CN106446891A - Automatic identification method of motor vehicle license plate - Google Patents

Automatic identification method of motor vehicle license plate Download PDF

Info

Publication number
CN106446891A
CN106446891A CN201610749685.9A CN201610749685A CN106446891A CN 106446891 A CN106446891 A CN 106446891A CN 201610749685 A CN201610749685 A CN 201610749685A CN 106446891 A CN106446891 A CN 106446891A
Authority
CN
China
Prior art keywords
license plate
word
image
described step
automatic identifying
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
Application number
CN201610749685.9A
Other languages
Chinese (zh)
Inventor
郑坚雄
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Kunshan Yibangtai Auto Parts Manufacturing Co Ltd
Original Assignee
Kunshan Yibangtai Auto Parts Manufacturing Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Kunshan Yibangtai Auto Parts Manufacturing Co Ltd filed Critical Kunshan Yibangtai Auto Parts Manufacturing Co Ltd
Priority to CN201610749685.9A priority Critical patent/CN106446891A/en
Publication of CN106446891A publication Critical patent/CN106446891A/en
Pending legal-status Critical Current

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
    • G06V20/63—Scene text, e.g. street names
    • 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
    • G06V30/24—Character recognition characterised by the processing or recognition method
    • G06V30/242—Division of the character sequences into groups prior to recognition; Selection of dictionaries
    • G06V30/244—Division of the character sequences into groups prior to recognition; Selection of dictionaries using graphical properties, e.g. alphabet type or font
    • 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
    • G06V20/625—License plates
    • 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

Abstract

The invention discloses an automatic identification method of a motor vehicle license plate. The automatic identification method comprises the following steps of: 1) obtaining an image; 2) preprocessing the obtained image; 3) carrying out license plate positioning on the preprocessed image; 4) carrying out text segmentation on the positioned image; 5) carrying out feature extraction and selection; and 6) carrying out BP (Back Propagation) network identification and outputting the license plate. The automatic identification method, which is provided by the invention, of the motor vehicle license plate is an algorithm which can realize the quick, accurate and automatic positioning and segmentation of the license plate under a complex underground.

Description

A kind of automatic identifying method of automobile license plate
Technical field
The present invention relates to a kind of method of Car license recognition, more particularly to a kind of automatic identifying method of automobile license plate.
Background technology
The automatic identification technology of license plate has important application in public safety, traffic administration and relevant military service It is worth.One complete vehicle license plate reading system generally comprises three parts：First to the image taken in by video camera Pre-process；Secondly determine the position of car plate in a complex background containing automobile；Finally the word on car plate is carried out Cutting, feature extraction and identification.
At present, the dividing method employed in image processing mainly carries out edge extracting or base by various boundary operators Carry out image region segmentation [1,2] in space clustering.Due to there is frame around car plate, generally can using edge extracting or The methods such as Hough transform determine the position of frame, but in a practical situation, the image diffusion often absorbed is unclear, disconnected during frame Shi Lian, so disappear.
Content of the invention
Present invention is primarily targeted at, overcome deficiency of the prior art, a kind of automatic knowledge of automobile license plate is provided Other method.The technical problem to be solved is that there is frame around car plate, generally can be become using edge extracting or Hough The method such as change determines the position of frame, but in a practical situation, the image diffusion often absorbed is unclear, when disconnected during frame even, is To disappearance.
In order to achieve the above object, the technical solution adopted in the present invention is：
A kind of automatic identifying method of automobile license plate, comprises the following steps：
1）Obtain image；
2）The image of acquisition is pre-processed；
3）License Plate is carried out to pretreated image；
4）Text segmentation is carried out to the image after positioning；
5）Feature extraction and selection；
6）BP Network Recognition simultaneously exports car plate.
Further：Described step 1) in image pass through picture pick-up device or photographing device and obtain.
Further：Described step 2）Comprise the following steps：
2-1）Eliminate the impact of light intensity using histogram equalization；
2-2）Using 3 × 3 medium filtering denoisings；
2-3）Binary conversion treatment is carried out using Laplacian algorithm.
Further：Described step 3）Comprise the following steps：
3-1）From the lower section of headstock toward scanning overhead；
3-2）Scan from left to right from headstock, if equispaced is intaveWhen, when certain is spaced int》intave, determine this point Apart from certain stroke too far it is believed that it is noise；
If the lower limit of the stroke number cross-num often going on car plate is th1, th1 is more than or equal to 8 strokes；
Cross-num when certain row<During th1, determine that this capable is not located in the range of car plate, so that it is determined that bound position Upline and downline, and determine position leftline and rightline on left and right circle.
Further：Described step 4）Comprise the following steps：
4-1）Normalized；
4-2）7 words that spacing is equal are had on car plate, also a separator " " accounts for 1/2 word width, word interval There is no pixel；
If the average a width of W of wordaveIf f (i, j) is the two-dimensional lattice figure of word, having at word is 1, otherwise for 0；
?Place's cutting, if during two word phase adhesions, its interval is just not inNow just it is aided with and be averaging the wide method of word；
If certain word width Wk《Wave, W is describedkIn contain more than one word, then at its trough cut.
Further：Described step 5）In feature extraction adopt projective transformation Y-factor method Y.
Compared with prior art, the invention has the advantages that：
Using the more stable feature of character stroke change frequency in license plate it is proposed that one kind can be under complex background Realize the algorithm that car plate is quick, accurate, is automatically positioned and splits.
The above is only the general introduction of technical solution of the present invention, in order to be better understood upon the technological means of the present invention, under The invention will be further described in face.
Specific embodiment
The present invention is further illustrated below.
The present invention provides a kind of automatic identifying method of automobile license plate, comprises the following steps：
1）Obtain image；
2）The image of acquisition is pre-processed；
3）License Plate is carried out to pretreated image；
4）Text segmentation is carried out to the image after positioning；
5）Feature extraction and selection；
6）BP Network Recognition simultaneously exports car plate.
Described step 1) in image pass through picture pick-up device or photographing device and obtain.
Described step 2）Comprise the following steps：
2-1）Eliminate the impact of light intensity using histogram equalization；
2-2）Using 3 × 3 medium filtering denoisings；
2-3）Binary conversion treatment is carried out using Laplacian algorithm.
Described step 3）Comprise the following steps：
3-1）From the lower section of headstock toward scanning overhead；
3-2）Scan from left to right from headstock, if equispaced is intaveWhen, when certain is spaced int》intave, determine this point Apart from certain stroke too far it is believed that it is noise；
If the lower limit of the stroke number cross-num often going on car plate is th1, th1 is more than or equal to 8 strokes；
Cross-num when certain row<During th1, determine that this capable is not located in the range of car plate, so that it is determined that bound position Upline and downline, and determine position leftline and rightline on left and right circle.
Described step 4）Comprise the following steps：
4-1）Normalized；
4-2）7 words that spacing is equal are had on car plate, also a separator " " accounts for 1/2 word width, word interval There is no pixel；
If the average a width of W of wordaveIf f (i, j) is the two-dimensional lattice figure of word, having at word is 1, otherwise for 0；
?Place's cutting, if during two word phase adhesions, its interval is just not inNow just it is aided with and be averaging the wide method of word；
If certain word width Wk《Wave, W is describedkIn contain more than one word, then at its trough cut.
Described step 5）In feature extraction adopt projective transformation Y-factor method Y.
General principle, principal character and the advantage of the present invention have been shown and described above.The technical staff of the industry should Understand, the present invention is not restricted to the described embodiments, the simply explanation present invention's described in above-described embodiment and specification is former Reason, without departing from the spirit and scope of the present invention, the present invention also has various changes and modifications, these changes and improvements Both fall within scope of the claimed invention.Claimed scope is by appending claims and its equivalent circle. Fixed.

Claims (6)

1. a kind of automatic identifying method of automobile license plate is it is characterised in that comprise the following steps：
1) obtain image；
2) image of acquisition is pre-processed；
3) License Plate is carried out to pretreated image；
4) Text segmentation is carried out to the image after positioning；
5) feature extraction and selection；
6) BP Network Recognition export car plate.
2. a kind of automobile license plate according to claim 1 automatic identifying method it is characterised in that：Described step 1) in Image pass through picture pick-up device or photographing device and obtain.
3. a kind of automobile license plate according to claim 1 automatic identifying method it is characterised in that：Described step 2) bag Include following steps：
2-1) histogram equalization is adopted to eliminate the impact of light intensity；
2-2) adopt 3 × 3 medium filtering denoisings；
2-3) binary conversion treatment is carried out using Laplacian algorithm.
4. a kind of automobile license plate according to claim 1 automatic identifying method it is characterised in that：Described step 3) bag Include following steps：
3-1) from the lower section of headstock toward scanning overhead；
3-2) scan from left to right from headstock, if equispaced is intaveWhen, when certain is spaced int》intave, determine this point distance Certain stroke is too far it is believed that it is noise；
If the lower limit of the stroke number cross-num often going on car plate is th1, th1 is more than or equal to 8 strokes；
Cross-num when certain row<During th1, determine that this capable is not located in the range of car plate, so that it is determined that bound position upline And downline, and determine position leftline and rightline on left and right circle.
5. a kind of automobile license plate according to claim 4 automatic identifying method it is characterised in that：Described step 4) bag Include following steps：
4-1) normalized；
7 words that spacing is equal 4-2) are had on car plate, also a separator " " accounts for 1/2 word width, and word interval does not have Pixel；
If the average a width of W of wordaveIf f (i, j) is the two-dimensional lattice figure of word, having at word is 1, otherwise for 0；
?Place's cutting, if during two word phase adhesions, its interval is just not inNow just it is aided with and be averaging the wide method of word；
If certain word width Wk《Wave, W is describedkIn contain more than one word, then at its trough cut.
6. a kind of automobile license plate according to claim 1 automatic identifying method it is characterised in that：Described step 5) in Feature extraction adopt projective transformation Y-factor method Y.
CN201610749685.9A 2016-08-29 2016-08-29 Automatic identification method of motor vehicle license plate Pending CN106446891A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610749685.9A CN106446891A (en) 2016-08-29 2016-08-29 Automatic identification method of motor vehicle license plate

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610749685.9A CN106446891A (en) 2016-08-29 2016-08-29 Automatic identification method of motor vehicle license plate

Publications (1)

Publication Number Publication Date
CN106446891A true CN106446891A (en) 2017-02-22

Family

ID=58182762

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610749685.9A Pending CN106446891A (en) 2016-08-29 2016-08-29 Automatic identification method of motor vehicle license plate

Country Status (1)

Country Link
CN (1) CN106446891A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109697857A (en) * 2019-01-18 2019-04-30 合肥米佑信息技术有限公司 Intelligent traffic control system based on image recognition and neural network algorithm
CN110378332A (en) * 2019-06-14 2019-10-25 上海咪啰信息科技有限公司 A kind of container terminal case number (CN) and Train number recognition method and system

Citations (4)

* Cited by examiner, † Cited by third party
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
CN101408933A (en) * 2008-05-21 2009-04-15 浙江师范大学 Method for recognizing license plate character based on wide gridding characteristic extraction and BP neural network
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
KR20160057059A (en) * 2014-11-13 2016-05-23 주식회사한맥아이피에스 Method and system for recognizing vehicle license plate

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101408933A (en) * 2008-05-21 2009-04-15 浙江师范大学 Method for recognizing license plate character based on wide gridding characteristic extraction and BP neural network
CN101398894A (en) * 2008-06-17 2009-04-01 浙江师范大学 Automobile license plate automatic recognition method and implementing device thereof
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
KR20160057059A (en) * 2014-11-13 2016-05-23 주식회사한맥아이피에스 Method and system for recognizing vehicle license plate

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘效静等: "《汽车牌照自动识别技术研究》", 《南京航空航天大学学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109697857A (en) * 2019-01-18 2019-04-30 合肥米佑信息技术有限公司 Intelligent traffic control system based on image recognition and neural network algorithm
CN110378332A (en) * 2019-06-14 2019-10-25 上海咪啰信息科技有限公司 A kind of container terminal case number (CN) and Train number recognition method and system

Similar Documents

Publication Publication Date Title
WO2017028587A1 (en) Vehicle monitoring method and apparatus, processor, and image acquisition device
CN105335743A (en) Vehicle license plate recognition method
CN102915640B (en) Safety belt detecting method based on Hough transform
Guo et al. Image-based seat belt detection
JP2011216051A (en) Program and device for discriminating traffic light
CN106446905A (en) Surface crack texture extraction method based on fusion of seepage algorithm and adaptive Canny algorithm
CN109460722B (en) Intelligent license plate recognition method
CN106022268A (en) Identification method and device of speed limiting sign
CN102663760A (en) Location and segmentation method for windshield area of vehicle in images
CN104657726A (en) Identification method for truck numbers of railway tank trucks
CN110674812B (en) Civil license plate positioning and character segmentation method facing complex background
CN105389561A (en) Method for detecting bus lane based on video
CN106446891A (en) Automatic identification method of motor vehicle license plate
CN109741391A (en) Detection method, device and the storage medium of surface gathered water depth
CN107358236A (en) A kind of number-plate number identifying system and method based on camera device
CN110154894B (en) Automobile safe driving early warning method based on road surface condition
CN105426896A (en) Car logo automatic identification method and system
Devane et al. Lane detection techniques using image processing
CN109145797B (en) Square induction method for road rescue equipment based on vehicle bottom shadow positioning license plate
CN106485701A (en) Based on the whether anti-loaded detection method of the railway overhead contact system catenary seat of image
CN103559793B (en) A kind of car internal sunshade board detecting method and device
CN112115778B (en) Intelligent lane line identification method under ring simulation condition
Salahshoor et al. Application of intelligent systems for iranian license plate recognition
CN106803064B (en) Traffic light rapid identification method
CN104504384B (en) Automobile logo identification method and its identifying system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20170222

RJ01 Rejection of invention patent application after publication