CN101751557A - Intelligent biological identification device and identification method thereof - Google Patents
Intelligent biological identification device and identification method thereof Download PDFInfo
- Publication number
- CN101751557A CN101751557A CN200910201446A CN200910201446A CN101751557A CN 101751557 A CN101751557 A CN 101751557A CN 200910201446 A CN200910201446 A CN 200910201446A CN 200910201446 A CN200910201446 A CN 200910201446A CN 101751557 A CN101751557 A CN 101751557A
- Authority
- CN
- China
- Prior art keywords
- face
- video
- people
- change
- microprocessor cpu
- 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
Images
Landscapes
- Alarm Systems (AREA)
- Image Processing (AREA)
Abstract
The invention relates to an intelligent biological identification device. A microprocessor CPU is connected with a video A/D converter; the video A/D converter is connected with a camera; the microprocessor CPU is further connected with a flash memory and a cache DDR; after the video picture is converted by the A/D converter, a face picture is identified by picture processing identification software Adaboost operated on the microprocessor CPU. The invention is characterized in that the abnormal person in a video monitoring field can be detected in real time by a face detection algorithm and a face barrier identification algorithm, and, if the dubitable person is found, an alarm signal is sent instantly. The invention is widely applied to the special security defense fields such as a monitoring system of ATM machine, a bank hall, an army or a government office building.
Description
Technical field
The present invention relates to a kind of device of the people's of identification face, particularly a kind of intelligent biological identification device and recognition methods thereof.
Background technology
As the video monitoring system of security protection important component part, be widely used in public arenas such as urban transportation, bank, government bodies, the building that write, supermarket, airports, we can say that video monitoring system is ubiquitous.The current video supervisory system adds the rear end image acquisition by front-end camera mostly and forms with functions such as compressing storage, is called " digital picture CD writer " or " DVR ", mainly comprises following characteristics:
1. this type of video monitoring system simulating signal of acquisition camera in real time, and be converted into digital signal, and by processor digitized signal is compressed, store local hard drive or CD into.
This type of video monitoring system usually can by network with the video information at scene real-time be transferred to the master control machine room, the staff can carry out real-time supervision to the situation at scene.
3. this type of video monitoring system provides a User Alarms input interface usually, and the user can provide warning to system software by this interface, as fire alarm signal, infrared sensor alerting signal etc.The staff then does emphasis according to alerting signal to the situation at scene and monitors, then takes corresponding action if necessary.
Along with entire society's improving constantly to security protection consciousness, video monitoring system based on image acquisition and storage (DVR) traditional, machinery can not meet the demands at some special occasions, intelligent video monitoring system is expected to replace the traditional video surveillance system, is the future trend of safety-security area.
Summary of the invention
Technical matters to be solved by this invention is intelligent biological identification device and the recognition methods thereof that a kind of people's of identification face portion shelter will be provided.
In order to solve above technical matters, the invention provides a kind of intelligent biological identification device, a microprocessor CPU is connected with the video a/d transducer, and the video a/d transducer connects camera, finishes the collection of video image; Microprocessor CPU also is connected with high-speed cache DDR with flash memory FLASH, and video image by the Adaboost image processing software identification facial image that runs on little processing CPU, and is handled and judged people's face portion state after the A/D conversion.
This recognition methods comprises the steps:
1) system start-up;
2) video data acquiring;
3) in a two field picture, seek people's face with the Adaboost algorithm;
If do not find people's face, change the 2nd) step;
If find people's face, then carry out next step;
4) people's face position coordinates location;
Is 5) colour of skin of judging people face mated?
If unusual, then change the 8th) step;
Do 6) mouth rim detection and mouth type mate?
If unusual, then change the 8th) step;
7) human eye location and pupil location and state analysis;
If normal, then change the 2nd) step;
8) warning output.
Superior effect of the present invention is:
1) thoroughly changed " passive " mode of operation of traditional video monitoring system, on the basis that guarantees existing video monitoring system operate as normal, if monitored field staff face wears masks or when wearing sunglasses etc. and blocking object, provide alerting signal immediately, remind the staff scene of master control machine room that abnormal conditions are arranged;
2) the present invention is by people's face detection algorithm and people's face shelter recognizer, can be in real time the unusual personnel at video monitoring scene be detected, as finds this type of a suspect to provide alerting signal immediately;
3) on the basis that does not change existing supervisory system, practical flexibly " alarm " function is provided, can be widely used in special security places such as ATM supervisory system, bank hall, army or government house.
Description of drawings
Fig. 1 is a schematic block circuit diagram of the present invention;
Fig. 2 is the process flow diagram of inventor's face recognition method.
The number in the figure explanation
The 1-microprocessor CPU; 2-video a/d transducer;
The 3-camera; 4-flash memory FLASH;
5-high-speed cache DDR.
Embodiment
See also shown in the accompanying drawing, the invention will be further described.
As shown in Figure 1, the invention provides a kind of intelligent biological identification device, a microprocessor CPU 1 is connected with video a/d transducer 2, and video a/d transducer 2 connects camera 3, finishes the collection of video image; Microprocessor CPU 1 also is connected with high-speed cache DDR5 with flash memory FLASH4, and video image by the Adaboost image processing software identification facial image that runs on little processing CPU1, and is handled and judged people's face portion state after the A/D conversion.Power supply is connected with microprocessor CPU 1 respectively with reset circuit 6.
Above-mentioned Adaboost algorithm is a kind of classifier algorithm, its ultimate principle is the Weak Classifier that utilizes a large amount of classification capacities general, rectangular characteristic as people's face, by certain stacked system, be combined into a strong classifier that classification capacity is very strong,, again several strong classifier cascades become a classification device as the rectangular characteristic of people's face, the Adaboost algorithm is exactly to determine one or more rectangle frames, the i.e. position of people's face and size by these people's face sorters in image.
Above camera and video a/d transducer also can be used digital camera device.
As shown in Figure 2, recognition methods of the present invention comprises the steps:
1) system start-up;
2) video data acquiring;
3) in a two field picture, seek people's face with the Adaboost algorithm;
If do not find people's face, change the 2nd) step;
If find people's face, then carry out next step;
4) people's face position coordinates location;
Is 5) colour of skin of judging people face mated?
If unusual, then change the 8th) step;
Do 6) mouth rim detection and mouth type mate?
If unusual, then change the 8th) step;
7) human eye location and pupil location and state analysis;
If normal, then change the 2nd) step;
8) warning output.
Claims (2)
1. intelligent biological identification device is characterized in that:
One microprocessor CPU is connected with the video a/d transducer, the video a/d transducer connects camera, microprocessor CPU also is connected with high-speed cache DDR with flash memory FLASH, video image is after the A/D conversion, by the Adaboost image processing software identification facial image that runs on little processing CPU, and people's face portion state handled and judge.
2. by the recognition methods of the described a kind of intelligent biological identification device of claim 1, it is characterized in that:
This recognition methods comprises the steps:
1) system start-up;
2) video data acquiring;
3) in a two field picture, seek people's face with the Adaboost algorithm;
If do not find people's face, change the 2nd) step;
If find people's face, then carry out next step;
4) people's face position coordinates location;
Is 5) colour of skin of judging people face mated?
If unusual, then change the 8th) step;
Do 6) mouth rim detection and mouth type mate?
If unusual, then change the 8th) step;
7) human eye location and pupil location and state analysis;
If normal, then change the 2nd) step;
8) warning output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910201446A CN101751557A (en) | 2009-12-18 | 2009-12-18 | Intelligent biological identification device and identification method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910201446A CN101751557A (en) | 2009-12-18 | 2009-12-18 | Intelligent biological identification device and identification method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101751557A true CN101751557A (en) | 2010-06-23 |
Family
ID=42478521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200910201446A Pending CN101751557A (en) | 2009-12-18 | 2009-12-18 | Intelligent biological identification device and identification method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101751557A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101980242A (en) * | 2010-09-30 | 2011-02-23 | 徐勇 | Human face discrimination method and system and public safety system |
| CN103198567A (en) * | 2013-03-07 | 2013-07-10 | 刘文萍 | ATM alarming system based on Adaboost face detection and method |
| CN103971100A (en) * | 2014-05-21 | 2014-08-06 | 国家电网公司 | Video-based camouflage and peeping behavior detection method for automated teller machine |
-
2009
- 2009-12-18 CN CN200910201446A patent/CN101751557A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101980242A (en) * | 2010-09-30 | 2011-02-23 | 徐勇 | Human face discrimination method and system and public safety system |
| CN101980242B (en) * | 2010-09-30 | 2014-04-09 | 徐勇 | Human face discrimination method and system and public safety system |
| CN103198567A (en) * | 2013-03-07 | 2013-07-10 | 刘文萍 | ATM alarming system based on Adaboost face detection and method |
| CN103971100A (en) * | 2014-05-21 | 2014-08-06 | 国家电网公司 | Video-based camouflage and peeping behavior detection method for automated teller machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Auvinet et al. | Multiple cameras fall dataset | |
| CN204156985U (en) | There is high-definition camera equipment and the supervisory control system of face recognition comparison function | |
| CN103092345A (en) | Method and device for mobile terminal mode switching | |
| Liu et al. | Real-time human detection and tracking in complex environments using single RGBD camera | |
| CN105427421A (en) | Entrance guard control method based on face recognition | |
| Bai et al. | A novel eye location algorithm based on radial symmetry transform | |
| CN109672863A (en) | A kind of construction personnel's safety equipment intelligent monitoring method based on image recognition | |
| TWI638569B (en) | Surveillance system and surveillance method | |
| CN202771441U (en) | Face recognition monitoring system | |
| CN103714631A (en) | ATM intelligent monitoring system based on human face recognition | |
| CN108200405A (en) | A kind of video monitoring system based on recognition of face | |
| WO2014101220A1 (en) | Intelligent security system based on facial recognition | |
| CN202856897U (en) | Intelligent video monitoring system based on face recognition | |
| CN107516076A (en) | Portrait identification method and device | |
| CN107995471A (en) | A kind of image recognition gate inhibition video camera | |
| CN101751557A (en) | Intelligent biological identification device and identification method thereof | |
| JP5752976B2 (en) | Image monitoring device | |
| Williams et al. | Distributed smart cameras for aging in place | |
| CN205847453U (en) | A kind of wisdom gold eyeball people based on intelligent video technology and the Activity recognition system of thing | |
| Ren et al. | Research on Safety Helmet Detection for Construction Site | |
| Nagamani et al. | Anti-Theft Monitoring for a Smart Home | |
| CN112686180A (en) | Method for calculating number of personnel in closed space | |
| Lin et al. | A fall detection system based on human body silhouette | |
| CN115953815A (en) | Monitoring method and device for infrastructure site | |
| Kokila et al. | Face recognition based person specific identification for video surveillance applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20100623 |