CN103886313A - Method for locating license plates at gas station - Google Patents
Method for locating license plates at gas station Download PDFInfo
- Publication number
- CN103886313A CN103886313A CN201410133641.4A CN201410133641A CN103886313A CN 103886313 A CN103886313 A CN 103886313A CN 201410133641 A CN201410133641 A CN 201410133641A CN 103886313 A CN103886313 A CN 103886313A
- Authority
- CN
- China
- Prior art keywords
- image
- car plate
- locating
- filtering
- gas station
- 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
Abstract
The invention relates to a method for locating license plates at a gas station. The method mainly solves the problem that at present no method for locating the license plates at the gas station exists. The method for locating the license plates at gas station comprises the following steps: 1, acquiring a source image; 2, conducting preprocessing on the source image, wherein the step 2 comprises the sub-steps of image graying, wavelet transform and image filtering; 3, filtering interference points, wherein edge detection is conducted on the image after preprocessing, corrosion and a closed operation are conducted on a detected result, the transverse and longitudinal interference points of the image are filtered through a bwareaopen function, and the closed operation is conducted on the image; 4, fusing edge points; 5, outputting a locating result. By means of the method based on combination of mathematical morphology, edge detection and colors, accurate locating of the license plates at the gas station is achieved, locating precision is high, and locating speed is fast. The method for locating the license plates at the gas station is applied to identification of the license plates at the gas station.
Description
Technical field
The present invention relates to image recognition technology field, be specifically related to a kind of refuelling station license plate locating method.
Background technology
Car plate is the outstanding feature of each car authentication, obtains the license plate number of vehicle, just equals to know the various important informations in vehicle archives, be convenient to vehicle to supervise, therefore, the widespread use of modern traffic control system active demand license plate recognition technology.License plate recognition technology is one of important component part in modern intelligent transportation system, applies very extensive.It is take technology such as Digital Image Processing, pattern-recognition, Computer Analysis as basis, and vehicle image or video sequence to shot by camera are analyzed, and obtain the unique number-plate number of each automobile, thus the identifying of completing.Refuelling station is one provides the Code in Hazardous Special Locations of fuel oil and lubricating oil for various vehicles, have that vehicle flowrate is large, down time is long, vehicle mixes, the background color of car plate and the color of character varied with the different feature of car plate hanging position height, license plate number relatively easily gathers, be necessary to install Vehicle License Plate Recognition System, can be public security department false-trademark vehicle, deck vehicle, the stolen and information of plundering vehicle and hit-and-run vehicle are provided, attack the criminal offence that relates to vehicle seriously, ensure citizen's safety of life and property.
Position System of automobile license plate location is as the important component part of Vehicle License Plate Recognition System, its effect is the position that provides car plate in image, for License Plate Character Segmentation and Recognition of License Plate Characters work provide element task, at present, Position System of automobile license plate location existing domestic and international experts and scholars research and develop, for parking lot management and road management violating the regulations, but because the vehicle of refuelling station mixes, the background color of car plate and the color of character are varied, car plate hanging position height is different, at present at home to the research of refuelling station's Position System of automobile license plate location still in the starting stage, also there is no effective refuelling station license plate locating method.
Summary of the invention
The present invention is not also specifically designed to the license plate locating method of refuelling station at present for solving, and proposes a kind of refuelling station license plate locating method.
A kind of refuelling station license plate locating method, carries out according to the following steps:
1, gather source images: have the position of licence plate to take pictures to vehicle, use Visible Light Camera daytime, use thermal infrared imager night;
2, source images is carried out to pre-service: comprise image gray processing and wavelet image filtering;
Gray processing processing can improve processing speed, reduce to take up room; Wavelet image filtering can make image regularization, reduces the contradiction of time and frequency resolution;
3, noise spot filtering: pretreated image is carried out to rim detection, the result detecting is carried out to burn into closed operation, then use bwareaopen function that horizontal, longitudinal noise spot is considered and removed to the image of closed operation;
Use bwareaopen function, according to the colour match filtering interfering edge of the background color of car plate and character, then according to car plate transverse features filtering interfering edge, obtain transverse edge point, then use the longitudinal filtering interfering point of bwareaopen function, obtain longitudinal edge point;
4, marginal point merges: the transverse edge point obtaining in step 3 is connected to fusion with longitudinal edge point;
5, output positioning result: transverse edge point is connected with longitudinal edge point after fusion, obtain connected component labeling, then according to shape, environment, connected component labeling is carried out to the screening of car plate district based on Ababoost algorithm, positioning result is finally exported at filtering interfering edge;
First according to car plate rectangular shape screening car plate district, then according to car plate surrounding environment Feature Selection car plate district, then according to vertical projection Feature Selection car plate district, finally based on Ababoost algorithm screening car plate district, and positioning result is exported.
The present invention includes following beneficial effect:
1, the present invention is based on the accurate location that method that mathematical morphology and rim detection and color combine realizes refuelling station's car plate, positioning precision is high, and locating speed is fast;
2, source images is carried out to image gray processing and wavelet image filter preprocessing, can improve processing speed, reduce to take up room, make image regularization, reduce the contradiction of time and frequency resolution;
3, the inventive method takes into full account the feature of turnover refuelling station vehicle self, and car plate position fixing process is simple, is conducive to adopt Vehicle License Plate Recognition System to hit the criminal offence of vehicle.
Accompanying drawing explanation
The process flow diagram that accompanying drawing 1 is the inventive method.
Embodiment
Embodiment one: a kind of refuelling station license plate locating method, carries out according to the following steps:
1, gather source images: have the position of licence plate to take pictures to vehicle, use Visible Light Camera daytime, use thermal infrared imager night;
2, source images is carried out to pre-service: comprise image gray processing and wavelet image filtering;
Gray processing processing can improve processing speed, reduce to take up room; Wavelet image filtering can make image regularization, reduces the contradiction of time and frequency resolution;
3, noise spot filtering: pretreated image is carried out to rim detection, the result detecting is carried out to burn into closed operation, then use bwareaopen function that horizontal, longitudinal noise spot is considered and removed to the image of closed operation;
Use bwareaopen function, according to the colour match filtering interfering edge of the background color of car plate and character, then according to car plate transverse features filtering interfering edge, obtain transverse edge point, then use the longitudinal filtering interfering point of bwareaopen function, obtain longitudinal edge point;
4, marginal point merges: the transverse edge point obtaining in step 3 is connected to fusion with longitudinal edge point;
5, output positioning result: transverse edge point is connected with longitudinal edge point after fusion, obtain connected component labeling, then according to shape, environment, connected component labeling is carried out to the screening of car plate district based on Ababoost algorithm, positioning result is finally exported at filtering interfering edge;
First according to car plate rectangular shape screening car plate district, then according to car plate surrounding environment Feature Selection car plate district, then according to vertical projection Feature Selection car plate district, finally based on Ababoost algorithm screening car plate district, and positioning result is exported.
Embodiment two: present embodiment is that embodiment one is described further, when have the position of licence plate to take pictures to vehicle night in step 1, have lighting.
Embodiment three: present embodiment is that embodiment one is described further, and in step 2, source images is carried out to pre-service, first carries out image gray processing processing, then carries out wavelet image filtering processing.
Claims (3)
1. refuelling station's license plate locating method, is characterized in that carrying out according to the following steps:
A, collection source images: have the position of licence plate to take pictures to vehicle, use Visible Light Camera daytime, use thermal infrared imager night;
B, source images is carried out to pre-service: comprise image gray processing and wavelet image filtering;
C, noise spot filtering: pretreated image is carried out to rim detection, the result detecting is carried out to burn into closed operation, then use bwareaopen function that horizontal, longitudinal noise spot is considered and removed to the image of closed operation;
Use bwareaopen function, according to the colour match filtering interfering edge of the background color of car plate and character, then according to car plate transverse features filtering interfering edge, obtain transverse edge point, then use the longitudinal filtering interfering point of bwareaopen function, obtain longitudinal edge point;
D, marginal point merge: the transverse edge point obtaining in step c is connected to fusion with longitudinal edge point;
E, output positioning result: transverse edge point is connected with longitudinal edge point after fusion, obtain connected component labeling, then according to shape, environment, connected component labeling is carried out to the screening of car plate district based on Ababoost algorithm, positioning result is finally exported at filtering interfering edge;
First according to car plate rectangular shape screening car plate district, then according to car plate surrounding environment Feature Selection car plate district, then according to vertical projection Feature Selection car plate district, finally based on Ababoost algorithm screening car plate district, and positioning result is exported.
2. a kind of refuelling station according to claim 1 license plate locating method, while it is characterized in that in step a, have the position of licence plate to take pictures to vehicle night, have lighting.
3. a kind of refuelling station according to claim 1 license plate locating method, is characterized in that, in step b, source images is carried out to pre-service, first carries out image gray processing processing, then carries out wavelet image filtering processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410133641.4A CN103886313A (en) | 2014-04-03 | 2014-04-03 | Method for locating license plates at gas station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410133641.4A CN103886313A (en) | 2014-04-03 | 2014-04-03 | Method for locating license plates at gas station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103886313A true CN103886313A (en) | 2014-06-25 |
Family
ID=50955196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410133641.4A Pending CN103886313A (en) | 2014-04-03 | 2014-04-03 | Method for locating license plates at gas station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103886313A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111325987A (en) * | 2020-01-20 | 2020-06-23 | 北京微油科技服务有限公司 | Fake plate identification method and device for gas station |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060023937A1 (en) * | 2004-07-30 | 2006-02-02 | Ana Tessadro | Method of measuring occluded features for high precision machine vision metrology |
| CN101520841A (en) * | 2009-03-10 | 2009-09-02 | 北京航空航天大学 | Real-time and anti-interference method for positioning license plate in high-definition TV video |
| CN101937508A (en) * | 2010-09-30 | 2011-01-05 | 湖南大学 | License plate localization and identification method based on high-definition image |
| CN102708356A (en) * | 2012-03-09 | 2012-10-03 | 沈阳工业大学 | Automatic license plate positioning and recognition method based on complex background |
| CN102999753A (en) * | 2012-05-07 | 2013-03-27 | 腾讯科技（深圳）有限公司 | License plate locating method |
-
2014
- 2014-04-03 CN CN201410133641.4A patent/CN103886313A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060023937A1 (en) * | 2004-07-30 | 2006-02-02 | Ana Tessadro | Method of measuring occluded features for high precision machine vision metrology |
| CN101520841A (en) * | 2009-03-10 | 2009-09-02 | 北京航空航天大学 | Real-time and anti-interference method for positioning license plate in high-definition TV video |
| CN101937508A (en) * | 2010-09-30 | 2011-01-05 | 湖南大学 | License plate localization and identification method based on high-definition image |
| CN102708356A (en) * | 2012-03-09 | 2012-10-03 | 沈阳工业大学 | Automatic license plate positioning and recognition method based on complex background |
| CN102999753A (en) * | 2012-05-07 | 2013-03-27 | 腾讯科技（深圳）有限公司 | License plate locating method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111325987A (en) * | 2020-01-20 | 2020-06-23 | 北京微油科技服务有限公司 | Fake plate identification method and device for gas station |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105426864B (en) | One kind being based on the matched Multi-lane Lines Detection method of equidistant marginal point | |
| US20150161796A1 (en) | Method and device for recognizing pedestrian and vehicle supporting the same | |
| CN102426786B (en) | Intelligent video analyzing system and method for automatically identifying fake plate vehicle | |
| CN102542807B (en) | RFID/VFID (Radio Frequency Identification Device/Video Frequency Identification Device) comprehensive comparison intelligent vehicle management system and method | |
| US8339282B2 (en) | Security systems | |
| Nemade | Automatic traffic surveillance using video tracking | |
| CN109409337B (en) | Muck vehicle feature identification method based on convolutional neural network | |
| CN202077142U (en) | Vehicle-mounted intelligent video detecting and analyzing system | |
| CN104504908A (en) | Monitoring method and system for illegal parking | |
| CN103778787B (en) | Automobile false deck recognition logic determination methods | |
| CN111161543A (en) | Automatic snapshot method and system for bus front violation behavior based on image recognition | |
| CN103544481A (en) | Road gate monitoring method and system based on human face recognition | |
| CN105825184A (en) | Vehicle data processing method and device | |
| CN103548069B (en) | For the method and apparatus identifying possible colliding object | |
| IL256942B (en) | Multi-stream based traffic enforcement for complex scenarios | |
| CN105355053B (en) | Disobey parking automatic checkout system in roadside | |
| Shobayo et al. | Development of smart plate number recognition system for fast cars with web application | |
| CN106297308A (en) | A kind of Intelligent electronic license plate identification system | |
| CN105259304A (en) | On-line monitoring system and method for pollutants in vehicle tail gas | |
| CN102496281A (en) | Vehicle red-light violation detection method based on combination of tracking and virtual loop | |
| CN114387785A (en) | Safety management and control method and system based on intelligent highway and storable medium | |
| CN107393311B (en) | A kind of license plate tamper Detection device and method | |
| CN109448390A (en) | A kind of vehicles management method, equipment and storage equipment | |
| CN103810859A (en) | Technology for completely eradicating fake and imitated license plates in current toll-gate and electronic police systems | |
| Yaseen et al. | Development of new Anpr dataset for automatic number plate detection and recognition in north of Iraq |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140625 |