CN103065137B - A kind of license plate character recognition method - Google Patents
A kind of license plate character recognition method Download PDFInfo
- Publication number
- CN103065137B CN103065137B CN201210587347.1A CN201210587347A CN103065137B CN 103065137 B CN103065137 B CN 103065137B CN 201210587347 A CN201210587347 A CN 201210587347A CN 103065137 B CN103065137 B CN 103065137B
- Authority
- CN
- China
- Prior art keywords
- density
- character
- edge
- hop
- transitions
- 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.)
- Active
Links
Abstract
The present invention proposes a kind of method of new Recognition of License Plate Characters, adopt the method for canny algorithm and bianry image combination to carry out identification character. And when identification is owing to having extracted edge and the saltus step information of character, then the saltus step of character edge pixel is done and mated with the saltus step of template character set, find the template character that matching degree is the highest, and then the recognition result of acquisition character. This character recognition based on saltus step, has solved character identification problem under various interference preferably, can effectively overcome various disturbing factors, keeps comparatively stable high discrimination. And, because the canny algorithm to standard is simplified, greatly improve the efficiency of identification, reduce the system resource taking, improve recognition speed.
Description
Affiliated technical field:
Patent of the present invention relates to a kind of character identifying method in Vehicle License Plate Recognition System, belongs to technical field of image processing.
Background technology:
Along with the fast development of Chinese national economy, the requirement of control of traffic and road is progressively improved to intelligent transportation systemArise at the historic moment. In intelligent transportation system, after accurate positioning licence plate and Character segmentation, carry out character by Vehicle License Plate Recognition SystemIdentification just finally completes complete car plate identification, and therefore the quality of character recognition plays vital work to character identification rateWith. Therefore, as the important component part of intelligent transportation system, Vehicle License Plate Recognition System has obtained fast development, is learned both at home and abroadPerson's broad research. Vehicle License Plate Recognition System is divided into image acquisition, car plate location, Character segmentation, character recognition four parts, wherein characterIdentification is the Research Emphasis of the each enterprise of the industry. Aspect character feature extraction, need to suppress various interference, such as uneven illuminationInconsistent and the situation such as fracture or adhesion of the rotation of even, character and deformation, stroke weight, just can extract stable character spyLevy, finally complete character recognition.
In prior art, common threshold obtains bianry image, and in the time that light is inhomogeneous, discrimination is not high, and originalAlgorithm steps is more, and the system resource taking while identification is too high, and recognition speed is not high; Meanwhile, for because turn inside diameter,That shooting angle etc. cause is license plate sloped, the fracture of characters on license plate stroke, character are stained, low light according to time noise etc., all can cause knowledgeRate does not decline.
Summary of the invention:
In order to improve the discrimination of character, the present invention proposes a kind of method of new Recognition of License Plate Characters, adopt cannyThe method of algorithm and bianry image combination is carried out identification character, and the canny algorithm of standard is simplified, specific as follows:
First license plate grey level image is divided into some character zones, to the gray level image I of each character zonecharPressProcess according to following steps order:
A, to IcharAsk adaptive threshold;
B, to IcharAdopt Canny algorithm to determine character edge image Iedge;
C, to above-mentioned character edge image IedgeCarry out filling cavity;
D, again determine above-mentioned character edge image IedgeBorder;
E, to above-mentioned IedgeBe normalized;
The horizontal hopping sequences S at F, calculating character edgeHoriWith vertical transition sequence SVert, and according to above-mentioned horizontal saltus stepSequence SHoriWith vertical transition sequence SVertDetermine upper number of transitions density Hop_DensityTop, lower number of transitions density Hop_DensityBottom, left number of transitions density Hop_DensityLeft, right number of transitions density Hop_DensityRight, and further trueFixed upper and lower number of transitions density ratio Hop_DensityTop/BottomWith left and right number of transitions density ratio Hop_DensityLeft/Right;
G, by above-mentioned F step determine above-mentioned horizontal hopping sequences SHori, vertical transition sequence SVert, upper and lower number of transitionsDensity ratio Hop_DensityTop/BottomWith left and right number of transitions density ratio Hop_DensityLeft/RightWith from Character mother plate concentrate readThe horizontal hopping sequences SM of the current character template of gettingHori, vertical transition sequence SMVert, upper and lower number of transitions density ratio Hop_Density_MTop/Bottom, left and right number of transitions density ratio Hop_Density_MLeft/RightMate one by one, find matching degreeHigh character index value, completes character recognition.
Adopt method of the present invention to process characters on license plate gray level image, owing to having extracted edge and the jumping of characterChange information, then the saltus step of character edge pixel is done and mated with the saltus step of template character set, the template word that matching degree is the highest foundSymbol, and then the recognition result of acquisition character. This character recognition based on saltus step, has solved preferably character under various interference and has knownOther problem, can effectively overcome various disturbing factors, keeps comparatively stable high discrimination. And, due to the canny to standardAlgorithm is simplified, and has greatly improved the efficiency of identification, has reduced the system resource taking, and has improved recognition speed.
Detailed description of the invention:
Method of the present invention is first license plate grey level image to be carried out to Character segmentation, and license plate image is divided into several charactersRegion, to the gray level image I of each character zonecharRepeat following operation, finally obtain each character in predetermined template wordAccord with concentrated index value Indexm, complete the identification to all characters with this. Wherein, predetermined masterplate character set can be according to needThe characters on license plate of identifying be the situations such as numeral, letter, Chinese character, font self-defined (for example, can comprise each province be called for short, 26English alphabet capital and small letter, numeral, can also set other words or other language as required). Specifically to gray level image IcharTreatment step as follows:
1. couple IcharAsk adaptive threshold T
2. couple IcharAdopt Canny algorithm to obtain character edge image Iedge
1) adopt the template of 3*3, ask that current pixel point P is upper and lower, the gradient G of left and right, two clinodiagonals1、G2、G3、G4,The corresponding operator of each gradient direction is respectively H1、H2、H3、H4:
2) find maximum gradient Gmax=MAX(G1,G2,G3,G4), and with mode mark P point below:
if((Gmax≥MIN_EDGE_GRADIENT)&&(Gray(P)≥T))
{
P is marginal point, at IedgeIn be labeled as 1;
else
{
P is non-marginal point, at IedgeIn be labeled as 0;
According to Gmax=MAX(G1,G2,G3,G4) find the greatest gradient of current pixel point P, and judge current pixel point PWhether meet the gray value that greatest gradient is greater than predetermined minimum marginal value and current pixel point simultaneously and whether be greater than above-mentioned self adaptationThreshold value, if it is mark is judged to be marginal point, IedgeBe labeled as 1; If not being judged to be not to be marginal point, IedgeMarkBe 0.
The gray value that wherein Gray (P) is ordered for P, MIN_EDGE_GRADIENT is defaulted as 15, can be according to captured imageThe difference of type is got different values.
3) get back to step 1), repeat this process, until travel through completely, finally obtain edge image Iedge。
3. pair character edge image IedgeFilling cavity, the impact of character saltus step being calculated with cancellation. Be specially
1) at IedgeIn, obtain current pixel point Pij;
2) if Gray is (Pij)==0, with PijCentered by get the window of 3 × 3, pixel value forms square in windowBattle array W3×3, definition operator Ask the scalar product C of the twoij=W3×3H, works as Cij≥Tc(Tc=6), justIedgeMiddle by PijBe set to marginal point.
3) get back to step 1, repeat this process, until travel through complete.
4. recalculate the border of character edge image, the object of doing is like this impact in order to eliminate noise at the boundary
1) look for IedgeUpper marginal position index IndexTop
Method: row traversal from top to bottom, the Num until count in row edgeHori≥Tnum,Tnum=1;
2) look for IedgeLower limb location index IndexBottom
Method: row traversal from top to bottom, the Num until count in row edgeHori≥Tnum,Tnum=1;
3) look for IedgeLeft hand edge location index IndexLeft
Method: from left to right row traversal, until column border points N umVert≥Tnum,Tnum=1;
4) look for IedgeRight hand edge location index IndexRight
Method: row traversal from right to left, until column border points N umVert≥Tnum,Tnum=1。
5. couple IedgeDo normalized, to reduce the requirement to Character segmentation precision
1)IndexTop、IndexBottom、IndexLeft、IndexRightFour determined images in border areIdivided_edge, by Idivided_edgeDo size normalization, its wide height is equated with the wide height of Character mother plate, obtain Inormal_edge;
2) record Inormal_edgeHeight H eight, width is Width.
3)
6. the horizontal and vertical hopping sequences S at calculating character edgeHoriAnd SVert, and obtain upper and lower number of transitions density Hop_DensityTop、Hop_DensityBottom, left and right number of transitions density Hop_DensityLeft、Hop_DensityRight, jump up and downParameter density ratio Hop_DensityTop/BottomWith left and right number of transitions density ratio Hop_DensityLeft/Right
1) obtain horizontal hopping sequences SHori
Method: row traversal I from top to bottomnormal_edgeAll row, for the capable R of jjIf there is some Pi(Pi-1=0,Pi=1), RjOn number of transitions HopjAdd 1 (HopjInitial value is 0), travel through so all row (R1,R2,..,Rj,..,RHeight),Obtain horizontal hopping sequences SHori={Hop1,Hop2,..,Hopj,...,HopHeight};
2) obtain vertical transition sequence SVert
Method: from left to right row traversal Inormal_edgeAll row, for j row CjIf there is some Pi(Pi-1=0,Pi=1), CjOn number of transitions HopjAdd 1 (HopjInitial value is 0), travel through so all row (C1,C2,..,Cj,..,CWidth),Obtain vertical transition sequence SVert={Hop1,Hop2,..,Hopj,...,HopWidth};
3) obtain upper and lower number of transitions density Hop_pensityTop、Hop_DensityBottom
(k default value is Height/2, Hopj∈SHori)
(k default value is Height/2, h=Height, Hopj∈SHori)
4) obtain left and right number of transitions density Hop_DensityLeft、Hop_DensityRight
(k gets default value Width/2, Hopj∈SVert)
(k gets default value Width/2, h=Width, Hopj∈SVert)
5) upper and lower number of transitions density ratio:
Hop_DensityTop/Bottom=Hop_DensityTop/Hop_DensityBottom
Left and right number of transitions density ratio:
Hop_DensityLeft/Right=Hop_DensityLeft/Hop_DensityRigth
7, all characters of Character mother plate collection do and mate one by one, find the Character mother plate index value that matching degree is the highest
1) concentrate and obtain current character template Tamplate at Character mother platei(1≤i≤n, n is template set largest indexValue), obtain its horizontal hopping sequences SMHori, vertical transition sequence SMVert, upper and lower number of transitions density ratio Hop_Density_MTop/Bottom, left and right number of transitions density ratio Hop_Density_MLeft/Right;
2)SHoriWith SMHoriDo and mate, obtain matching degree M1;
3)SVertWith SMVertDo and mate, obtain matching degree M2;
4)Hop_DensityTop/BottomWith Hop_Density_MTop/BottomDo and mate, obtain mating M3;
5)Hop_DensityLeft/RightWith Hop_Density_MLeft/RightDo and mate, obtain matching degree M4;
6) calculate total matching degree Mti:Mti=w1M1+w2M2+w3M3+w4M4
Wherein, w1、w2、w3、w4Be respectively M1、M2、M3、M4Weight;
7) get back to step 1, repeat this process, until travel through complete;
8) get IndexmFor { Mt1,Mt2,…,Mti,…,MtnIn peaked index value, IndexmBe final identificationResult. So far, this character recognition is complete.
Claims (5)
1. a license plate character recognition method, is divided into some character zones by license plate grey level image, to each character zoneGray level image IcharOrder is processed in accordance with the following steps:
A, to IcharAsk adaptive threshold;
B, to IcharAdopt Canny algorithm to determine character edge image Iedge;
C, to above-mentioned character edge image IedgeCarry out filling cavity;
D, again determine above-mentioned character edge image IedgeBorder;
E, to above-mentioned IedgeBe normalized;
The horizontal hopping sequences S at F, calculating character edgeHoriWith vertical transition sequence SVert, and according to above-mentioned horizontal hopping sequencesSHoriWith vertical transition sequence SVertDetermine upper number of transitions density Hop_DensityTop, lower number of transitions density Hop_DensityBottom, left number of transitions density Hop_DensityLeft, right number of transitions density Hop_DensityRight, and further trueFixed upper and lower number of transitions density ratio Hop_DensityTop/BottomWith left and right number of transitions density ratio Hop_DensityLeft/Right;
G, by above-mentioned F step determine above-mentioned horizontal hopping sequences SHori, vertical transition sequence SVert, upper and lower number of transitions densityCompare Hop_DensityTop/BottomWith left and right number of transitions density ratio Hop_DensityLeft/RightWith from Character mother plate concentrate readThe horizontal hopping sequences SM of current character templateHori, vertical transition sequence SMVert, upper and lower number of transitions density ratio Hop_Density_MTop/Bottom, left and right number of transitions density ratio Hop_Density_MLeft/RightMate one by one, find matching degreeHigh character index value, completes character recognition.
2. license plate character recognition method as claimed in claim 1, is further included in and in above-mentioned steps B, adopts canny algorithmObtain character edge image, be specially:
B1, adopt the template of 3*3, ask that current pixel point P is upper and lower, the gradient G of left and right, two clinodiagonals1、G2、G3、G4, each ladderThe corresponding operator of degree direction is respectively H1、H2、H3、H4:
According to Gmax=MAX(G1,G2,G3,G4) find the greatest gradient of current pixel point P, and judge that whether current pixel point P is sameIn time, meets the gray value that greatest gradient is greater than predetermined minimum marginal value and P and whether is greater than above-mentioned adaptive threshold, if it is markNote is judged to be marginal point, IedgeBe labeled as 1; If not being judged to be not to be marginal point, IedgeBe labeled as 0;
B2, get back to step B1, repeat this process, until travel through completely, finally obtain edge image Iedge。
3. license plate character recognition method as claimed in claim 2, further comprises in above-mentioned steps C character edge imageIedgeThe method of filling cavity is:
C1, at IedgeIn, obtain current pixel point Pij;
If C2 Gray is (Pij)==0, with PijCentered by get the window of 3 × 3, pixel value structure in window
Become matrix W3×3, definition operatorAsk the scalar product C of the twoij=W3×3H, works as Cij>=6, just at IedgeMiddle by PijBe set to marginal point; The gray value that wherein Gray (P) is ordered for P;
C3, get back to step C1, repeat this process, until travel through complete.
4. license plate character recognition method as claimed in claim 3, is further included in above-mentioned steps D and again determines above-mentioned wordSymbol edge image IedgeThe method on border be:
D1, row traversal to be to determine I from top to bottomedgeUpper marginal position index IndexTop;
D2, row traversal to be to determine I from top to bottomedgeLower limb location index IndexBottom;
D3, from left to right row traversal to be to determine IedgeLeft hand edge location index IndexLeft;
D4, row traversal to be to determine I from right to leftedgeRight hand edge location index IndexRight。
5. want the license plate character recognition method as described in one of 1-4 as right, further comprise in above-mentioned steps G and Character mother plate collectionThe method of coupling is as follows:
1) concentrate and obtain current character template Tamplate at Character mother platei, obtain its horizontal hopping sequences SMHori, vertical transitionSequence SMVert, upper and lower number of transitions density ratio Hop_Density_MTop/Bottom, left and right number of transitions density ratio Hop_Density_MLeft/Right;
2)SHoriWith SMHoriDo and mate, obtain matching degree M1;
3)SVertWith SMVertDo and mate, obtain matching degree M2;
4)Hop_DensityTop/BottomWith Hop_Density_MTop/BottomDo and mate, obtain mating M3;
5)Hop_DensityLeft/RightWith Hop_Density_MLeft/RightDo and mate, obtain matching degree M4;
6) calculate total matching degree Mti:Mti=w1M1+w2M2+w3M3+w4M4
Wherein, w1、w2、w3、w4Be respectively M1、M2、M3、M4Weight, its weight numerical value can be self-defined according to the difference of concrete image;
7) get back to step 1), repeat this process, until travel through complete;
8) get IndexmFor { Mt1,Mt2,…,Mti,…,MtnIn peaked index value, IndexmBe final recognition result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210587347.1A CN103065137B (en) | 2012-12-30 | 2012-12-30 | A kind of license plate character recognition method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210587347.1A CN103065137B (en) | 2012-12-30 | 2012-12-30 | A kind of license plate character recognition method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103065137A CN103065137A (en) | 2013-04-24 |
CN103065137B true CN103065137B (en) | 2016-05-25 |
Family
ID=48107760
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210587347.1A Active CN103065137B (en) | 2012-12-30 | 2012-12-30 | A kind of license plate character recognition method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103065137B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104636748B (en) * | 2013-11-14 | 2018-08-17 | 张伟伟 | A kind of method and device of number plate identification |
CN106423913A (en) * | 2016-09-09 | 2017-02-22 | 华侨大学 | Construction waste sorting method and system |
CN107301429B (en) * | 2017-06-27 | 2020-05-19 | 成都理工大学 | License plate similar character recognition method based on local position value scoring |
CN109834941B (en) * | 2019-04-09 | 2020-08-28 | 台州明创科技有限公司 | Saving type box body 3D printing system |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101329734A (en) * | 2008-07-31 | 2008-12-24 | 重庆大学 | License plate character recognition method based on K-L transform and LS-SVM |
CN101739566A (en) * | 2009-12-04 | 2010-06-16 | 重庆大学 | Self-adapting projection template method-based automobile plate positioning method |
-
2012
- 2012-12-30 CN CN201210587347.1A patent/CN103065137B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101329734A (en) * | 2008-07-31 | 2008-12-24 | 重庆大学 | License plate character recognition method based on K-L transform and LS-SVM |
CN101739566A (en) * | 2009-12-04 | 2010-06-16 | 重庆大学 | Self-adapting projection template method-based automobile plate positioning method |
Non-Patent Citations (2)
Title |
---|
Canny Edge-Detection Based Vehicle Plate Recognition;Allam Mousa;《International Journal of Signal Processing》;20120930;第5卷(第3期);1-6 * |
车牌识别中关键技术的研究与实现;韩立明 等;《计算机工程与设计》;20100930;第31卷(第17期);3919-3923 * |
Also Published As
Publication number | Publication date |
---|---|
CN103065137A (en) | 2013-04-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111563412B (en) | Rapid lane line detection method based on parameter space voting and Bessel fitting | |
CN102375982B (en) | Multi-character characteristic fused license plate positioning method | |
CN103324930B (en) | A kind of registration number character dividing method based on grey level histogram binaryzation | |
CN106156768B (en) | The vehicle registration certificate detection method of view-based access control model | |
CN103971128A (en) | Traffic sign recognition method for driverless car | |
CN104700072B (en) | Recognition methods based on lane line historical frames | |
CN103136528B (en) | A kind of licence plate recognition method based on dual edge detection | |
CN102663378B (en) | Method for indentifying joined-up handwritten characters | |
CN107066986A (en) | A kind of lane line based on monocular vision and preceding object object detecting method | |
CN104299009B (en) | License plate character recognition method based on multi-feature fusion | |
CN105023256B (en) | A kind of image defogging method and system | |
CN105989334B (en) | Road detection method based on monocular vision | |
CN103065137B (en) | A kind of license plate character recognition method | |
CN106529532A (en) | License plate identification system based on integral feature channels and gray projection | |
CN103198315A (en) | License plate character segmentation algorithm based on character outline and template matching | |
CN104573627A (en) | Lane line reservation and detection algorithm based on binary image | |
CN103824091A (en) | Vehicle license plate recognition method for intelligent transportation system | |
CN104200207A (en) | License plate recognition method based on Hidden Markov models | |
CN104200228A (en) | Recognizing method and system for safety belt | |
CN103996030A (en) | Lane line detection method | |
CN106503748A (en) | A kind of based on S SIFT features and the vehicle targets of SVM training aids | |
CN104143091A (en) | Single-sample face recognition method based on improved mLBP | |
CN108734170B (en) | License plate character segmentation method based on machine learning and template | |
CN110733416A (en) | lane departure early warning method based on inverse perspective transformation | |
CN109446882A (en) | Logo feature extraction and recognition methods based on the characteristic quantification that gradient direction divides |
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 | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210517 Address after: No. 6, Jiuhua Road, khuchuang Park, Mianyang, Sichuan Patentee after: Sichuan Jiuzhou Investment Holding Group Co.,Ltd. Address before: 621000 No.6, Jiuhua Road, Mianyang City, Sichuan Province Patentee before: SICHUAN JIUZHOU ELECTRIC GROUP Co.,Ltd. |
|
TR01 | Transfer of patent right |