CN105005780A - License plate identification method - Google Patents
License plate identification method Download PDFInfo
- Publication number
- CN105005780A CN105005780A CN201510371902.0A CN201510371902A CN105005780A CN 105005780 A CN105005780 A CN 105005780A CN 201510371902 A CN201510371902 A CN 201510371902A CN 105005780 A CN105005780 A CN 105005780A
- Authority
- CN
- China
- Prior art keywords
- license plate
- character
- image
- carried out
- recognition method
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a license plate identification method. By a plurality of steps of carrying out shooting, analog-digital conversion, dual positioning, preprocessing, character segmentation and identification and the like, complete automatic identification of a license plate is implemented, wherein a positioning method comprises the steps of identifying blue by adopting an HSV model, identifying white by an RGB model, respectively scanning blue pixel points in the vertical direction and white pixel points in the horizontal direction so as to find out a license plate region and extracting the positioned region; the preprocessing method comprises the steps of carrying out gray processing and gray stretching on the positioned region; the gray stretching is implemented by a gray regulating function imadjust () of matlab. The license plate identification method has a good identification effect, does not require Artificial participation and has a high automation degree. The license plate identification method not only can be applied to the field of traffic monitoring, but also can be applied to the field of other detection and identification and has wide application prospect.
Description
Technical field
The present invention relates to image processing field, particularly relate to a kind of licence plate recognition method.
Background technology
Along with the dramatic change of traffic environment and instrument, the quantity of automobile grows with each passing day, and adopts Vehicle License Plate Recognition System to the inexorable trend that automobile carries out intellectuality, automatic management becomes social development.
License plate recognition technology (Vehicle License Plate Recognition, VLPR) is the one application of Video Image recognition technology in License Plate Identification.
License plate recognition technology requires the license plate in motion to be extracted and identifies from complex background, by technology such as license plate retrieving, Image semantic classification, feature extraction, Recognition of License Plate Characters, identify vehicle identification number, this technology is widely applied in vehicle on highway management, multiple field such as electronic charging (ETC) system, parking lot management etc.
As the Main Means identifying testing vehicle register, license plate recognition technology advances traffic administration to one of gordian technique of intelligent development.Pass through Car license recognition, many important informations of vehicle can be obtained, thus greatly can promote the intelligence degree of transportation system management, current, the development that Car license recognition is existing larger technically, and in the face of day by day complicated traffic environment, the complexity of image, the power of light, the real current situation of car plate and the realization of the travel speed of vehicle to Recognition Algorithm of License Plate are had higher requirement.
License plate recognition technology requires the license plate in motion to be extracted and identifies from complex background, by pre-service, License Plate, character cutting, identification, thus finally identify vehicle license, and the performance that outstanding license plate recognition technology all possesses excellence in recognition correct rate, recognition time, recognition speed etc. can be applied among the recognition system with reality.
Summary of the invention
Technical matters to be solved by this invention is to invent a kind of licence plate recognition method, thus robotization obtains the important information of vehicle, promotes the intelligence degree in traffic administration.
The present invention is achieved in that a kind of licence plate recognition method, comprises the steps:
S1. monitor vehicular traffic, when detecting that vehicle passes through the target area of presetting, starting camera and taking pictures, described vehicle license plate background color is blue, and license board information is white;
S2. the image photographed is carried out quantification and becomes digital form image by described camera, and transfers to graphics processing unit;
S3. described graphics processing unit carries out initial alignment to image, and described initial alignment is for position license plate area;
S4. pre-service is carried out to the region behind location;
S5. Character segmentation is carried out to pretreated car plate;
S6. character recognition is carried out to car plate;
Described initial alignment method is: adopt HSV Model Identification blue, by RGB Model Identification white, scans the blue pixel point of vertical direction and the white pixel point of horizontal direction respectively, thus finds out license plate area, and by the extracted region behind described location out;
Described preprocess method is: the region behind described location is carried out gray processing and gray scale stretching, and gray scale Tuning function imadjust () that described gray scale stretching is carried by use matlab realizes.
Preferably, after initial alignment, also carry out area filter to image, obtain the region behind location, the principle of described area filter comprises the length breadth ratio in the region behind described location.
Preferably, described length breadth ratio is 2.5 ~ 3.5.
Preferably, the region behind described location is positioned within the coverage of image predeterminable area.
Preferably, described predeterminable area is region, image bottom 1/3 ~ 1/4.
Preferably, use closure operation in S5, corrosion erasing is not the part of automotive license plate.
Preferably, in S6, cut out the border of each character in car plate, according to each character boundary, slant correction is carried out to each character, and the character in the template base of each character and pre-stored is compared, thus complete Car license recognition.
Preferably, described length breadth ratio and predeterminable area can rule of thumb be arranged.
Implement the present invention, there is following beneficial effect:
The invention provides a kind of licence plate recognition method, by carrying out automatic camera, automatically location to car plate and automatically identifying, realize the full-automatic identification of car plate.Recognition effect of the present invention is good, and do not need artificial participation, automaticity is high.The present invention both can be applied to traffic monitoring field also can be applied to other detection and Identification fields, has broad application prospects.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly, below the present invention is described in further detail.
Embodiments provide a kind of licence plate recognition method, comprise the steps:
S1. monitor vehicular traffic, when detecting that vehicle passes through the target area of presetting, starting camera and taking pictures, described vehicle background color is blue, and license board information is white;
S2. the image photographed is carried out quantification and becomes digital form image by described camera, and transfers to graphics processing unit;
S3. described graphics processing unit carries out initial alignment to image, and described initial alignment is for position license plate area;
S4. pre-service is carried out to the region behind location;
S5. Character segmentation is carried out to pretreated car plate;
S6. character recognition is carried out to car plate;
Described initial alignment method is: adopt HSV Model Identification blue, by RGB Model Identification white, scans the blue pixel point of vertical direction and the white pixel point of horizontal direction respectively, thus finds out license plate area, and by the extracted region behind described location out;
Described preprocess method is: the region behind described location is carried out gray processing and gray scale stretching, and gray scale Tuning function imadjust () that described gray scale stretching is carried by use matlab realizes.
Preferably, after initial alignment, also carry out area filter to image, obtain the region behind location, the principle of described area filter comprises the length breadth ratio in the region behind described location.
Preferably, described length breadth ratio is 2.5.
Preferably, the region behind described location is positioned within the coverage of image predeterminable area.
Preferably, described predeterminable area is region, image bottom 1/3.
Preferably, use closure operation in S5, corrosion erasing is not the part of automotive license plate.
Preferably, in S6, cut out the border of each character in car plate, according to each character boundary, slant correction is carried out to each character, and the character in the template base of each character and pre-stored is compared, thus complete Car license recognition.
Preferably, described length breadth ratio and predeterminable area can rule of thumb be arranged.
Another embodiment, a kind of licence plate recognition method, comprises the steps:
S1. monitor vehicular traffic, when detecting that vehicle passes through the target area of presetting, starting camera and taking pictures, described vehicle background color is blue, and license board information is white;
S2. the image photographed is carried out quantification and becomes digital form image by described camera, and transfers to graphics processing unit;
S3. described graphics processing unit carries out initial alignment to image, and described initial alignment is for position license plate area;
S4. pre-service is carried out to the region behind location;
S5. Character segmentation is carried out to pretreated car plate;
S6. character recognition is carried out to car plate;
Described initial alignment method is: adopt HSV Model Identification blue, by RGB Model Identification white, scans the blue pixel point of vertical direction and the white pixel point of horizontal direction respectively, thus finds out license plate area, and by the extracted region behind described location out;
Described preprocess method is: the region behind described location is carried out gray processing and gray scale stretching, and gray scale Tuning function imadjust () that described gray scale stretching is carried by use matlab realizes.
Preferably, after initial alignment, also carry out area filter to image, obtain the region behind location, the principle of described area filter comprises the length breadth ratio in the region behind described location.
Preferably, described length breadth ratio is 3.5.
Preferably, the region behind described location is positioned within the coverage of image predeterminable area.
Preferably, described predeterminable area is region, image bottom 1/4.
Preferably, use closure operation in S5, corrosion erasing is not the part of automotive license plate.
Preferably, in S6, cut out the border of each character in car plate, according to each character boundary, slant correction is carried out to each character, and the character in the template base of each character and pre-stored is compared, thus complete Car license recognition.
Preferably, described length breadth ratio and predeterminable area can rule of thumb be arranged
Above disclosedly be only present pre-ferred embodiments, certainly can not limit the interest field of the present invention with this, therefore according to the equivalent variations that the claims in the present invention are done, still belong to the scope that the present invention is contained.
Claims (8)
1. a licence plate recognition method, is characterized in that, comprises the steps:
S1. monitor vehicular traffic, when detecting that vehicle passes through the target area of presetting, starting camera and taking pictures, described vehicle license plate background color is blue, and license board information is white;
S2. the image photographed is carried out quantification and becomes digital form image by described camera, and transfers to graphics processing unit;
S3. described graphics processing unit carries out initial alignment to image, and described initial alignment is for position license plate area;
S4. pre-service is carried out to the region behind location;
S5. Character segmentation is carried out to pretreated car plate;
S6. character recognition is carried out to car plate;
Described initial alignment method is: adopt HSV Model Identification blue, by RGB Model Identification white, scans the blue pixel point of vertical direction and the white pixel point of horizontal direction respectively, thus finds out license plate area, and by the extracted region behind described location out;
Described preprocess method is: the region behind described location is carried out gray processing and gray scale stretching, and gray scale Tuning function imadjust () that described gray scale stretching is carried by use matlab realizes.
2. a kind of licence plate recognition method according to claim 1, is characterized in that, after initial alignment, also carry out area filter to image, obtains the region behind location, and the principle of described area filter comprises the length breadth ratio in the region behind described location.
3. a kind of licence plate recognition method according to claim 2, is characterized in that, described length breadth ratio is 2.5 ~ 3.5.
4. a kind of licence plate recognition method according to Claims 2 or 3, is characterized in that, the region behind described location is positioned within the coverage of image predeterminable area.
5. a kind of licence plate recognition method according to claim 4, is characterized in that, described predeterminable area is region, image bottom 1/3 ~ 1/4.
6. a kind of licence plate recognition method according to claim 1, is characterized in that, use closure operation in S5, and corrosion erasing is not the part of automotive license plate.
7. a kind of licence plate recognition method according to claim 6, it is characterized in that, the border of each character in car plate is cut out in S6, according to each character boundary, slant correction is carried out to each character, and compared by the character in the template base of each character and pre-stored, thus complete Car license recognition.
8. a kind of licence plate recognition method according to claim 5, is characterized in that, described length breadth ratio and predeterminable area can rule of thumb be arranged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510371902.0A CN105005780A (en) | 2015-06-29 | 2015-06-29 | License plate identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510371902.0A CN105005780A (en) | 2015-06-29 | 2015-06-29 | License plate identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105005780A true CN105005780A (en) | 2015-10-28 |
Family
ID=54378445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510371902.0A Pending CN105005780A (en) | 2015-06-29 | 2015-06-29 | License plate identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105005780A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105930831A (en) * | 2016-05-19 | 2016-09-07 | 湖南博广信息科技有限公司 | License plate intelligent identification method |
| WO2017124303A1 (en) * | 2016-01-19 | 2017-07-27 | 冯旋宇 | License plate recognition method and system for intelligent transportation |
| CN110188751A (en) * | 2019-05-20 | 2019-08-30 | 福建福清核电有限公司 | A kind of M310 nuclear power unit equipment label position image-recognizing method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102364496A (en) * | 2011-11-24 | 2012-02-29 | 无锡慧眼电子科技有限公司 | Method and system for identifying automobile license plates automatically based on image analysis |
| CN102750703A (en) * | 2012-06-27 | 2012-10-24 | 北京航空航天大学 | Remote sensing image airport automatic detecting method based on linear cutting |
| CN102902957A (en) * | 2012-09-05 | 2013-01-30 | 佳都新太科技股份有限公司 | Video-stream-based automatic license plate recognition method |
| CN102945367A (en) * | 2012-11-26 | 2013-02-27 | 昆山振天智能化设备有限公司 | Vehicle license plate recognition system |
| US20130163822A1 (en) * | 2006-04-04 | 2013-06-27 | Cyclops Technologies, Inc. | Airborne Image Capture and Recognition System |
| CN104680163A (en) * | 2015-02-10 | 2015-06-03 | 柳州市金旭节能科技有限公司 | Licence plate recognition system |
-
2015
- 2015-06-29 CN CN201510371902.0A patent/CN105005780A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130163822A1 (en) * | 2006-04-04 | 2013-06-27 | Cyclops Technologies, Inc. | Airborne Image Capture and Recognition System |
| CN102364496A (en) * | 2011-11-24 | 2012-02-29 | 无锡慧眼电子科技有限公司 | Method and system for identifying automobile license plates automatically based on image analysis |
| CN102750703A (en) * | 2012-06-27 | 2012-10-24 | 北京航空航天大学 | Remote sensing image airport automatic detecting method based on linear cutting |
| CN102902957A (en) * | 2012-09-05 | 2013-01-30 | 佳都新太科技股份有限公司 | Video-stream-based automatic license plate recognition method |
| CN102945367A (en) * | 2012-11-26 | 2013-02-27 | 昆山振天智能化设备有限公司 | Vehicle license plate recognition system |
| CN104680163A (en) * | 2015-02-10 | 2015-06-03 | 柳州市金旭节能科技有限公司 | Licence plate recognition system |
Non-Patent Citations (2)
| Title |
|---|
| 孙玉芹: "车牌自动识别方法研究", 《中国优秀硕士学位论文全文数据库.信息科技辑》 * |
| 陈永超: "基于数字图像处理的车牌识别研究", 《中国优秀硕士学位论文全文数据库.信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017124303A1 (en) * | 2016-01-19 | 2017-07-27 | 冯旋宇 | License plate recognition method and system for intelligent transportation |
| CN105930831A (en) * | 2016-05-19 | 2016-09-07 | 湖南博广信息科技有限公司 | License plate intelligent identification method |
| CN110188751A (en) * | 2019-05-20 | 2019-08-30 | 福建福清核电有限公司 | A kind of M310 nuclear power unit equipment label position image-recognizing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110069986B (en) | Traffic signal lamp identification method and system based on hybrid model | |
| CN107506760B (en) | Traffic signal detection method and system based on GPS positioning and visual image processing | |
| Omachi et al. | Detection of traffic light using structural information | |
| Saha et al. | License Plate localization from vehicle images: An edge based multi-stage approach | |
| CN202563526U (en) | Transportation vehicle detection and recognition system based on video | |
| CN107016362B (en) | Vehicle weight recognition method and system based on vehicle front windshield pasted mark | |
| CN102637257A (en) | Video-based detection and recognition system and method of vehicles | |
| CN101334836A (en) | License plate positioning method incorporating color, size and texture characteristic | |
| CN109215364B (en) | Traffic signal recognition method, system, device and storage medium | |
| CN108198417B (en) | A kind of road cruising inspection system based on unmanned plane | |
| CN107180230B (en) | Universal license plate recognition method | |
| CN106919939B (en) | A kind of traffic signboard tracks and identifies method and system | |
| CN106709412B (en) | Traffic sign detection method and device | |
| CN102902957A (en) | Video-stream-based automatic license plate recognition method | |
| CN112863194B (en) | Image processing method, device, terminal and medium | |
| CN111881832A (en) | Lane target detection method, device, equipment and computer readable storage medium | |
| Grbić et al. | Automatic vision-based parking slot detection and occupancy classification | |
| CN105022992A (en) | Automatic identification method of vehicle license plate | |
| CN105005780A (en) | License plate identification method | |
| Ghahremannezhad et al. | Automatic road detection in traffic videos | |
| CN109800693B (en) | Night vehicle detection method based on color channel mixing characteristics | |
| Chowdhury et al. | An adaptive technique for computer vision based vehicles license plate detection system | |
| CN103903449B (en) | A kind of vehicle on highway lookup method based on license plate recognition technology | |
| Philipsen et al. | Ongoing work on traffic lights: Detection and evaluation | |
| Deb et al. | Parallelogram and histogram based vehicle license plate detection |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20151028 |