CN102708691B - False license plate identification method based on matching between license plate and automobile type - Google Patents
False license plate identification method based on matching between license plate and automobile type Download PDFInfo
- Publication number
- CN102708691B CN102708691B CN201110440188.8A CN201110440188A CN102708691B CN 102708691 B CN102708691 B CN 102708691B CN 201110440188 A CN201110440188 A CN 201110440188A CN 102708691 B CN102708691 B CN 102708691B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- image
- car
- license plate
- automobile
- 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.)
- Expired - Fee Related
Links
Landscapes
- Image Processing (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a false license plate identification method based on matching between a license plate and an automobile type. The method is based on automatic identification of the conventional license plate. The method comprises the following steps of: extracting a contour characteristic of an automobile window through an image processing technology, and digitalizing the contour characteristic into a characteristic code; then searching a database of an automobile management center; and comparing the characteristic code of the automobile with a characteristic code of the automobile with the same number, which is registered in the database, and judging whether the automobile is legal. By the method, images are indirectly stored, transmitted and compared, and only the characteristic code of the automobile is searched and inquired, so that the speed for identifying whether the license plate is matched with the automobile type can be increased.
Description
Technical field
The present invention relates to a kind of false licence plate recognition method based on car plate vehicle coupling, belong to the field of image recognition of vehicle in intelligent intelligent traffic administration system.
Background technology
In order to identify the false car plate of vehicle, the present invention devises a kind of false automatic license plate identification system by mating car plate and vehicle information.The present invention is based upon on the basis of existing license auto-recognition system.First, by image processing techniques, extract the resemblance of vehicle, and be digitized as feature code.Then, in searching database, by the vehicle feature of this vehicle be registered in storehouse jack per line vehicle feature compared with, confirm whether be identified vehicle has " legal " identity with this.
The feature of this method is, when identifying vehicle, and the encode vehicle feature of vehicle.With vehicle image ratio to compared with discriminating method, the feature code that this method adopts is more accurately succinct, the also storage of convenient vehicle information, transmission and operation.Herein, vehicle feature code contains the eigenwerts such as the number-plate number, body color, vehicle size, vehicle window girth and vehicle window area.
On the basis of overall vehicle volume computing comparison, this method propose and extract vehicle window as characteristic portion, and in addition digitizing vehicle window information, confirm vehicle further.Why select vehicle window as characteristic portion, be in some consideration following:
1. the vehicle of same kind is tending towards similar on build, will segment vehicle further, needs to carry out identification to the details of car body.
2. vehicle window, especially side vehicle window, have higher discrimination.Different model vehicles, vehicle window broadly similar, but details place is different, and this is the foundation that this method effectively distinguishes vehicle.
3. vehicle window has higher identification in car load image, convenient extraction.Vehicle window is because the singularity of structure and material, in the display of image, obvious difference is had with car body, be mainly reflected in colouring discrimination, gray scale difference, and possess complete closure frame profiles clearly, by color range process, choose suitable threshold values binary image and profile and the operation such as to choose, vehicle window station diagram picture can be separated;
The method extracts vehicle window part, calculates vehicle window girth and area information, by these two information being representative vehicle window features, carries out the matching identification of vehicle.It is the guiding theory of this method that characteristics of image quantizes.Image information can take ample resources in the process storing, transmit and process, and in intelligent transportation system, data volume is too huge is one of main difficulty of engineering construction.This method wins the effective information in image, and does not directly store, transmits and comparison chart picture, alleviates greatly because the immense pressure brought of direct control image.
Summary of the invention
The defect that the present invention seeks to exist for prior art provides a kind of false licence plate recognition method based on car plate vehicle coupling.
The present invention for achieving the above object, adopts following technical scheme:
A kind of false licence plate recognition method based on car plate vehicle coupling of the present invention, comprises the steps:
One, according to existing vehicle recongnition technique, the number-plate number of this car is obtained;
Two, body side position video camera shooting vehicle is leaned to one side bit image, and bit image input computing machine of being leaned to one side by vehicle prepares to carry out vehicle cab recognition program;
Three, vehicle cab recognition program is started:
1) leaned to one side by the vehicle environmental background image of bit image and preservation does difference comparsion, rejects environmental background, obtains vehicle body image;
2) pick up vehicle body colouring information color, commonly use look according to vehicle body, its color is included in black, white, blue, red, grey, silver-colored, yellow, green and other colour types;
3) calculate area squareofcar and the pixel number of vehicle body image, according to pixel number, vehicle is divided into large car (L), in-between car (M) and compact car (S);
4) with in the vehicle body image determined, search effective vehicle characteristic information and vehicle window further, to vehicle body image through circumstances in which people get things ready for a trip contrast whole and rim detection, find out the profile of vehicle window, calculate profile perimeter p eriofwin and institute encloses area squareofwin;
5) with the combinations of values obtained in above-mentioned steps become the feature code typecode=num//color//squofcar//L/M/S//periofwin//squofwi n/ of this vehicle/;
Four, the permissible error of each composition position of code is set, and the weighting proportion in result judges, the feature code typecode then will generated, with the feature code of jack per line vehicle in database, compares by reservation strategy;
Five, the comparison result of analytical characteristic code, sends corresponding suggestion according to symbol degree and judges: mate, substantially do not mate, do not mate.
During identification vehicle of the present invention, the encode vehicle feature of vehicle.With vehicle image ratio to compared with discriminating method, the feature code that this method adopts is more accurately succinct, the also storage of convenient vehicle information, transmission and operation.The inventive method extracts the effective information in image, and does not directly store, transmits and comparison chart picture, drastically increases the recognition speed of false car plate.
Accompanying drawing explanation
Fig. 1: present system structural drawing;
Fig. 2: car plate vehicle coupling process flow diagram;
Fig. 3: detect window edge after image procossing;
Fig. 4: extract vehicle window profile and fill, calculates girth and area.
Embodiment
As shown in Figure 1, be false automatic license plate identification system schematic diagram.When vehicle is provided with the section of video monitoring equipment by freeway toll station or other, camera is recorded automatically real-time and is taken the photograph video, the video image comprising car plate is taken in by video acquisition interface acquisition camera, then from video image, license plate image is extracted, carry out License Plate, auto Segmentation character, and then character is identified.Meanwhile image procossing is carried out to the picture that equipment collects, thus extracts the external form profile of vehicle, then system various parameter is processed, relatively after automatically go out to differentiate the vehicle of vehicle.By the vehicle information with board vehicle in comparison Current vehicle and database, thus effectively check out whether there is by vehicle the cheating that vehicle and car plate such as not to be inconsistent at the aspect.
The false licence plate recognition method that the present invention is based on car plate vehicle coupling as shown in Figures 2 to 4, comprises the steps:
One, this automatic recognition system, on the basis of existing license auto-recognition system, obtains the license plate number num of current detected vehicle, according to this license board information retrieval vehicle management database, if do not find this license board information, conclude that this car plate is false car plate, give the alarm; If find this license board information, then enter program two;
Two, recall the vehicle characteristic information of this car from database, treat that vehicle comparison operation uses;
Three, body side position video camera shooting vehicle side image, input computing machine prepares to carry out vehicle cab recognition program;
Four, vehicle cab recognition program is started.This program mainly completes following operation:
1) the environmental background image of vehicle side image and preservation is done difference comparsion, obtain vehicle body image;
2) pick up vehicle body colouring information color, commonly use look according to vehicle body, its color is included in black, white, blue, red, grey, silver-colored, yellow, green and other colour types.
3) calculate area squareofcar and the pixel number of vehicle body image, according to pixel number, vehicle is divided into large car (L), in-between car (M) and compact car (S).
4) with in the vehicle body image determined, search effective vehicle characteristic information and vehicle window further, to vehicle body image through circumstances in which people get things ready for a trip contrast whole and rim detection, find out the profile of vehicle window, calculate profile perimeter p eriofwin and institute encloses area squareofwin;
5) with the combinations of values obtained in above-mentioned steps become the feature code typecode=num//color//squofcar//L/M/S//periofwin//squofwi n/ of this vehicle/;
Five, by the feature code ~ typecode:num comparison with board vehicle same format in the feature code typecode of generation and database.During comparison, according to circumstances can set the permissible error of code composition position and the weighting proportion in result judges, with to the requirement meeting system robustness and testing result reliability.
Six, the comparison result of analytical characteristic code, sends corresponding suggestion according to symbol degree and judges: meet, be not substantially inconsistent, do not meet.
The present invention, on the basis of overall vehicle volume computing comparison, this method proposes and extracts vehicle window as characteristic portion, and in addition digitizing vehicle window information, confirm vehicle further.Why select vehicle window as characteristic portion, be in some consideration following:
1. the vehicle of same kind is tending towards similar on build, will segment vehicle further, needs to carry out identification to the details of car body.
2. vehicle window, especially side vehicle window, have higher discrimination.Every a car, vehicle window broadly similar, but details place is different, and this is the foundation that this method effectively distinguishes vehicle.
3. vehicle window has higher identification in car load image, convenient extraction.Vehicle window is because the singularity of structure and material, in the display of image, obvious difference is had with car body, be mainly reflected in colouring discrimination, gray scale difference, and possess complete closure frame profiles clearly, by color range process, choose suitable threshold values binary image and profile is chosen, vehicle window station diagram picture can be separated;
The method extracts vehicle window part, calculates vehicle window girth and area information, by these two information being representative vehicle window features, carries out the matching identification of vehicle.
Claims (1)
1., based on a false licence plate recognition method for car plate vehicle coupling, it is characterized in that comprising the steps:
According to vehicle-carried microwave designation card, obtain the number-plate number of this car;
Body side position video camera shooting vehicle is leaned to one side bit image, and bit image input computing machine of being leaned to one side by vehicle prepares to carry out vehicle cab recognition;
Start vehicle cab recognition:
Vehicle side image and Conservation environment background image are done difference comparsion, rejects environmental background, obtain vehicle body image;
Pickup vehicle body colouring information color, commonly uses look according to vehicle body, its color is included in black, white, blue, red, grey, silver-colored, yellow, green classification;
Calculate the area squareofcar of vehicle body image: pixel number, is divided into large car (L), in-between car (M) and compact car (S) according to pixel number by vehicle;
In fixed vehicle body image, search effective vehicle characteristic information further: vehicle window, carry out color range adjustment and rim detection, find out the profile of vehicle window to vehicle body image, calculating profile perimeter p eriofwin and institute enclose area squareofwin;
With the combinations of values obtained in above-mentioned steps become the feature code typecode of this vehicle for num//color//squofcar//L/M/S//periofwin//squofwin//;
The permissible error of each composition position of setting code, and the weighting proportion in result judges, the feature code typecode then will generated, with the feature code of jack per line vehicle in database, compares by predetermined policy;
The comparison result of analytical characteristic code, sends corresponding suggestion according to matching degree and judges: mate, substantially do not mate, do not mate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110440188.8A CN102708691B (en) | 2011-12-26 | 2011-12-26 | False license plate identification method based on matching between license plate and automobile type |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110440188.8A CN102708691B (en) | 2011-12-26 | 2011-12-26 | False license plate identification method based on matching between license plate and automobile type |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102708691A CN102708691A (en) | 2012-10-03 |
| CN102708691B true CN102708691B (en) | 2015-04-22 |
Family
ID=46901403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110440188.8A Expired - Fee Related CN102708691B (en) | 2011-12-26 | 2011-12-26 | False license plate identification method based on matching between license plate and automobile type |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102708691B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI596552B (en) * | 2016-08-02 | 2017-08-21 | Nat Chin-Yi Univ Of Tech | Car models recognition system and method |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488973B (en) * | 2013-09-12 | 2017-10-20 | 上海依图网络科技有限公司 | Vehicle brand recognition methods and system based on image |
| CN103927512B (en) * | 2014-03-11 | 2017-05-10 | 浙江工商大学 | vehicle identification method |
| KR20150125463A (en) * | 2014-04-30 | 2015-11-09 | 렉스젠(주) | Device for converting the vehicle number into the image, Method for controlling the same and Vehicle number reading system using the same |
| CN105279475A (en) * | 2014-07-15 | 2016-01-27 | 贺江涛 | Fake-licensed vehicle identification method and apparatus based on vehicle identity recognition |
| CN105321350B (en) * | 2014-08-05 | 2018-01-23 | 北京大学 | Fake-licensed car detection method and device |
| JP6515726B2 (en) * | 2015-08-04 | 2019-05-22 | オムロン株式会社 | Vehicle identification device and vehicle identification system provided with the same |
| CN108932857B (en) * | 2017-05-27 | 2021-07-27 | 西门子（中国）有限公司 | Method and device for controlling traffic signal lamp |
| CN108022427A (en) * | 2017-10-30 | 2018-05-11 | 深圳市赛亿科技开发有限公司 | A kind of recognition methods of fake license plate vehicle and system |
| CN109376617A (en) * | 2018-09-30 | 2019-02-22 | 佳都新太科技股份有限公司 | Counterfeit vehicle registration plate identification method, device, identification equipment and storage medium |
| CN113205069B (en) * | 2021-05-27 | 2023-05-30 | 上海高德威智能交通系统有限公司 | False license plate detection method and device and computer storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3926673B2 (en) * | 2002-05-15 | 2007-06-06 | 富士通株式会社 | Vehicle type identification device |
| JP4035910B2 (en) * | 1999-01-29 | 2008-01-23 | 三菱電機株式会社 | Car color discrimination device |
| CN101110160A (en) * | 2007-08-31 | 2008-01-23 | 天津大学 | Vehicle traffic information monitoring method and system combining RFID and machine vision |
| CN201278214Y (en) * | 2008-09-23 | 2009-07-22 | 许文阁 | Automatic recognition apparatus for vehicle license |
| CN101540105A (en) * | 2009-04-15 | 2009-09-23 | 四川川大智胜软件股份有限公司 | Fake-licensed car detection method based on number-plate identification and gridding supervision |
| CN101635092A (en) * | 2009-05-22 | 2010-01-27 | 上海宝康电子控制工程有限公司 | Identification system and method of unlicensed motor vehicles |
| CN101783076A (en) * | 2010-02-04 | 2010-07-21 | 西安理工大学 | Method for quick vehicle type recognition under video monitoring mode |
| CN101799984A (en) * | 2009-02-10 | 2010-08-11 | 上海宝康电子控制工程有限公司 | System and method for automatically verifying electronic license plate and actual license plate |
-
2011
- 2011-12-26 CN CN201110440188.8A patent/CN102708691B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4035910B2 (en) * | 1999-01-29 | 2008-01-23 | 三菱電機株式会社 | Car color discrimination device |
| JP3926673B2 (en) * | 2002-05-15 | 2007-06-06 | 富士通株式会社 | Vehicle type identification device |
| CN101110160A (en) * | 2007-08-31 | 2008-01-23 | 天津大学 | Vehicle traffic information monitoring method and system combining RFID and machine vision |
| CN201278214Y (en) * | 2008-09-23 | 2009-07-22 | 许文阁 | Automatic recognition apparatus for vehicle license |
| CN101799984A (en) * | 2009-02-10 | 2010-08-11 | 上海宝康电子控制工程有限公司 | System and method for automatically verifying electronic license plate and actual license plate |
| CN101540105A (en) * | 2009-04-15 | 2009-09-23 | 四川川大智胜软件股份有限公司 | Fake-licensed car detection method based on number-plate identification and gridding supervision |
| CN101635092A (en) * | 2009-05-22 | 2010-01-27 | 上海宝康电子控制工程有限公司 | Identification system and method of unlicensed motor vehicles |
| CN101783076A (en) * | 2010-02-04 | 2010-07-21 | 西安理工大学 | Method for quick vehicle type recognition under video monitoring mode |
Non-Patent Citations (4)
| Title |
|---|
| UHF无源金属电子标签车辆号牌及其识别系统;杨磊;《江苏警官学院学报》;20090720(第04期);第181-187页 * |
| 基于色差均值的快速车窗定位算法;王运琼等;《计算机应用与软件》;20040112(第01期);第78-79页 * |
| 基于车流信息采集的套牌车辆治理方法研究;靳引利等;《中国水运(学术版)》;20070901(第09期);第173-176页 * |
| 新车型识别方法及其在套牌车辆鉴别中的应用;王枚等;《计算机工程与应用》;20090611(第17期);第211-214页 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI596552B (en) * | 2016-08-02 | 2017-08-21 | Nat Chin-Yi Univ Of Tech | Car models recognition system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102708691A (en) | 2012-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102708691B (en) | False license plate identification method based on matching between license plate and automobile type | |
| CN110245663B (en) | Method for identifying steel coil information | |
| CN111666834A (en) | Forest fire automatic monitoring and recognizing system and method based on image recognition technology | |
| CN101715111B (en) | Method for automatically searching abandoned object in video monitoring | |
| CN107016362B (en) | Vehicle weight recognition method and system based on vehicle front windshield pasted mark | |
| CN102902957A (en) | Video-stream-based automatic license plate recognition method | |
| CN110490150B (en) | Automatic illegal picture auditing system and method based on vehicle retrieval | |
| JP4577153B2 (en) | Environment recognition device | |
| CN107578012A (en) | A kind of drive assist system based on clustering algorithm selection sensitizing range | |
| CN106991821A (en) | Vehicles peccancy hand-held mobile terminal data collecting system | |
| CN113034378B (en) | Method for distinguishing electric automobile from fuel automobile | |
| CN111213154A (en) | Lane line detection method, lane line detection equipment, mobile platform and storage medium | |
| CN112115800A (en) | Vehicle combination recognition system and method based on deep learning target detection | |
| CN103680145B (en) | A kind of people's car automatic identifying method based on local image characteristics | |
| CN103106400B (en) | A kind of method for detecting human face and device | |
| CN107507140A (en) | The outdoor scene vehicle shadow disturbance restraining method of highway of feature based fusion | |
| CN108563997B (en) | Method and device for establishing face detection model and face recognition | |
| CN112669615B (en) | Parking space detection method and system based on camera | |
| CN102542304B (en) | Region segmentation skin-color algorithm for identifying WAP (Wireless Application Protocol) mobile porn image | |
| CN105574511B (en) | Have the adaptability object sorter and its method of parallel framework | |
| CN111968078A (en) | Appearance detection method, device, equipment and storage medium for power transformation equipment | |
| Priya et al. | Intelligent parking system | |
| Rajesh et al. | Smart Parking system using Image processing | |
| CN104616007A (en) | Vehicle identification method based on significant detection and color histogram models | |
| CN114283361A (en) | Method and apparatus for determining status information, storage medium, and electronic apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150422 Termination date: 20171226 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |