CN110287794A - A kind of production line face intelligent identifying system - Google Patents

A kind of production line face intelligent identifying system Download PDF

Info

Publication number
CN110287794A
CN110287794A CN201910437784.7A CN201910437784A CN110287794A CN 110287794 A CN110287794 A CN 110287794A CN 201910437784 A CN201910437784 A CN 201910437784A CN 110287794 A CN110287794 A CN 110287794A
Authority
CN
China
Prior art keywords
processing unit
central processing
face
production line
electrically connected
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
Application number
CN201910437784.7A
Other languages
Chinese (zh)
Inventor
关经纬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Warner Technologies (shenzhen) Ltd
Original Assignee
Warner Technologies (shenzhen) Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Warner Technologies (shenzhen) Ltd filed Critical Warner Technologies (shenzhen) Ltd
Priority to CN201910437784.7A priority Critical patent/CN110287794A/en
Publication of CN110287794A publication Critical patent/CN110287794A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161Detection; Localisation; Normalisation
    • G06V40/166Detection; Localisation; Normalisation using acquisition arrangements

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)
  • General Factory Administration (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a kind of production line face intelligent identifying systems, including central processing unit, power module and video camera, the input terminal of the central processing unit is electrically connected by the output end of A/D conversion module and video camera, the central processing unit is electrically connected with the USB interface with PC machine electrical property, the central processing unit is electrically connected with display screen, the central processing unit is electrically connected with memory module, the central processing unit is connected with monitor terminal by radio transmitting and receiving chip signal, and the power module is the power supply of each electric elements;Which which staff this programme can recorde in and which platform machine used by installing FMI in production machine time;When problem occurs, this provides trackability for every machine;It can recorde the unwarranted staff for attempting to touch PC machine, can be to avoid unwarranted worker's illegal operation, and maintenance cost is reduced about 30%.

Description

A kind of production line face intelligent identifying system
Technical field
The present invention relates to technical field of face recognition, and in particular to a kind of production line face intelligent identifying system.
Background technique
In recent years, with the fast development of robot technology, catering industry, market, exhibition, the Department of Science and Technology, conference centre, The occasions such as opening celebration start to be widely applied robot, the manual labor carried out instead of the mankind to a certain extent.With The continuous promotion of China's administration of justice service, part judicial department started to introduce judicial service robot, pass through judicial server Device people carries out welcome's information, voice response, the work such as guidance of handling affairs.Judicial robot needs to carry out face knowledge to visiting personnel Not.
Currently, everybody face of judicial machine identifies that accuracy cannot be guaranteed, it is typically necessary by manually carrying out auxiliary knowledge Not, the intensity of the labour greatly increased in this way, and accuracy can not be guaranteed.
Summary of the invention
The purpose of the present invention is to provide a kind of production line face intelligent identifying systems, to solve in above-mentioned background technique The judicial identification device mentioned, typically by manually being identified, the intensity of the labour greatly increased in this way, and also it is accurate The problems such as property can not be guaranteed.
To achieve the above object, the invention provides the following technical scheme: a kind of production line face intelligent identifying system, including Central processing unit, power module and video camera, the input terminal of the central processing unit are defeated by A/D conversion module and video camera Outlet is electrically connected, and the central processing unit is electrically connected with the USB interface with PC machine electrical property, and the central processing unit electrically connects It is connected to display screen, the central processing unit is electrically connected with memory module, and the central processing unit is believed by radio transmitting and receiving chip It number is connected with monitor terminal, the power module is the power supply of each electric elements.
Preferably, the central processing unit is T89C51 single-chip microcontroller, and AT89C51 mcu programming has BP neural network calculation Method, Data fusion technique are the new technologies that developed recently gets up, and neural network is applied as a kind of data fusion method In multiple fields, neural network have conclude, summarize, extracting, memory, association and fault-tolerance, it relies on the complexity of system, By adjusting relationship interconnected between internal great deal of nodes, to achieve the purpose that handle information, in application process, lead to It crosses and trains, obtain related knowledge and information, measured data is compared with this information, carry out data fusion, edge calculations.
Preferably, the central processing unit is electrically connected by voltage detecting circuit and power module, voltage detecting circuit Micro energy lose precision battery low-voltage detection circuit is constituted for LMP7300, LMP7300 is micropower, accurate benchmark and adjustable sluggishness Comparator, reference voltage 2.048V, reference voltage precision be 0.25%, supply voltage range be 2.7-12V.
Preferably, the radio transmitting and receiving chip is TC35i-GSM, is the highly integrated GSM mould of double frequency 900/1800MHz Block.
Preferably, the display screen uses LM016L Liquid Crystal Module, internal to have controller, have the function of simply and compared with The functions such as character blinking, movement may be implemented in strong instruction set, and 8 or 4 parallel-by-bits transmission 2 can be used with single chip communication Kind mode, LM016I liquid-crystal data line DO~D7 are connect with P1.0~1.7 mouthful of single-chip computer AT89C52 respectively, control line RS, RW, RE and the port single-chip microcontroller P2.5, P2.6, P2.7 connect.
Preferably, memory module selects SPI mode, and the pin 1 of single-chip microcontroller is SPI route selection, and pin 2 is the number of spi bus According to input line, pin 7 is DOL Data Output Line, and pin 5 is clock line.
Preferably, the central processing unit is electrically connected with key by key module.
Preferably, the processing method of the central processing unit is as follows:
1) the image surface archives of face are initially set up;With the image surface file of the face of video camera acquisition units personnel or take theirs Photo forms image surface file, and these image surface file generated face lines (Faceprint) coding is stored up;
2) current human body image surface is obtained;The image surface of the current discrepancy personnel of cameras capture is used, or takes photo to input, and will Current image surface file generated face line coding;
3) with the comparison of current face line coding and archives inventory;In the face line coding of image surface that will be current and archives inventory Line coding in face carries out retrieval comparison;Above-mentioned " face line coding " mode is substantive characteristics and beginning according to face face come work 's.
Preferably, the central processing unit has the following characteristics that accurate proprietary face recognition algorithms
False acceptance rate, FAR≤5%;
False rejection rate, FRR≤2%;
Discrimination >=98%;
When being used together with password, discrimination=100%;
Recognition speed < 0.25s(@checks that distance=1.0m ,@1000 register user);
Light joint development.
Compared with prior art, the beneficial effects of the present invention are:
Which which staff this programme can recorde in and which platform machine used by installing FMI in production machine time Device;When problem occurs, this provides trackability for every machine;It can recorde the unwarranted work for attempting to touch PC machine Make personnel, can be to avoid unwarranted worker's illegal operation, and maintenance cost is reduced about 30%.
Detailed description of the invention
Fig. 1 is system block diagram of the invention;
Fig. 2 is the circuit diagram of central processing unit of the invention;
Fig. 3 is the circuit diagram of voltage detecting circuit of the invention;
Fig. 4 is the circuit diagram of radio transmitting and receiving chip of the invention;
Fig. 5 is the circuit diagram of display screen of the invention;
Fig. 6 is the circuit diagram of memory module of the invention;
Fig. 7 is the circuit diagram of power supply of the invention;
Fig. 8 is the circuit diagram of key circuit of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other Embodiment shall fall within the protection scope of the present invention.
The present invention provides a kind of technical solution as shown in figures 1-8, a kind of production line face intelligent identifying system, including Central processing unit, power module and video camera, the input terminal of the central processing unit are defeated by A/D conversion module and video camera Outlet is electrically connected, and the central processing unit is electrically connected with the USB interface with PC machine electrical property, and the central processing unit electrically connects It is connected to display screen, the central processing unit is electrically connected with memory module, and the central processing unit is believed by radio transmitting and receiving chip It number is connected with monitor terminal, the power module is the power supply of each electric elements.
Further, the central processing unit is T89C51 single-chip microcontroller, and AT89C51 mcu programming has BP neural network calculation Method, Data fusion technique are the new technologies that developed recently gets up, and neural network is applied as a kind of data fusion method In multiple fields, neural network have conclude, summarize, extracting, memory, association and fault-tolerance, it relies on the complexity of system, By adjusting relationship interconnected between internal great deal of nodes, to achieve the purpose that handle information, in application process, lead to It crosses and trains, obtain related knowledge and information, measured data is compared with this information, carry out data fusion, edge calculations.
Further, the central processing unit is electrically connected by voltage detecting circuit and power module, voltage detecting electricity Road is that LMP7300 constitutes micro energy lose precision battery low-voltage detection circuit, LMP7300 be micropower, accurate benchmark and it is adjustable late Stagnant comparator, reference voltage 2.048V, reference voltage precision are 0.25%, and supply voltage range is 2.7-12V.
Further, the radio transmitting and receiving chip is TC35i-GSM, is the highly integrated GSM mould of double frequency 900/1800MHz Block.
Further, the display screen uses LM016L Liquid Crystal Module, internal to have controller, have the function of simply and The functions such as character blinking, movement may be implemented in stronger instruction set, can be used 8 with single chip communication or 4 parallel-by-bits are transmitted 2 kinds of modes, LM016I liquid-crystal data line DO~D7 are connect with P1.0~1.7 mouthful of single-chip computer AT89C52 respectively, control line RS, RW, RE and the port single-chip microcontroller P2.5, P2.6, P2.7 connect.
Further, memory module selects SPI mode, and the pin 1 of single-chip microcontroller is SPI route selection, and pin 2 is spi bus Data In-Line, pin 7 are DOL Data Output Line, and pin 5 is clock line.
Further, the central processing unit is electrically connected with key by key module.
This programme, processing method are as follows:
1) the image surface archives of face are initially set up;With the image surface file of the face of video camera acquisition units personnel or take theirs Photo forms image surface file, and these image surface file generated face lines (Faceprint) coding is stored up;
2) current human body image surface is obtained;The image surface of the current discrepancy personnel of cameras capture is used, or takes photo to input, and will Current image surface file generated face line coding;
3) with the comparison of current face line coding and archives inventory;In the face line coding of image surface that will be current and archives inventory Line coding in face carries out retrieval comparison;Above-mentioned " face line coding " mode is substantive characteristics and beginning according to face face come work 's.
This programme has the following characteristics that accurate proprietary face recognition algorithms
False acceptance rate, FAR≤5%;
False rejection rate, FRR≤2%;
Discrimination >=98%;
When being used together with password, discrimination=100%;
Recognition speed < 0.25s(@checks that distance=1.0m ,@1000 register user);
Light joint development.
Working principle: this system is mounted on the installation at the top of PC display
SMT machine, Placement, SPI, Reflow oven, Printing and AOI are operated using PC.This system is pacified On their display
According to the height of display, FMI camera angle is adjusted.It can be always towards the operator before PC machine in this way
For data communication, FMI is by USB and PC machine " call " to realize following functions:
Transmission video signal
Control command is received from the end PC
PC is sent by signal face identification state
USB cable only need to be connected to any PC USB port from FMI by us
Software implementation:
In terms of PC, we have developed a management application programs
It is linked up with FMI
Show FMI stream video signal
PC machine is locked to prevent unwarranted staff
PC machine is unlocked for authorization worker
The time that record authorization worker logs in/exits
This application program will not influence existing production routine by well-designed
(3) the key technical indexes and economic indicator
1, the key technical indexes
(1) quick recognition speed was less than 0.5 second
(2) accuracy rate is higher than 98%
(3) with the flexible interface of computer and equipment, including the port USB, UART Com
(4) power consumption is lower than 300 mA 5V
2, the expected economic indicator being up to
By installing FMI in production machine, can recorde which staff in which time and any platform machine used.Work as problem When appearance, this provides trackability for every machine;
FMI can also record the unwarranted staff for attempting to touch PC machine.
Can be to avoid unwarranted worker's illegal operation, and maintenance cost is reduced about 30%.
In addition, face recognition product can be widely applied to various applications.Access control, equipment operation certification, affairs Authorization, personalized service only give some instances.These application programs represent a very important market scale and business Potentiality.
Finally, it should be noted that the foregoing is only a preferred embodiment of the present invention, it is not intended to restrict the invention, Although the present invention is described in detail referring to the foregoing embodiments, for those skilled in the art, still may be used To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features, All within the spirits and principles of the present invention, any modification, equivalent replacement, improvement and so on should be included in of the invention Within protection scope.

Claims (9)

1. a kind of production line face intelligent identifying system, including central processing unit, power module and video camera, it is characterised in that: The input terminal of the central processing unit is electrically connected by the output end of A/D conversion module and video camera, the central processing unit It is electrically connected with the USB interface with PC machine electrical property, the central processing unit is electrically connected with display screen, the central processing unit electricity Property is connected with memory module, and the central processing unit is connected with monitor terminal, the power supply mould by radio transmitting and receiving chip signal Block is the power supply of each electric elements.
2. a kind of production line face intelligent identifying system according to claim 1, it is characterised in that: the central processing unit For T89C51 single-chip microcontroller, AT89C51 mcu programming has BP neural network algorithm, and Data fusion technique is developed recently One new technology, neural network are used in multiple fields as a kind of data fusion method, and neural network, which has, to be concluded, is total Knot, extraction, memory, association and fault-tolerance, it relies on the complexity of system, mutually interconnects by adjusting between internal great deal of nodes The relationship connect, thus achieve the purpose that handling information by training, obtains related knowledge and information in application process, it will Measured data is compared with this information, carries out data fusion, edge calculations.
3. a kind of production line face intelligent identifying system according to claim 1, it is characterised in that: the central processing unit It is electrically connected by voltage detecting circuit and power module, voltage detecting circuit is that LMP7300 composition micro energy lose precision battery is low Voltage detecting circuit, LMP7300 are the comparator of micropower, accurate benchmark and adjustable sluggishness, reference voltage 2.048V, benchmark Voltage accuracy is 0.25%, and supply voltage range is 2.7-12V.
4. a kind of production line face intelligent identifying system according to claim 1, it is characterised in that: the wireless receiving and dispatching core Piece is TC35i-GSM, is the highly integrated gsm module of double frequency 900/1800MHz.
5. a kind of production line face intelligent identifying system according to claim 1, it is characterised in that: the display screen uses LM016L Liquid Crystal Module, it is internal to have controller, have the function of simply and stronger instruction set, may be implemented character blinking, The functions such as mobile can be used 8 with single chip communication or 4 parallel-by-bits transmit 2 kinds of modes, LM016I liquid-crystal data line DO~D7 It is connect respectively with P1.0~1.7 mouthful of single-chip computer AT89C52, control line RS, RW, RE and the port single-chip microcontroller P2.5, P2.6, P2.7 Connection.
6. a kind of production line face intelligent identifying system according to claim 1, it is characterised in that: memory module is selected SPI mode, the pin 1 of single-chip microcontroller are SPI route selection, and pin 2 is the Data In-Line of spi bus, and pin 7 is DOL Data Output Line, Pin 5 is clock line.
7. a kind of production line face intelligent identifying system according to claim 1, it is characterised in that: the central processing unit Key is electrically connected with by key module.
8. a kind of production line face intelligent identifying system according to claim 1, it is characterised in that: the central processing unit Processing method it is as follows:
1) the image surface archives of face are initially set up;With the image surface file of the face of video camera acquisition units personnel or take theirs Photo forms image surface file, and these image surface file generated face lines (Faceprint) coding is stored up;
2) current human body image surface is obtained;The image surface of the current discrepancy personnel of cameras capture is used, or takes photo to input, and will Current image surface file generated face line coding;
3) with the comparison of current face line coding and archives inventory;In the face line coding of image surface that will be current and archives inventory Line coding in face carries out retrieval comparison;Above-mentioned " face line coding " mode is substantive characteristics and beginning according to face face come work 's.
9. a kind of production line face intelligent identifying system according to claim 1, it is characterised in that: the central processing unit Have the following characteristics that accurate proprietary face recognition algorithms
False acceptance rate, FAR≤5%;
False rejection rate, FRR≤2%;
Discrimination >=98%;
When being used together with password, discrimination=100%;
Recognition speed < 0.25s(@checks that distance=1.0m ,@1000 register user);
Light joint development.
CN201910437784.7A 2019-05-24 2019-05-24 A kind of production line face intelligent identifying system Pending CN110287794A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910437784.7A CN110287794A (en) 2019-05-24 2019-05-24 A kind of production line face intelligent identifying system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910437784.7A CN110287794A (en) 2019-05-24 2019-05-24 A kind of production line face intelligent identifying system

Publications (1)

Publication Number Publication Date
CN110287794A true CN110287794A (en) 2019-09-27

Family

ID=68002581

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910437784.7A Pending CN110287794A (en) 2019-05-24 2019-05-24 A kind of production line face intelligent identifying system

Country Status (1)

Country Link
CN (1) CN110287794A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113158931A (en) * 2021-04-27 2021-07-23 河南能创电子科技有限公司 Low-voltage centralized reading, operation and maintenance implementation method based on AI intelligent face recognition technology

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103383216A (en) * 2012-12-31 2013-11-06 于净 Bullet cabinet and identity identifying method for bullet cabinet user
CN105760864A (en) * 2016-04-01 2016-07-13 成都奥卡卡科技有限公司 High-precision human face recognition system based on DC integrated voltage-stabilizing circuit
CN106127156A (en) * 2016-06-27 2016-11-16 上海元趣信息技术有限公司 Robot interactive method based on vocal print and recognition of face
CN108520217A (en) * 2018-03-28 2018-09-11 朱旭辉 A kind of face identification and Activity recognition system
CN108919982A (en) * 2018-06-14 2018-11-30 北京理工大学 A kind of automatic key mouse switching method based on facial orientation identification
CN208737284U (en) * 2018-11-08 2019-04-12 淄博特耐尔真空设备有限公司 A kind of the vacuum equipment monitoring and control system of safe and intelligent
CN109712274A (en) * 2017-10-25 2019-05-03 南京维汀拉沃网络科技有限公司 A kind of Gate-ban Monitoring System of Home House based on recognition of face

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103383216A (en) * 2012-12-31 2013-11-06 于净 Bullet cabinet and identity identifying method for bullet cabinet user
CN105760864A (en) * 2016-04-01 2016-07-13 成都奥卡卡科技有限公司 High-precision human face recognition system based on DC integrated voltage-stabilizing circuit
CN106127156A (en) * 2016-06-27 2016-11-16 上海元趣信息技术有限公司 Robot interactive method based on vocal print and recognition of face
CN109712274A (en) * 2017-10-25 2019-05-03 南京维汀拉沃网络科技有限公司 A kind of Gate-ban Monitoring System of Home House based on recognition of face
CN108520217A (en) * 2018-03-28 2018-09-11 朱旭辉 A kind of face identification and Activity recognition system
CN108919982A (en) * 2018-06-14 2018-11-30 北京理工大学 A kind of automatic key mouse switching method based on facial orientation identification
CN208737284U (en) * 2018-11-08 2019-04-12 淄博特耐尔真空设备有限公司 A kind of the vacuum equipment monitoring and control system of safe and intelligent

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
HAIXIA WANG 等: ""A practical service robot system for greeting guests"", 《PROCEEDINGS OF THE 31ST CHINESE CONTROL CONFERENCE》 *
周茜 等: ""一种便携式仓储温湿度检测仪的设计"", 《国外电子测量技术》 *
张东阳 等: ""基于TSL256x的助航灯光监控系统设计"", 《成组技术与生产现代化》 *
张丹媚 等: "《智慧社区管理》", 28 February 2019 *
李春雷 等: "《电子应用系统设计》", 31 March 2017 *
邓素萍 等: ""SPI串行总线与单片机系统的优化设计"", 《南京师范大学学报(工程技术版)》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113158931A (en) * 2021-04-27 2021-07-23 河南能创电子科技有限公司 Low-voltage centralized reading, operation and maintenance implementation method based on AI intelligent face recognition technology

Similar Documents

Publication Publication Date Title
CN110795989A (en) Intelligent safety monitoring system for electric power operation and monitoring method thereof
CN208479837U (en) A kind of real-time target detection device based on raspberry pie
CN211509189U (en) Electric power operation field supervision equipment and system
CN207727662U (en) A kind of wisdom pump house
CN102096811A (en) Intelligent face recognition module based on embedded platform, and recognition method thereof
CN110287794A (en) A kind of production line face intelligent identifying system
CN110310450A (en) A kind of electrical intelligent fire disaster cruising inspection system and method based on wearable device
CN201345116Y (en) Online patrol management device
CN209149389U (en) The quick checking device of recognition of face pass gates
CN207720304U (en) A kind of intelligent remote video monitoring system merged based on mobile intelligent terminal and technology of Internet of things
CN102157049A (en) Intelligent image identification based remote monitoring transmission system of operating conditions of fire alarm controller
CN207909325U (en) A kind of power grid taiwan area identifying system
CN207636578U (en) A kind of underwater environment monitoring device based on POE
CN207352429U (en) A kind of building safety defense monitoring system
CN109361902A (en) A kind of intelligent safety helmet wearing monitoring system based on edge calculations
CN211741567U (en) Transmission line foreign matter winding monitoring system
CN104732622A (en) Safety door system based on ZigBee
CN209007512U (en) A kind of entrance control type intelligent networking detection instrument case
CN209433223U (en) A kind of controller for optical cross box status monitoring
CN209543389U (en) Face alignment system based on smart glasses, smart watches and smart phone
CN207799414U (en) A kind of site construction monitoring system
CN109753780A (en) A kind of method and system of protective relaying device identification user identity
CN204667494U (en) A kind of supervisory system based on face recognition and password confirming
CN215910582U (en) Monitoring system for electric power safety behavior of power grid
CN211531116U (en) Safe electric power automation equipment

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: 20190927

RJ01 Rejection of invention patent application after publication