CN103207992A - Character and color combined recognition method of license plates - Google Patents
Character and color combined recognition method of license plates Download PDFInfo
- Publication number
- CN103207992A CN103207992A CN2013101176980A CN201310117698A CN103207992A CN 103207992 A CN103207992 A CN 103207992A CN 2013101176980 A CN2013101176980 A CN 2013101176980A CN 201310117698 A CN201310117698 A CN 201310117698A CN 103207992 A CN103207992 A CN 103207992A
- Authority
- CN
- China
- Prior art keywords
- character
- color
- area
- license plate
- license
- 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 discloses a character and color combined recognition method of license plates. The character and color combined recognition method includes steps of: 1) positioning a vehicle plate area in an image; 2) dividing the vehicle plate area into a character area and a background area; and 3) recognizing the color of the background area, and recognizing the characters of the character area. Compared with the prior art, the character and color combined recognition method has the advantages of fast achieving combined recognition on characters and color, being improved in recognition accuracy compared with other methods, and achieving two recognition results. The total character recognition rate of 98% reaches the international advanced level, and the color of the vehicle plates can be accurately recognized.
Description
Technical field
The invention belongs to " computer vision " and " pattern-recognition " field, refer to a kind of recognition methods of vehicle license especially.
Background technology
Along with expanding economy, automobile is more and more, and popularizing of automobile become inevitable trend.The robotization of traffic administration, intelligent transportation system are the development trends of 21 century world's road traffic.The continuous development of highway communication capital construction and vehicle management system constantly perfect is for the practical application based on the intelligent transportation system of vision monitoring is laid a good foundation.In intelligent transportation system, automatic license plate identification system is a very important developing direction.
Along with the demand increase of the full-automatic supervisory system of vehicle, market presses for the Vehicle License Plate Recognition System that performance better can provide comprehensive information, needs identification character and color simultaneously.Yet, yet there are no the vehicle license recognition methods of energy while identification character and color.
Summary of the invention
At the problem that prior art exists, order of the present invention is to provide a kind of character that can accurately identify on the car plate, also can identify the vehicle license recognition methods of the color of car plate simultaneously.
For achieving the above object, vehicle license character of the present invention and color associating recognition methods may further comprise the steps: 1) locate license plate area in image; 2) license plate area is divided into character zone and background area; 3) color identification is carried out in the background area, character zone is carried out character recognition.
Further, step 1) specifically comprises: license plate area pre-determined bit and license plate area are finally located.
Further, described license plate area pre-determined bit specifically comprises: search for the rectangular area according to frequency spectrum in image, judge according to the size characteristic of this rectangular area whether this rectangular area is license plate area.
Further, in the rectangular area of judging through size characteristic, extract the feature of character shape feature, character arrangement linearity feature, character stroke width unanimity, and judge further whether this rectangular area is license plate area.
Further, the final location of described license plate area specifically comprises: the license plate area that obtains through the license plate area pre-determined bit is carried out gray processing, trimming frame, removes the gold-plating nail; Then, the method that adopts a kind of vertical projection, connected region, situation template to combine is come out Character segmentation, further judges whether to be license plate area according to the character number that is partitioned into.
Further, step 2) specifically comprise: in the license plate area of location, finding character definition is character zone, and the license plate area of non-character stroke is defined as the background area.
Further, the color identification method of background area is specially in the step 3): each pixel in the statistics car plate background area, add up the color of each pixel in the car plate background area then, judge the car plate color according to different colours pixel number purpose comparative result in the car plate background area.
Further, the color approach of each pixel is in the statistics car plate background area: the rgb value of each pixel is transferred to the hsv color value, and classify with sorter, what pixels add up shades of colour then has respectively.
Further, the character identifying method of character zone is specially in the step 3): each character in the license plate area is extracted, character size is carried out normalization, and extract the Gabor statistical nature of character, classify with SVM or multilayer neural network afterwards.
Compared with prior art, the invention has the beneficial effects as follows that realized the identification of uniting of the identification of character and color rapidly, the identification accuracy increases than other method, and two kinds of recognition results have all been realized.Its overall character identification rate has reached the leading level in the world, reaches 98%, and the identification of car plate color is very accurate.
Description of drawings
Fig. 1 is the process flow diagram of vehicle license character of the present invention and color associating recognition methods.
Embodiment
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described in further detail.Following examples are used for explanation the present invention, but do not limit protection scope of the present invention.
The invention provides a kind of vehicle license character and color associating recognition methods, it can accurately identify the character on the car plate, also can identify the color of car plate simultaneously.
As shown in Figure 1, the technical solution adopted in the present invention is: advanced driving board pre-determined bit, and carry out Character segmentation then and judge license plate area, identify car plate color and characters on license plate again, export recognition result at last.
At first carry out the car plate pre-determined bit, the size characteristic that this is regional is judged in search Frequency spectrum ratio higher rectangular area in image, have only satisfy wide be high more than 2 times could be as car plate.In this zone, extract the information such as feature of character shape feature, character arrangement linearity feature, character stroke width unanimity, judge further whether this zone is car plate.Through after the car plate pre-determined bit, owing to be coated with information such as advertisement on the car plate, final to judge that the license plate area that draws may have a plurality of, this just need carry out Character segmentation further judgement which is only real license plate area actually.
Carry out Character segmentation then, in the license plate area to pre-determined bit, car plate is carried out gray processing, trimming frame, goes operations such as gold-plating nail.Then, the method that adopts a kind of vertical projection, connected region, situation template to combine is come out Character segmentation.The Character segmentation priori is because the character boundary of car plate and spacing are all fixed.If can accurately cut apart the character that finds about 7, just car plate is used as in this zone, otherwise is just thought that it is not car plate.Thereby in the tabulation of candidate's license plate area, find real license plate area.
Identification for the car plate color, in the license plate area behind the location, find character, to the license plate area of non-character stroke, add up its each pixel, the rgb value of each pixel is transferred to the hsv color value, and classify with sorter, what pixels add up shades of colour then has respectively, and last pixel color is maximum, is exactly the car plate color.The car plate color generally has 4 kinds, and blue, yellow, white, black divide time-like to select 1 to judge that it belongs to any color and gets final product with regard to 4.
For the identification of character, each character is extracted, character size is carried out normalization, and extract the Gabor statistical nature of character, classify with SVM or multilayer neural network afterwards.The method that the Gabor feature combines with SVM or neural network has improved discrimination greatly, particularly to the discrimination of Chinese character.Because the Gabor feature has translation invariance, can embody the feature details of Chinese character.
Claims (9)
1. vehicle license character and color associating recognition methods is characterized in that, may further comprise the steps: 1) locate license plate area in image; 2) license plate area is divided into character zone and background area; 3) color identification is carried out in the background area, character zone is carried out character recognition.
2. vehicle license character according to claim 1 and color associating recognition methods, it is characterized in that step 1) specifically comprises: license plate area pre-determined bit and license plate area are finally located.
3. vehicle license character according to claim 2 and color associating recognition methods, it is characterized in that, described license plate area pre-determined bit specifically comprises: search for the rectangular area according to frequency spectrum in image, judge according to the size characteristic of this rectangular area whether this rectangular area is license plate area.
4. vehicle license character according to claim 3 and color associating recognition methods, it is characterized in that, in the rectangular area of judging through size characteristic, extract the feature of character shape feature, character arrangement linearity feature, character stroke width unanimity, and judge further whether this rectangular area is license plate area.
5. according to claim 3 or 4 described vehicle license characters and color associating recognition methods, it is characterized in that the final location of described license plate area specifically comprises: the license plate area that obtains through the license plate area pre-determined bit is carried out gray processing, trimming frame, removes the gold-plating nail; Then, the method that adopts a kind of vertical projection, connected region, situation template to combine is come out Character segmentation, further judges whether to be license plate area according to the character number that is partitioned into.
6. vehicle license character according to claim 1 and color associating recognition methods is characterized in that step 2) specifically comprise: in the license plate area of location, finding character definition is character zone, and the license plate area of non-character stroke is defined as the background area.
7. vehicle license character according to claim 1 and color associating recognition methods, it is characterized in that, the color identification method of background area is specially in the step 3): each pixel in the statistics car plate background area, add up the color of each pixel in the car plate background area then, judge the car plate color according to different colours pixel number purpose comparative result in the car plate background area.
8. vehicle license character according to claim 7 and color associating recognition methods, it is characterized in that, the color approach of each pixel is in the statistics car plate background area: the rgb value of each pixel is transferred to the hsv color value, and classify with sorter, what pixels add up shades of colour then has respectively.
9. vehicle license character according to claim 1 and color associating recognition methods, it is characterized in that, the character identifying method of character zone is specially in the step 3): each character in the license plate area is extracted, character size is carried out normalization, and the Gabor statistical nature of extraction character, classify with SVM or multilayer neural network afterwards.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101176980A CN103207992A (en) | 2013-04-07 | 2013-04-07 | Character and color combined recognition method of license plates |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101176980A CN103207992A (en) | 2013-04-07 | 2013-04-07 | Character and color combined recognition method of license plates |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103207992A true CN103207992A (en) | 2013-07-17 |
Family
ID=48755209
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013101176980A Pending CN103207992A (en) | 2013-04-07 | 2013-04-07 | Character and color combined recognition method of license plates |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103207992A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971097A (en) * | 2014-05-15 | 2014-08-06 | 武汉睿智视讯科技有限公司 | Vehicle license plate recognition method and system based on multiscale stroke models |
| CN104268509A (en) * | 2014-09-17 | 2015-01-07 | 深圳市捷顺科技实业股份有限公司 | Method and system for detecting license plate of dump truck |
| CN106530732A (en) * | 2016-11-08 | 2017-03-22 | 合肥掌韵车聚信息科技有限公司 | Parking lot video vehicle license plate recognition system based on ORC technology |
| CN107590500A (en) * | 2017-07-20 | 2018-01-16 | 济南中维世纪科技有限公司 | A kind of color recognizing for vehicle id method and device based on color projection classification |
| CN108334881A (en) * | 2018-03-12 | 2018-07-27 | 南京云创大数据科技股份有限公司 | A kind of licence plate recognition method based on deep learning |
| CN108647689A (en) * | 2018-06-01 | 2018-10-12 | 中国科学院福建物质结构研究所 | Magic square restored method and its device based on GoogLeNet neural networks |
| CN109558872A (en) * | 2018-11-22 | 2019-04-02 | 四川大学 | A kind of vehicle color identification method |
| CN111126383A (en) * | 2019-12-06 | 2020-05-08 | 广州烽火众智数字技术有限公司 | License plate detection method, system, device and storage medium |
| CN111444911A (en) * | 2019-12-13 | 2020-07-24 | 珠海大横琴科技发展有限公司 | Training method and device of license plate recognition model and license plate recognition method and device |
| CN111860539A (en) * | 2020-07-20 | 2020-10-30 | 济南博观智能科技有限公司 | License plate color recognition method, device and medium |
| CN113112503A (en) * | 2021-05-10 | 2021-07-13 | 上海贝德尔生物科技有限公司 | Method for realizing automatic detection of medicine label based on machine vision |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2246894A (en) * | 1990-06-13 | 1992-02-12 | Matsushita Electric Ind Co Ltd | Licence plate recognition system |
| CN1725266A (en) * | 2004-07-21 | 2006-01-25 | 上海高德威智能交通系统有限公司 | Vehicle intelligent monitoring recording syste mand method based on video trigger and speed measuring |
-
2013
- 2013-04-07 CN CN2013101176980A patent/CN103207992A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2246894A (en) * | 1990-06-13 | 1992-02-12 | Matsushita Electric Ind Co Ltd | Licence plate recognition system |
| CN1725266A (en) * | 2004-07-21 | 2006-01-25 | 上海高德威智能交通系统有限公司 | Vehicle intelligent monitoring recording syste mand method based on video trigger and speed measuring |
Non-Patent Citations (1)
| Title |
|---|
| 徐武妮: "车辆牌照自动识别算法改进研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, 15 August 2011 (2011-08-15) * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971097B (en) * | 2014-05-15 | 2015-05-13 | 武汉睿智视讯科技有限公司 | Vehicle license plate recognition method and system based on multiscale stroke models |
| CN103971097A (en) * | 2014-05-15 | 2014-08-06 | 武汉睿智视讯科技有限公司 | Vehicle license plate recognition method and system based on multiscale stroke models |
| CN104268509A (en) * | 2014-09-17 | 2015-01-07 | 深圳市捷顺科技实业股份有限公司 | Method and system for detecting license plate of dump truck |
| CN104268509B (en) * | 2014-09-17 | 2018-05-29 | 深圳市捷顺科技实业股份有限公司 | The method and system of dump truck car plate detection |
| CN106530732A (en) * | 2016-11-08 | 2017-03-22 | 合肥掌韵车聚信息科技有限公司 | Parking lot video vehicle license plate recognition system based on ORC technology |
| CN107590500A (en) * | 2017-07-20 | 2018-01-16 | 济南中维世纪科技有限公司 | A kind of color recognizing for vehicle id method and device based on color projection classification |
| CN108334881B (en) * | 2018-03-12 | 2022-04-29 | 南京云创大数据科技股份有限公司 | License plate recognition method based on deep learning |
| CN108334881A (en) * | 2018-03-12 | 2018-07-27 | 南京云创大数据科技股份有限公司 | A kind of licence plate recognition method based on deep learning |
| CN108647689A (en) * | 2018-06-01 | 2018-10-12 | 中国科学院福建物质结构研究所 | Magic square restored method and its device based on GoogLeNet neural networks |
| CN109558872A (en) * | 2018-11-22 | 2019-04-02 | 四川大学 | A kind of vehicle color identification method |
| CN109558872B (en) * | 2018-11-22 | 2022-02-11 | 四川大学 | Vehicle color identification method |
| CN111126383A (en) * | 2019-12-06 | 2020-05-08 | 广州烽火众智数字技术有限公司 | License plate detection method, system, device and storage medium |
| CN111444911A (en) * | 2019-12-13 | 2020-07-24 | 珠海大横琴科技发展有限公司 | Training method and device of license plate recognition model and license plate recognition method and device |
| CN111444911B (en) * | 2019-12-13 | 2021-02-26 | 珠海大横琴科技发展有限公司 | Training method and device of license plate recognition model and license plate recognition method and device |
| CN111860539A (en) * | 2020-07-20 | 2020-10-30 | 济南博观智能科技有限公司 | License plate color recognition method, device and medium |
| CN113112503A (en) * | 2021-05-10 | 2021-07-13 | 上海贝德尔生物科技有限公司 | Method for realizing automatic detection of medicine label based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103207992A (en) | Character and color combined recognition method of license plates | |
| CN101872416B (en) | Vehicle license plate recognition method and system of road image | |
| CN107016362B (en) | Vehicle weight recognition method and system based on vehicle front windshield pasted mark | |
| CN108073928B (en) | License plate recognition method and device | |
| CN103198315B (en) | Based on the Character Segmentation of License Plate of character outline and template matches | |
| CN103226696B (en) | The identification system and method for car plate | |
| CN103136528B (en) | A kind of licence plate recognition method based on dual edge detection | |
| CN101436252A (en) | Method and system for recognizing vehicle body color in vehicle video image | |
| CN102819728A (en) | Traffic sign detection method based on classification template matching | |
| Ellahyani et al. | Traffic sign detection and recognition using features combination and random forests | |
| CN102880863B (en) | Method for positioning license number and face of driver on basis of deformable part model | |
| CN107729812B (en) | Method suitable for recognizing vehicle color in monitoring scene | |
| CN102902957A (en) | Video-stream-based automatic license plate recognition method | |
| CN103345766A (en) | Method and device for identifying signal light | |
| CN109215364B (en) | Traffic signal recognition method, system, device and storage medium | |
| Peng et al. | Vehicle type classification using PCA with self-clustering | |
| CN103390167A (en) | Multi-characteristic layered traffic sign identification method | |
| CN105354533B (en) | A kind of unlicensed vehicle model recognizing method of bayonet based on bag of words | |
| CN102799859A (en) | Method for identifying traffic sign | |
| CN103824091A (en) | Vehicle license plate recognition method for intelligent transportation system | |
| CN103544480A (en) | Vehicle color recognition method | |
| CN102737221B (en) | Method and apparatus for vehicle color identification | |
| CN109657664A (en) | A kind of recognition methods, device and the electronic equipment of license plate type | |
| CN105139011A (en) | Method and apparatus for identifying vehicle based on identification marker image | |
| CN110378317A (en) | A kind of licence plate recognition method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130717 |