21 | 山西清众科技股份有限公司 | Deep palm print recognition device and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112417986B (en) | 2023-03-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111460962B (en) | Face recognition method and face recognition system for mask | |
| CN109711370B (en) | Data fusion method based on WIFI detection and face clustering | |
| CN108022235B (en) | Method for identifying defects of key components of high-voltage transmission iron tower | |
| CN106919921B (en) | Gait recognition method and system combining subspace learning and tensor neural network | |
| CN112417986B (en) | Semi-supervised online face recognition method and system based on deep neural network model | |
| CN102890776A (en) | Method for searching emoticons through facial expression | |
| CN113205002B (en) | Low-definition face recognition method, device, equipment and medium for unlimited video monitoring | |
| CN112801054A (en) | Face recognition model processing method, face recognition method and device | |
| Tahseen et al. | Access control to robotic systems based on biometric: the generalized model and its practical implementation | |
| CN113269903A (en) | Face recognition class attendance system | |
| CN105184236A (en) | Robot-based face identification system | |
| Rajput et al. | Attendance Management System using Facial Recognition | |
| Thakurdesai et al. | Face recognition using one-shot learning | |
| Painuly et al. | Efficient Real-Time Face Recognition-Based Attendance System with Deep Learning Algorithms | |
| Moctezuma et al. | Appearance model update based on online learning and soft‐biometrics traits for people re‐identification in multi‐camera environments | |
| Mishra et al. | A Face Recognition Method Using Deep Learning to Identify Mask and Unmask Objects | |
| Narlagiri et al. | Biometric authentication system based on face recognition | |
| CN101639876A (en) | Identity authentication method | |
| Bhatia et al. | Face Recognition Door Unlocking and Monitoring System | |
| CN116189026A (en) | Pedestrian re-recognition method and device and storage medium | |
| Kakran et al. | Identification and Recognition of face and number Plate for Autonomous and Secure Car Parking | |
| CN111191563A (en) | Face recognition method and system based on data sample and test data set training | |
| Li et al. | Application of data-driven feature extraction methods in biometrics | |
| CN115424383B (en) | Intelligent access control management system and method | |
| Ren et al. | Large-scale pose-invariant face recognition using cellular simultaneous recurrent network |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Third floor, No.10, Jiuxing Avenue, high tech Zone, Chengdu, Sichuan 610041 Applicant after: Sichuan Tianyi Network Co.,Ltd. Address before: Third floor, No.10, Jiuxing Avenue, high tech Zone, Chengdu, Sichuan 610041 Applicant before: SICHUAN TIANYI NETWORK SERVICE Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |