CN103226696B - The identification system and method for car plate - Google Patents
The identification system and method for car plate Download PDFInfo
- Publication number
- CN103226696B CN103226696B CN201310117722.0A CN201310117722A CN103226696B CN 103226696 B CN103226696 B CN 103226696B CN 201310117722 A CN201310117722 A CN 201310117722A CN 103226696 B CN103226696 B CN 103226696B
- Authority
- CN
- China
- Prior art keywords
- character
- car plate
- rectangular area
- characters
- judged
- 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
- Character Input (AREA)
- Character Discrimination (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides the recognition methods of a kind of car plate, by its frequency spectrum threshold value of the filtered image setting containing car plate, selecting frequency spectrum to exceed the rectangular area that this threshold value and color are identical with car plate color；Judge whether the shape of this rectangular area meets the shape of car plate, if so, then extract and judge that in described rectangular area, whether the feature of each character is consistent；If it is consistent, then described rectangular area is carried out gray processing, binaryzation, trimming frame and goes gold-plating to follow closely, and each character in this rectangular area is split, judge whether the number of characters after segmentation meets the number of characters of car plate, if so, then judge the whether linear arrangement of each character shape intercharacter whether identical, each after splitting, if, then the size of described each character is normalized, the character statistical nature classification that will extract, exports license plate recognition result；The present invention can quickly recognize the car plate of arbitrary resolution, and its discrimination is high, the strong adaptability to environment；The present invention also provides for the identification system of a kind of car plate.
Description
Technical field
The present invention relates to computer vision and area of pattern recognition, particularly to the identification system and method for a kind of car plate.
Background technology
The automatization of traffic administration, traffic system intellectuality be the development trend of 21 century world's road traffic；In intelligent transportation system, automatic license plate identification system is a very important developing direction.
Along with the demand of vehicle Full-automatic monitoring system increases, market is in the urgent need to the good Vehicle License Plate Recognition System of Performance comparision, especially for the Car license recognition of arbitrary resolution so that nearer from car plate in photographic head higher gears or photographic head, namely, when resolution is big, car plate can be accurately identified；Meanwhile, or photographic head more low-grade at photographic head from car plate farther out time, i.e. resolution hour, remain to accurately identify car plate；Different additionally, due to environment, photographic head model also differs, how developing one can widely used Vehicle License Plate Recognition System, also main direction of studying in the industry is become, it is therefore proposed that a kind of have versatility, can be able to identify under arbitrary resolution the system and method for car plate be strictly necessity.
Summary of the invention
For the deficiencies in the prior art, the present invention provides the identification system and method for a kind of car plate so that it is can be suitably used for various different environment, the identification being particularly suited under arbitrary resolution car plate.
For realizing object above, the present invention is achieved by the following technical programs:
The recognition methods of a kind of car plate, comprises the following steps:
S1, obtain containing the image of car plate and it is filtered；
S2, setting frequency spectrum threshold value, select described vision intermediate frequency spectrum to exceed the rectangular area that this threshold value and color are identical with car plate color；Judge whether the shape of described rectangular area meets the shape of car plate, if so, then perform step S3, otherwise continue executing with step S2；
S3, the character local feature extracted in described rectangular area, it is judged that whether described character local feature is consistent；If consistent, then perform step S4, otherwise return and perform step S2；
S4, described rectangular area is carried out gray processing, binaryzation, trimming frame and goes gold-plating to follow closely, and the character zone in this rectangular area is split, it is judged that whether the number of characters after segmentation meets the number of characters of car plate, if, then perform step S5, otherwise return and perform step S2；
S5, judge each character shape intercharacter whether identical, each whether linear arrangement after segmentation, if so, then perform step S6, otherwise return and perform step S2；
S6, size to described each character are normalized, and extract the statistical nature of character and classifys, output license plate recognition result.
Preferably, described step S2 farther includes to judge whether the width of described rectangular area is its at least twice highly, if so, then performs step S3, otherwise continues executing with step S2.
Preferably, described step S4 farther includes:
S41, described rectangular area is carried out gray processing, binaryzation, obtain binary image；
S42, search for described binary image line by line, it is judged that whether the black and white change frequency of each row is more than 12 times, and if so, then this row is character zone, if it is not, this row then carries out trimming frame and goes gold-plating to follow closely；
S43, described character zone is split, it is judged that whether the number of characters after segmentation meets the number of characters of car plate, if so, then perform step S5, otherwise return and perform step S2.
Preferably, described step S43 farther includes: binary image corresponding for described character zone carries out upright projection, regional connectivity and situation template comparison, determine the position of each character, and described character zone is split, it is judged that whether the number of characters after segmentation meets the number of characters of car plate.
Preferably, described step S6 farther includes the size of described each character is normalized, and extracts the statistical nature of character and is sent to SVM or multilayer neural network is classified, exporting license plate recognition result.
The identification system of a kind of car plate, includes:
Filter unit, for obtaining the image containing car plate and it being filtered；
First recognition unit, is used for setting frequency spectrum threshold value, selects described vision intermediate frequency spectrum to exceed the rectangular area that this threshold value and color are identical with car plate color；Judge whether the shape of described rectangular area meets the shape of car plate；
Second recognition unit, for extracting the character local feature in described rectangular area, it is judged that whether described character local feature is consistent；
Character segmentation unit, for described rectangular area carrying out gray processing, binaryzation, trimming frame and going gold-plating to follow closely, and splits the character zone in this rectangular area, it is judged that whether the number of characters after segmentation meets the number of characters of car plate；
3rd recognition unit, for judging each character shape intercharacter whether identical, each whether linear arrangement after segmentation；
Output unit, for the size normalization to described each character, extracts the statistical nature of character and is classified, exporting license plate recognition result.
Preferably, described first recognition unit is further used for judging whether the width of described rectangular area is its at least twice highly.
Preferably, described Character segmentation unit is further used for carrying out binary image corresponding for described character zone upright projection, regional connectivity and situation template comparison, determine the position of each character, and described character zone is split, it is judged that whether the number of characters after segmentation meets the number of characters of car plate.
Preferably, described output unit is further used for the size of described each character is normalized, and extracts the statistical nature of character and is sent to SVM or multilayer neural network is classified, exporting license plate recognition result.
The present invention is by providing the identification system and method for a kind of car plate, the car plate of arbitrary resolution can be quickly recognized, the image big for size and the little image of size all may identify which, its recognition speed is fast, discrimination is high, the strong adaptability to environment, it is also possible to by arranging province priority, improve discrimination, can be widely used in intelligent transportation system and electronic police system.
Accompanying drawing explanation
Fig. 1 is the flow chart of one embodiment of the invention；
Fig. 2 is the system and device figure of one embodiment of the invention.
Detailed description of the invention
Below for the identification system and method for a kind of car plate proposed by the invention, describe in detail in conjunction with the accompanying drawings and embodiments.
The present invention provides the recognition methods of a kind of car plate, as it is shown in figure 1, comprise the following steps:
S1, obtain containing the image of car plate and it is filtered；
S2, setting frequency spectrum threshold value, select described vision intermediate frequency spectrum to exceed the rectangular area that this threshold value and color are identical with car plate color；Judge whether the shape of described rectangular area meets the shape of car plate, if so, then perform step S3, otherwise continue executing with step S2；
S3, the character local feature extracted in described rectangular area, it is judged that whether described character local feature is consistent；If consistent, then perform step S4, otherwise return and perform step S2；
S4, described rectangular area is carried out gray processing, binaryzation, trimming frame and goes gold-plating to follow closely, and the character zone in this rectangular area is split, it is judged that whether the number of characters after segmentation meets the number of characters of car plate, if, then perform step S5, otherwise return and perform step S2；
S5, judge each character shape intercharacter whether identical, each whether linear arrangement after segmentation, if so, then perform step S6, otherwise return and perform step S2；Owing to character to meet certain length-width ratio, each character boundary of a car plate should be identical；
S6, size to described each character are normalized, and extract the statistical nature of character and classifys, output license plate recognition result.
Preferably, described step S2 farther includes to judge whether the width of described rectangular area is its at least twice highly, if so, then performs step S3, otherwise continues executing with step S2.
Character local feature in described step S3 can be the stroke width of character, it is possible to obtain character stroke by the algorithm of edge extracting, then calculates the width of stroke by vertical information, and only each character stroke width is consistent, could as license plate area.
Preferably, described step S4 farther includes:
S41, described rectangular area is carried out gray processing, binaryzation, obtain binary image；
S42, search for described binary image line by line, it is judged that whether the black and white change frequency of each row is more than 12 times, and if so, then this row is character zone, if it is not, this row then carries out trimming frame and goes gold-plating to follow closely；
S43, described character zone is split, it is judged that whether the number of characters after segmentation meets the number of characters of car plate, if so, then perform step S5, otherwise return and perform step S2.
Preferably, described step S43 farther includes: binary image corresponding for described character zone carries out upright projection, regional connectivity and situation template comparison, determine the position of each character, and described character zone is split, it is judged that whether the number of characters after segmentation meets the number of characters of car plate.
After license plate binary, carry out upright projection, namely the number of every string white or black pixel point is added up, and draw a rectangular histogram, the part that each character is corresponding will have very big numerical value, may determine that character is where by this characteristic, in conjunction with width and the elevation information of character, it may be determined that a character；
Owing to each numeral and capitalization English letter are connected regions, according to this characteristic, utilize the method that labelling extends to obtain connected region, and then judge the position at character place；
Characters on license plate arrangement has certain rule, has a point and have more than 7 characters in the middle of the car plate of single character, and the car plate general both the above word following five word of double character uses such situation template, it is possible to obtain the position of each character exactly.
Preferably, described step S6 farther includes the size of described each character is normalized, and extracts the statistical nature of character and is sent to SVM or multilayer neural network is classified, exporting license plate recognition result.
As in figure 2 it is shown, the present invention also provides for the identification system of a kind of car plate, include:
Filter unit, for obtaining the image containing car plate and it being filtered；
First recognition unit, is used for setting frequency spectrum threshold value, selects described vision intermediate frequency spectrum to exceed the rectangular area that this threshold value and color are identical with car plate color；Judge whether the shape of described rectangular area meets the shape of car plate；
Second recognition unit, for extracting the character local feature in described rectangular area, it is judged that whether described character local feature is consistent；
Character segmentation unit, for described rectangular area carrying out gray processing, binaryzation, trimming frame and going gold-plating to follow closely, and splits the character zone in this rectangular area, it is judged that whether the number of characters after segmentation meets the number of characters of car plate；
3rd recognition unit, for judging each character shape intercharacter whether identical, each whether linear arrangement after segmentation；
Output unit, for the size normalization to described each character, extracts the statistical nature of character and is classified, exporting license plate recognition result.
Preferably, described first recognition unit is further used for judging whether the width of described rectangular area is its at least twice highly.
Preferably, described Character segmentation unit is further used for carrying out binary image corresponding for described character zone upright projection, regional connectivity and situation template comparison, determine the position of each character, and described character zone is split, it is judged that whether the number of characters after segmentation meets the number of characters of car plate.
Preferably, described output unit is further used for the size of described each character is normalized, and extracts the statistical nature of character and is sent to SVM or multilayer neural network is classified, exporting license plate recognition result.
By setting up recognizer, RGB containing license plate image or jpeg data are input in function, be obtained with containing the number-plate number, car plate color, car plate particular location recognition result, the image of arbitrary resolution can be identified by this system and method, its recognition speed is very fast, generally at about 30ms, discrimination is more than 98%, blueness, black, white and four kinds of car plates of yellow can accurately be identified, can recognise that the car plate in arbitrarily province, the whole nation, more can pass through to arrange province priority, improve discrimination
The present invention is by providing the identification system and method for a kind of car plate, the car plate of arbitrary resolution can be quickly recognized, the image big for size and the little image of size all may identify which, its recognition speed is fast, discrimination is high, the strong adaptability to environment, it is also possible to by arranging province priority, improve discrimination, can be widely used in intelligent transportation system and electronic police system.
Embodiment of above is merely to illustrate the present invention; and it is not limitation of the present invention; those of ordinary skill about technical field; without departing from the spirit and scope of the present invention; can also make a variety of changes and modification; therefore all equivalent technical schemes fall within scope of the invention, and the scope of patent protection of the present invention should be defined by the claims.
Claims (8)
1. the recognition methods of a car plate, it is characterised in that comprise the following steps:
S1, obtain containing the image of car plate and it is filtered；
S2, setting frequency spectrum threshold value, select described vision intermediate frequency spectrum to exceed the rectangular area that this threshold value and color are identical with car plate color；Judge whether the shape of described rectangular area meets the shape of car plate, if so, then perform step S3, otherwise continue executing with step S2；
S3, the character local feature extracted in described rectangular area, it is judged that whether described character local feature is consistent；If consistent, then performing step S4, otherwise return and perform step S2, described character local feature includes the stroke width of character；
S4, described rectangular area is carried out gray processing, binaryzation, trimming frame and goes gold-plating to follow closely, and the character zone in this rectangular area is split, it is judged that whether the number of characters after segmentation meets the number of characters of car plate, if, then perform step S5, otherwise return and perform step S2；Described step S4 farther includes:
S41, described rectangular area is carried out gray processing, binaryzation, obtain binary image；
S42, search for described binary image line by line, it is judged that whether the black and white change frequency of each row is more than 12 times, and if so, then this row is character zone, if it is not, this row then carries out trimming frame and goes gold-plating to follow closely；
S43, described character zone is split, it is judged that whether the number of characters after segmentation meets the number of characters of car plate, if so, then perform step S5, otherwise return and perform step S2；
S5, judge each character shape intercharacter whether identical, each whether linear arrangement after segmentation, if so, then perform step S6, otherwise return and perform step S2；
S6, size to described each character are normalized, and extract the statistical nature of character and classifys, output license plate recognition result.
2. the method for claim 1, it is characterised in that described step S2 farther includes to judge whether the width of described rectangular area is its at least twice highly, if so, then performs step S3, otherwise continues executing with step S2.
3. the method for claim 1, it is characterized in that, described step S43 farther includes: binary image corresponding for described character zone carries out upright projection, regional connectivity and situation template comparison, determine the position of each character, and described character zone is split, it is judged that whether the number of characters after segmentation meets the number of characters of car plate.
4. the method for claim 1, it is characterised in that described step S6 farther includes the size of described each character is normalized, extracts the statistical nature of character and is sent to SVM or multilayer neural network is classified, exporting license plate recognition result.
5. the identification system of a car plate, it is characterised in that include:
Filter unit, for obtaining the image containing car plate and it being filtered；
First recognition unit, is used for setting frequency spectrum threshold value, selects described vision intermediate frequency spectrum to exceed the rectangular area that this threshold value and color are identical with car plate color；Judge whether the shape of described rectangular area meets the shape of car plate；
Second recognition unit, for extracting the character local feature in described rectangular area, it is judged that whether described character local feature is consistent, and described character local feature includes the stroke width of character；
Character segmentation unit, for described rectangular area carrying out gray processing, binaryzation, trimming frame and going gold-plating to follow closely, and splits the character zone in this rectangular area, it is judged that whether the number of characters after segmentation meets the number of characters of car plate；Described Character segmentation unit is additionally operable to perform following steps:
S41, described rectangular area is carried out gray processing, binaryzation, obtain binary image；
S42, search for described binary image line by line, it is judged that whether the black and white change frequency of each row is more than 12 times, and if so, then this row is character zone, if it is not, this row then carries out trimming frame and goes gold-plating to follow closely；
S43, described character zone is split, it is judged that whether the number of characters after segmentation meets the number of characters of car plate；
3rd recognition unit, for judging each character shape intercharacter whether identical, each whether linear arrangement after segmentation；
Output unit, for the size normalization to described each character, extracts the statistical nature of character and is classified, exporting license plate recognition result.
6. system as claimed in claim 5, it is characterised in that described first recognition unit is further used for judging whether the width of described rectangular area is its at least twice highly.
7. system as claimed in claim 5, it is characterized in that, described Character segmentation unit is further used for carrying out binary image corresponding for described character zone upright projection, regional connectivity and situation template comparison, determine the position of each character, and described character zone is split, it is judged that whether the number of characters after segmentation meets the number of characters of car plate.
8. system as claimed in claim 5, it is characterised in that described output unit is further used for the size of described each character is normalized, extracts the statistical nature of character and is sent to SVM or multilayer neural network is classified, exporting license plate recognition result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310117722.0A CN103226696B (en) | 2013-04-07 | 2013-04-07 | The identification system and method for car plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310117722.0A CN103226696B (en) | 2013-04-07 | 2013-04-07 | The identification system and method for car plate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103226696A CN103226696A (en) | 2013-07-31 |
| CN103226696B true CN103226696B (en) | 2016-07-06 |
Family
ID=48837137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310117722.0A Expired - Fee Related CN103226696B (en) | 2013-04-07 | 2013-04-07 | The identification system and method for car plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103226696B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902981A (en) * | 2014-04-02 | 2014-07-02 | 浙江师范大学 | Method and system for identifying license plate characters based on character fusion features |
| CN103971126B (en) * | 2014-05-12 | 2017-08-08 | 百度在线网络技术（北京）有限公司 | A kind of traffic sign recognition method and device |
| CN105005757B (en) * | 2015-03-12 | 2018-04-06 | 电子科技大学 | A kind of license plate character recognition method popular based on Grassmann |
| CN108073928B (en) * | 2016-11-16 | 2021-04-02 | 杭州海康威视数字技术股份有限公司 | License plate recognition method and device |
| CN108073926B (en) * | 2016-11-17 | 2020-04-03 | 杭州海康威视数字技术股份有限公司 | License plate recognition method and device |
| CN108090484B (en) * | 2016-11-23 | 2020-04-03 | 杭州海康威视数字技术股份有限公司 | License plate recognition method and device |
| CN108288403A (en) * | 2018-01-31 | 2018-07-17 | 中国地质大学（武汉） | Parking management system based on intelligent space lock |
| CN108805008A (en) * | 2018-04-19 | 2018-11-13 | 江苏理工学院 | A kind of community's vehicle security system based on deep learning |
| CN109978132A (en) * | 2018-12-24 | 2019-07-05 | 中国科学院深圳先进技术研究院 | A kind of neural network method and system refining vehicle identification |
| CN112950950A (en) * | 2021-01-26 | 2021-06-11 | 上海启迪睿视智能科技有限公司 | Parking auxiliary device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398894A (en) * | 2008-06-17 | 2009-04-01 | 浙江师范大学 | Automobile license plate automatic recognition method and implementing device thereof |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8929588B2 (en) * | 2011-07-22 | 2015-01-06 | Honeywell International Inc. | Object tracking |
-
2013
- 2013-04-07 CN CN201310117722.0A patent/CN103226696B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398894A (en) * | 2008-06-17 | 2009-04-01 | 浙江师范大学 | Automobile license plate automatic recognition method and implementing device thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103226696A (en) | 2013-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103226696B (en) | The identification system and method for car plate | |
| CN108073928B (en) | License plate recognition method and device | |
| Sheikh et al. | Traffic sign detection and classification using colour feature and neural network | |
| KR101848019B1 (en) | Method and Apparatus for Detecting Vehicle License Plate by Detecting Vehicle Area | |
| KR101992398B1 (en) | Method and Apparatus for Recognizing Road Symbols and Lanes | |
| CN106650553A (en) | License plate recognition method and system | |
| Sulaiman et al. | Development of automatic vehicle plate detection system | |
| US20120128210A1 (en) | Method for Traffic Sign Recognition | |
| CN103413147A (en) | Vehicle license plate recognizing method and system | |
| CN102819728A (en) | Traffic sign detection method based on classification template matching | |
| CN103390167A (en) | Multi-characteristic layered traffic sign identification method | |
| Kim et al. | Effective traffic lights recognition method for real time driving assistance systemin the daytime | |
| CN103544480A (en) | Vehicle color recognition method | |
| Islam et al. | Automatic vehicle number plate recognition using structured elements | |
| CN103207992A (en) | Character and color combined recognition method of license plates | |
| CN111191611A (en) | Deep learning-based traffic sign label identification method | |
| Ingole et al. | Characters feature based Indian vehicle license plate detection and recognition | |
| Pandya et al. | Morphology based approach to recognize number plates in India | |
| Sallah et al. | Road sign detection and recognition system for real-time embedded applications | |
| CN104834891A (en) | Method and system for filtering Chinese character image type spam | |
| Chakraborty et al. | Bangladeshi road sign detection based on YCbCr color model and DtBs vector | |
| CN107392115B (en) | Traffic sign identification method based on hierarchical feature extraction | |
| CN110633635A (en) | ROI-based traffic sign board real-time detection method and system | |
| CN111008554A (en) | Dynamic traffic zebra crossing interior impersonation pedestrian identification method based on deep learning | |
| Bailmare et al. | A review paper on Vehicle Number Plate Recognition (VNPR) using improved character segmentation method |
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: 20160706 Termination date: 20190407 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |