CN110569715A - Face recognition system based on convolutional neural network - Google Patents
Face recognition system based on convolutional neural network Download PDFInfo
- Publication number
- CN110569715A CN110569715A CN201910665197.3A CN201910665197A CN110569715A CN 110569715 A CN110569715 A CN 110569715A CN 201910665197 A CN201910665197 A CN 201910665197A CN 110569715 A CN110569715 A CN 110569715A
- Authority
- CN
- China
- Prior art keywords
- information
- face
- face recognition
- platform
- data
- 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
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 54
- 230000005540 biological transmission Effects 0.000 claims abstract description 10
- 238000012986 modification Methods 0.000 claims description 9
- 230000004048 modification Effects 0.000 claims description 9
- 238000012217 deletion Methods 0.000 claims description 5
- 230000037430 deletion Effects 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 description 41
- 238000007726 management method Methods 0.000 description 25
- 238000004364 calculation method Methods 0.000 description 7
- 238000000034 method Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 210000000887 face Anatomy 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
-
- 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
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
the invention discloses a face recognition system based on a convolutional neural network, which is characterized by comprising an AI edge algorithm server, an IOT (Internet of things) platform and a face recognition management platform, wherein the data transmission is carried out among the AI edge algorithm server, the IOT platform and the face recognition management platform; the AI edge algorithm server is also connected with the face recognition camera, sends a control instruction to the face recognition camera and receives data fed back by the face recognition camera; the AI edge algorithm server is used for starting a face recognition camera to capture video, comparing faces of people appearing in video data, storing comparison result information, sending recognition information to the IOT platform, sending the video data to the face recognition management platform through the IOT platform, and receiving update data of the face recognition management platform to the face information from the IOT platform; the IOT platform is used for receiving data sent by the face recognition management platform.
Description
Technical Field
the invention relates to a face recognition system, in particular to a face recognition system based on a convolutional neural network.
Background
Face recognition is mainly used for identity recognition, and particularly, a brand-new biometric identification technology appears along with rapid progress of computer technology, image processing technology, pattern recognition technology and the like in recent years. The method can be widely applied to various fields such as security verification, video monitoring, access control and the like, and has high identification speed and high identification rate, so the method becomes a main development direction in the field of identity identification technology research
At present, the mainstream human face recognition obtains a human face image on the basis of matching, and a classification algorithm is applied to carry out human face recognition. The following methods are mainly used: the method based on geometric features: detecting facial organs such as eyes, eyebrows, a nose, a mouth, a chin and the like, and identifying the human face by using the position, the size and the mutual spatial distribution relation of each organ; subspace-based approach: the face image is projected into the subspace through projection transformation, and the face representation in the subspace has higher resolution because the projection transformation has the characteristics of non-orthogonality and nonlinearity; method based on local features: and calculating corresponding face images by using various local operators, counting histograms of the face images, and identifying by using histogram information.
Disclosure of Invention
The technical problems to be solved by the invention are that the corresponding relation of the existing background management system is fixed, the face recognition management difficulty is high, and the interaction with a user is difficult.
the invention is realized by the following technical scheme:
A face recognition system based on a convolutional neural network is characterized by comprising an AI edge algorithm server, an IOT (Internet of things) platform and a face recognition management platform which are in data transmission with each other; the AI edge algorithm server is also connected with the face recognition camera, sends a control instruction to the face recognition camera and receives data fed back by the face recognition camera; the AI edge algorithm server is used for starting a face recognition camera to capture video, comparing faces of people appearing in video data, storing comparison result information, sending recognition information to the IOT platform, sending data to the face recognition management platform through the IOT platform, and receiving update data of the face recognition management platform to the face information from the IOT platform; the IOT platform is used for receiving the data sent by the face recognition management platform, forwarding the data to the AI edge algorithm server, receiving the recognition result of the AI edge algorithm server and forwarding the data to the face recognition management platform; the face recognition management platform is used for receiving video data and recognition information collected by the AI edge server and sent by the IOT platform, managing and displaying the information, and sending face data modification information to the IOT platform.
At present, when face recognition is carried out, a special recognition camera is needed for face recognition, most commonly, a face recognition all-in-one machine captures video pictures through a local camera, and a face recognition result is obtained through calculation of an algorithm model and is directly displayed. Under the condition, the background management system can only be in one-to-one correspondence to manage the death board, and compared with the traditional face recognition system and the traditional networking concept of fire and heat, the background management system stores the face recognition model on the AI edge algorithm server and utilizes the IOT platform to be connected with the face recognition management platform to manage the algorithm server.
The method adopts a mode that an AI edge algorithm server, an IOT (Internet of things) platform and a face recognition management platform carry out data transmission mutually, video data acquired by a face recognition camera is analyzed through the AI edge algorithm server, the real-time performance of acquisition and analysis can be improved, the AI edge algorithm server carries out data analysis by adopting edge calculation, although in the automation field, the edge calculation is controlled and analyzed in a period of 100ms and is not real-time, in the general life field, the delay is difficult to be perceived by people, the control and analysis rate is fast, the reaction time is fast, and the bandwidth is also reduced by a dispersion method of the edge calculation. Data processing starts from a collection point, and only data needing to be stored is sent to the cloud. This makes edge computation more efficient and scalable and reduces network load.
Further, after the AI edge algorithm server carries out face recognition on the video data collected by the face recognition camera, the recognition result is fed back to the IOT platform through the MQTT protocol. The MQTT protocol is an instant messaging protocol, is a protocol designed for communication of remote sensors and control equipment which have limited large computing capacity and work in a low-bandwidth and unreliable network, and selects message publishing supported by the MQTT at most once, wherein the message publishing completely depends on a bottom TCP/IP network. The distributed messages may be lost or repeated. For example, this level may be used for environmental sensor data, with a single loss of data having no relevance since a second transmission may occur in the near future.
Further, the AI edge algorithm server and the IOT platform provide network connection by using TCP/IP. Because the message issuing mode is selected at most once, the data support can be carried out by depending on a bottom TCP/IP network, and the data of the AI edge algorithm server can be sent to the IOT platform through the data transmission of the bottom layer.
Furthermore, a face information base is arranged in the face recognition management platform, face information is stored in the face information base, and the stored face information is sent to the IOT platform.
Furthermore, an information input module, an information deletion module, an information coding module and an information modification module are arranged in the face information base; the information input module is used for inputting face information data, the information deletion module is used for deleting face information stored in a face information base, the information coding module is used for communicating with the IOT (Internet of things) platform and sending the face data to the IOT platform, and the information modification module is used for modifying and covering the face information; personnel adding, deleting, modifying and managing are carried out through the information input module, the information deleting module, the information coding module and the information modifying module, a face library modifying message is sent to the IOT platform, the IOT platform forwards the message to the AI edge algorithm server, and the AI edge algorithm server receives the message and synchronously updates the face library information.
Furthermore, the AI edge algorithm server is formatted through an equipment initialization module and the equipment initialization module in the AI edge algorithm server, and data stored inside the AI edge algorithm server is cleared. And the initialization module in the AI edge algorithm server is used for cleaning the data of the whole server, removing all the data and enabling the AI edge algorithm server to receive the face data of the face recognition management platform again.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. The face recognition system based on the convolutional neural network can be accessed to different equipment types, and can meet the user requirements of automatic door opening, face attendance checking, intelligent furniture and the like according to face recognition result information;
2. The face recognition system based on the convolutional neural network can update the face information base at the highest speed by continuously inputting and modifying the face data in the face recognition management platform, so that the face data in the AI edge algorithm server can be updated in real time;
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a flow chart of the system of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Examples
As shown in fig. 1, the face recognition system based on the convolutional neural network of the present invention is characterized in that an AI edge algorithm server, an IOT internet of things platform and a face recognition management platform perform data transmission with each other; the AI edge algorithm server is also connected with the face recognition camera, sends a control instruction to the face recognition camera and receives data fed back by the face recognition camera; the AI edge algorithm server is used for starting a face recognition camera to capture video, comparing faces of people appearing in video data, storing comparison result information, sending recognition information to the IOT platform, sending data to the face recognition management platform through the IOT platform, and receiving update data of the face recognition management platform to the face information from the IOT platform; the IOT platform is used for receiving data sent by the face recognition management platform, forwarding the data to the AI edge algorithm server, receiving data collected by the AI edge algorithm server and forwarding video data to the face recognition management platform; the face recognition management platform is used for receiving video data and recognition information collected by the AI edge server and sent by the IOT platform, managing and displaying the information, and sending face data modification information to the IOT platform.
when the face recognition server is in actual use, firstly, a user needs to input face data to be recognized through a face information base in a face recognition management platform, when the face data needs to be modified and deleted, the face data are modified and deleted through the face information base, after the face data are input, the face data are sent to an IOT (Internet of things) platform through an MQTT (maximum likelihood test) protocol through the face information base, the IOT platform and each server have the characteristic of facilitating information interaction pushing, the IOT platform sends the data to an AI edge algorithm server, the AI edge algorithm server has three advantages, the first is real-time performance, edge calculation is utilized, although data processing is mainly carried out at the cloud end, the data can be transmitted back and forth between central servers within a few seconds. The time span for data transmission is too long. Edge calculation has great use under the requirement of 'real-time calculation'. Secondly, the network is intelligent, a large number of functions in the network can be directly processed at edge nodes, some functions of the traditional architecture need to return to a central server for processing, but can be directly processed at the edge and return corresponding results, thirdly, the data are aggregated, a physical device usually generates a large amount of data when running, the physical device can be filtered at the edge firstly and then gathered to the center for processing, and the computing capability of the edge is utilized.
And the AI edge algorithm server performs face recognition on the video data acquired by the face recognition camera and feeds back the recognition result to the IOT platform through the MQTT protocol. The MQTT protocol is an instant messaging protocol, is a protocol designed for communication of remote sensors and control equipment which have limited large computing capacity and work in a low-bandwidth and unreliable network, and selects message publishing supported by the MQTT at most once, wherein the message publishing completely depends on a bottom TCP/IP network. The distributed messages may be lost or repeated. For example, this level may be used for environmental sensor data, with a single loss of data having no relevance since a second transmission may occur in the near future.
The AI edge algorithm server and the IOT platform of the internet of things provide network connection by using TCP/IP. Because the message issuing mode is selected at most once, the data support can be carried out by depending on a bottom TCP/IP network, and the data of the AI edge algorithm server can be sent to the IOT platform through the data transmission of the bottom layer.
the face recognition management platform is internally provided with a face information base, stores face information through the face information base, and sends the stored face information to the IOT platform. The face information base is a data storage base, various face data input in the face recognition management platform can be stored in the face information base, when a user uses the face information base, the face data are input into the face information base, data in the face information base are added, modified and deleted, and then the data are sent to the AI edge algorithm server through the IOT platform.
the face information base is provided with an information input module, an information deleting module, an information coding module and an information modifying module; the information input module is used for inputting face information data, the information deletion module is used for deleting face information stored in a face information base, the information coding module is used for communicating with the IOT (Internet of things) platform and sending the face data to the IOT platform, and the information modification module is used for modifying and covering the face information; personnel adding, deleting, modifying and managing are carried out through the information input module, the information deleting module, the information coding module and the information modifying module, a face library modifying message is sent to the IOT platform, the IOT platform forwards the message to the AI edge algorithm server, and the AI edge algorithm server receives the message and synchronously updates the face library information. Various information modules in the face information base can record face information data into a database, can modify and delete the face information data, sends the face information which is recorded, modified and deleted to an IOT (Internet of things) platform through an information coding module, forwards the face data to an AI (Artificial intelligence) edge algorithm server through the IOT platform, and the AI edge algorithm server compares and identifies the data collected by the face identification camera through the face data.
And the AI edge algorithm server is formatted through the equipment initialization module and the equipment initialization module, and the data stored inside is cleared. And the initialization module in the AI edge algorithm server is used for cleaning the data of the whole server, removing all the data and enabling the AI edge algorithm server to receive the face data of the face recognition management platform again.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (6)
1. A face recognition system based on a convolutional neural network is characterized by comprising an AI edge algorithm server, an IOT (Internet of things) platform and a face recognition management platform which are in data transmission with each other; the AI edge algorithm server is also connected with the face recognition camera, sends a control instruction to the face recognition camera and receives data fed back by the face recognition camera;
The AI edge algorithm server is used for starting a face recognition camera to capture video, comparing faces of people appearing in video data, storing comparison result information, sending recognition information to the IOT platform, and receiving update data of the face recognition management platform to the face information from the IOT platform;
The IOT platform is used for receiving data sent by the face recognition management platform, forwarding the data to the AI edge algorithm server, receiving the identification information collected by the AI edge algorithm server and forwarding the identification information to the face recognition management platform;
the face recognition management platform is used for receiving recognition information collected by the AI edge server and sent by the IOT platform, managing and displaying the information, and sending face data modification information to the IOT platform.
2. The face recognition system based on the convolutional neural network as claimed in claim 1, wherein the AI edge algorithm server performs face recognition on the video data acquired by the face recognition camera, and then feeds back the recognition result to the IOT internet of things platform through MQTT protocol.
3. The convolutional neural network-based face recognition system of claim 2, wherein the AI edge algorithm server and the IOT internet of things platform provide network connection using TCP/IP.
4. The face recognition system based on the convolutional neural network as claimed in claim 1, wherein a face information base is arranged in the face recognition management platform, the face information is stored in the face information base, and the stored face information is sent to the IOT internet of things platform.
5. the face recognition system based on the convolutional neural network of claim 4, wherein an information input module, an information deletion module, an information coding module and an information modification module are arranged in the face information base; the information input module is used for inputting face information data, the information deletion module is used for deleting face information stored in a face information base, the information coding module is used for communicating with the IOT (Internet of things) platform and sending the face data to the IOT platform, and the information modification module is used for modifying and covering the face information; personnel adding, deleting, modifying and managing are carried out through the information input module, the information deleting module, the information coding module and the information modifying module, a face library modifying message is sent to the IOT platform, the IOT platform forwards the message to the AI edge algorithm server, and the AI edge algorithm server receives the message and synchronously updates the face library information.
6. The face recognition system based on the convolutional neural network of claim 1, wherein the AI edge algorithm server is formatted by the device initialization module through the device initialization module, and internally stored data is removed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910665197.3A CN110569715A (en) | 2019-07-23 | 2019-07-23 | Face recognition system based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910665197.3A CN110569715A (en) | 2019-07-23 | 2019-07-23 | Face recognition system based on convolutional neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110569715A true CN110569715A (en) | 2019-12-13 |
Family
ID=68773104
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910665197.3A Pending CN110569715A (en) | 2019-07-23 | 2019-07-23 | Face recognition system based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110569715A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113504831A (en) * | 2021-07-23 | 2021-10-15 | 电光火石(北京)科技有限公司 | IOT (input/output) equipment control method based on facial image feature recognition, IOT and terminal equipment |
| CN113538036A (en) * | 2021-06-04 | 2021-10-22 | 深圳市英创艾伦智能科技有限公司 | 5G, AI edge calculation and Internet of things digital management system, method and device |
| CN113962645A (en) * | 2021-09-30 | 2022-01-21 | 福建数博讯信息科技有限公司 | Method for updating face data of face recognition equipment in real time |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105426875A (en) * | 2015-12-18 | 2016-03-23 | 武汉科技大学 | Face identification method and attendance system based on deep convolution neural network |
-
2019
- 2019-07-23 CN CN201910665197.3A patent/CN110569715A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105426875A (en) * | 2015-12-18 | 2016-03-23 | 武汉科技大学 | Face identification method and attendance system based on deep convolution neural network |
Non-Patent Citations (1)
| Title |
|---|
| 任丽梅等: "《认知计算导论》", 首都经济贸易大学出版社, pages: 19 - 20 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538036A (en) * | 2021-06-04 | 2021-10-22 | 深圳市英创艾伦智能科技有限公司 | 5G, AI edge calculation and Internet of things digital management system, method and device |
| CN113504831A (en) * | 2021-07-23 | 2021-10-15 | 电光火石(北京)科技有限公司 | IOT (input/output) equipment control method based on facial image feature recognition, IOT and terminal equipment |
| CN113962645A (en) * | 2021-09-30 | 2022-01-21 | 福建数博讯信息科技有限公司 | Method for updating face data of face recognition equipment in real time |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111698470B (en) | Security video monitoring system based on cloud edge cooperative computing and implementation method thereof | |
| CN106997629B (en) | Access control method, apparatus and system | |
| US7617167B2 (en) | Machine vision system for enterprise management | |
| Liu et al. | iBotGuard: an Internet-based intelligent robot security system using invariant face recognition against intruder | |
| CN110428522A (en) | A kind of intelligent safety and defence system of wisdom new city | |
| CN110458154A (en) | Face identification method, device and computer readable storage medium | |
| CN109819208A (en) | A kind of dense population security monitoring management method based on artificial intelligence dynamic monitoring | |
| CN110046586A (en) | A kind of data processing method, equipment and storage medium | |
| CN109614882A (en) | A kind of act of violence detection system and method based on human body attitude estimation | |
| CN110569715A (en) | Face recognition system based on convolutional neural network | |
| JP2020516188A (en) | Face image duplication deletion method and apparatus, electronic device, storage medium, and program | |
| CN109086739A (en) | A kind of face identification method and system of no human face data training | |
| CN111565225B (en) | Character action track determining method and device | |
| CN111768336A (en) | Face image processing method and device, computer equipment and storage medium | |
| CN110263642A (en) | For replacing the image buffer storage of the part of image | |
| CN111918039B (en) | Artificial intelligence high risk operation management and control system based on 5G network | |
| CN112132197A (en) | Model training method, image processing method, device, computer equipment and storage medium | |
| CN111708663A (en) | Cloud computing safety monitoring system based on artificial intelligence | |
| CN110414376A (en) | Update method, face recognition cameras and the server of human face recognition model | |
| CN104883548A (en) | Monitoring-video face-capturing processing method and system | |
| CN109902681B (en) | User group relation determining method, device, equipment and storage medium | |
| CN110599129A (en) | Campus attendance checking method, device, identification terminal and system based on image tracking | |
| CN111652331A (en) | Image recognition method and device and computer readable storage medium | |
| Chandran et al. | Real-time identification of pedestrian meeting and split events from surveillance videos using motion similarity and its applications | |
| CN113947742A (en) | Person trajectory tracking method and device based on face recognition |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191213 |
|
| RJ01 | Rejection of invention patent application after publication |