CN101154270A - License plate binaryzation method based on compensation principle and center section scanning - Google Patents
License plate binaryzation method based on compensation principle and center section scanning Download PDFInfo
- Publication number
- CN101154270A CN101154270A CNA2006101225309A CN200610122530A CN101154270A CN 101154270 A CN101154270 A CN 101154270A CN A2006101225309 A CNA2006101225309 A CN A2006101225309A CN 200610122530 A CN200610122530 A CN 200610122530A CN 101154270 A CN101154270 A CN 101154270A
- Authority
- CN
- China
- Prior art keywords
- license plate
- image
- character
- binaryzation
- car plate
- 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
Landscapes
- Image Processing (AREA)
- Character Input (AREA)
Abstract
The invention provides a two-valued method for license plate based on compensation principle and center region scanning. Firstly, the license plate region is converted through grey level stretching to realize reinforcement of the character region on the license plate; second the grey levels of the character pixel element and the background pixel element g1 and g2 of the reinforced license plate are figured out through a histogram method; thirdly the mean and the standard deviation of the reinforced license plate image is calculated and an illumination compensation factor is also obtained according to the mean and the standard deviation; fourthly an illumination penalty function is accordingly calculated based on the illumination compensation factor; fifthly a two-valued threshold value is consequently obtained according to the illumination penalty function, the standard deviation and the mean; and finally the type of the license plate can be judged through a center region scanning method with normalization treatment. Compared with the prior global dynamic thresholding method, the method of the invention has the advantages of not only quick two-valued process, but also high robustness and realization of complete separate between background and characters.
Description
Technical field
The invention belongs to the image processing technique field, particularly the license plate binary method in the complex background in the license plate recognition technology.
Background technology
Along with the continuous development of China joined WTO and communications and transportation, the popularization of intelligent transportation system (Intelligent TrafficSystem the is called for short ITS) trend that is inevitable.As the important component part of ITS, quick, the accurate realization of vehicle license identification (License Plate Recognition is called for short LPR) plays important effect for the intellectuality of work such as traffic administration, security punishment.Since the nineties in 20th century people just to the automatically research of identification of license plate, its main path is to adopt computer image processing technology that the image of car plate is analyzed, and extracts license board information automatically, determines mark of car.The theory of car plate identification at present reaches its maturity.See document for details: T.Vaito, T.Tsukada, K.Yamada, K.Kozuka, and S.Yamamoto, " Robust license-plate recognition method for passingvehicles under outside environment, " IEEE Trans.Veh.Technol., vol.49, pp.2309-2319, Nov.2000 and document: Shyang-Lih Chang, Li-Shien Chen, YunChung Chung, Sei-Wan Chen, Automatic license plate recognition, Intelligent Transportation Systems, IEEE Transactions on, March 2004 is described.
Before the license plate that splits from background was carried out character recognition, selecting suitable binary-state threshold to realize was an important step in the automatic license plate recognition technology to the cutting apart of character and background.The binaryzation precision of car plate directly influences the degree of accuracy of Character segmentation, and then influences the performance of whole Vehicle License Plate Recognition System.Conventional threshold value system of selection is normally carried out based on gray-scale value, but in real life, owing to be subjected to the unevenness of illumination condition, the environmental factors such as ambiguity of weather conversion, and the influence of factor such as the contaminated degree of car plate itself, be difficult to find a suitable gray threshold that character is separated fully with background.Present most license plate binary methods have just solved the problem of extracting character under the specified conditions from complex background to a certain extent, yet these algorithms to the requirement of condition than higher, when running into new problem or some condition and no longer set up, again must the new method of redesign.License plate binary method general, that can be applicable to all environment and condition does not also successfully find out.Therefore, how to have now on all valuable achievements in research, improving the versatility of license plate binary, the main direction that raising binaryzation precision will become our current research.See document for details: B.Sankur and M.Sezgin, " A survey over image thresholding techniques and quantitative performance evaluation ", Journal of Electronic Imaging, v13, n1, January, p 146-168,2004. and document: Meenen, P.andAdhami, R; " Approaches to image binarization in current automated fingerprint identificationsystems "; Proceedings of the Thirty-Seventh Southeastern Symposium on 20-22 March 2005Page (s): 276-281,2005.
At present, Chang Yong image binaryzation method mainly contains global threshold method and local threshold method two big classes.In the global threshold method, relatively more classical selection of threshold method mainly contains:
(1) histogram method.This method is calculated the grey level histogram of entire image earlier, selects a desirable threshold value according to histogram then.Its advantage be image and background gray scale difference obviously the time effect more outstanding; Shortcoming is that this method is often ignored details easily, often is difficult to obtain desirable effect when having more shade or variation of image grayscale more complicated in the image, thereby has limited the use of said method.See document Zhao Mansuo for details, Yan Hong.Signal Processing andIts Applications, Adaptive Threshold Method for Binarization Blueprint Images.In:Proceedingsof the Fifth International Symposium on ISSPA ' 99,1999,2:931-934
(2) Otsu algorithm.It asks for the binaryzation optimal threshold by compute classes internal variance and inter-class variance.Its advantage is that the stroke on the vehicle license is full through this algorithm process, hollow, fracture do not occur; Shortcoming is that elapsed time is more, does not meet the real-time requirement when calculating inter-class variance and class internal variance.See document P.K.Sahoo for details, S.Soltani, A.K.Wong, and Y.C.Chan, " A survey of thresholding techniques ", Computer Vision, Graphics, and ImageProcessing, vol.41, pp.233-260,1988.
Binarization method based on local threshold has: ..
(1) Niblack method.Its basic thought is to each point in the image, in its r*r neighborhood, calculates the average and the variance of picture element in the neighborhood, obtains binary-state threshold by correction factor then.Its shortcoming is too to have exaggerated the details of image, does not notice the whole structure of image, as long as the background gray scale in the image produces certain variation, this method will be thought background by mistake to be object, and calculated amount is big, and speed is slow.See document Trier O D for details, Jain A K. " Goal-directedEvaluation of Binarization Methods ", IEEE Trans on PAMI, 1995,17 (12): 1991-1201.
(2) Bernsen algorithm.Its shortcoming is that the Bernsen algorithm might cause phenomenons such as pseudo-shadow, stroke fracture, is unfavorable for the correct identification in later stage.See document Zhao Hong for details, Wang Li-min, Wang Gong-yi. " Research on binarizationmethod of license plate recognition in automatic recognition ", Applied Science andTechnology, Vol.31, Mar.2004
The common ground of above-mentioned several license plate binary methods is: these methods all are to have certain condition restriction, therefore are subjected to the influence of factors such as weather, background, illumination easily, and robustness is bad.In case condition changes, bigger fluctuation will take place in their binaryzation accuracy rate, thereby the performance of whole Vehicle License Plate Recognition System reduces greatly.
Summary of the invention
Task of the present invention provides a kind of license plate binary method based on illumination compensation principle and central area scanning, and it has realizes character and the fine characteristics of separating of background under the environment of illumination unevenness.According to binarization method of the present invention, it comprises the following step:
Grey level histogram has been described the gray level content of image, has reflected the gray distribution of image situation.It adds up each gray level occurs in the license plate image number of times or probability by whole license plate area is scanned, and concrete statistical formula is: grayA (1, A (i, j)+1)=grayA (1, A (i, j)+1)+1, wherein, the line position of i presentation video, the column position of j presentation video, the A license plate image, (grayA represents the grey level histogram matrix to A for i, a j) pixel value in the expression license plate image.From histogram, can obtain minimum and maximum gray-scale value x
1And x
2, two threshold values of grey level stretching conversion just.
The grey level stretching conversion is the simplest a kind of piecewise linear transform function.The concrete transformation for mula of grey level stretching is: as x＜x
1The time,
Work as x
1≤ x≤x
2The time,
As x＞x
2The time,
Wherein, x is the gray level of pixel in the original license plate image, and f (x) is that picture element x is through the gray level after strengthening, (x
1, y
1) and (x
2, y
2) be two threshold values of grey level stretching conversion
(1) grey level histogram of the license plate image after calculate strengthening, and utilize grey level histogram to calculate the gray level g of character picture element and background pixels point in the car plate after strengthening
1And g
2And the average and the standard deviation of the license plate image after strengthening.Wherein, consistent in the computing method of grey level histogram and the step 1, only A is the license plate image after strengthening; The gray level g of character picture element
1Can get the gray level g of background pixels point by the average of calculating in the grey level histogram preceding 30% point
2Get by the average of calculating the point of back 70% in the grey level histogram; And the image average can be by formula M=r
1* g
1+ r
2* g
2Calculate, the standard deviation of image can be by formula
Calculate and get, wherein, r
1Be the shared ratio of character pixel in the license plate image, r
2Be the shared ratio of background pixels in the license plate image, g
1And g
2Be respectively the gray level of character picture element and background pixels point in the car plate after the enhancing, and 0＜r
1＜r
2＜1, r
1+ r
2=1, M is for strengthening the average of back license plate image, and C is for strengthening the standard deviation of back license plate image.
(2) calculate illumination compensation function f (L).Illumination compensation function representation intensity of illumination is to the influence degree of binary-state threshold.The computing formula of concrete illumination compensation function f (L) is: when 0＜L≤1,
When 1＜L＜2,
When L 〉=2,
Wherein, L is the illumination compensation factor, and e is an exponential function, and f (L) is the illumination compensation function.Illumination compensation factor L judges the factor of the exposure status of license plate image with the form of decision illumination compensation function, and its computing formula is
Wherein, M is for strengthening the average of back license plate image, and C is for strengthening the standard deviation of back license plate image.When 0＜L≤1, the under-exposure of expression license plate image; When 1＜L＜2, the license plate image normal exposure; When L 〉=2, the expression license plate image is over-exposed.
(3) threshold value of calculating binaryzation, and to the license plate image after strengthening is carried out binaryzation.In conjunction with the illumination compensation function that obtains above, standard deviation and average, the threshold value of calculating binaryzation.Concrete binary-state threshold T is calculated by following formula:
Wherein, M is for strengthening the average of back license plate image, and C is for strengthening the standard deviation of back license plate image, and f (L) is the illumination compensation function, r
1Be the shared ratio of character pixel in the license plate image, r
2Be the shared ratio of background pixels in the license plate image, T is a binary-state threshold.Utilize binary-state threshold T that the license plate image f (x) after strengthening is carried out binaryzation then.Concrete binarization method is: when f (x) 〉=T, and f (y)=255; When f (x)＜T, f (y)=0.Wherein, T is a binary-state threshold, and f (x) is the license plate image after strengthening, and f (y) is the license plate image after the preliminary binaryzation.
(1) determines the position of car plate central area.In the method, the position of central area is a little
With
The zone that surrounds, wherein x is the width of license plate image, y is the height of license plate image.
(2) calculate two-value license plate area horizontal direction black and white line segment length sum, and statistics is black, the maximum length separately of white line section.Judge black line segment to begin be to seek gray scale to drop to 0 point from 255, the black line segment end point is that gray scale is raised to 255 point or row end from 0; Judge the white line section to begin be to seek gray scale to be raised to 255 point from 0, white line section end point is that gray scale drops to 0 point or row end from 255.
(3) maximum length of relatively black, white line section judges that original car plate type is white gravoply, with black engraved characters or black matrix wrongly written or mispronounced character.If the longest white wire segment length, thinks then that this car plate is a white gravoply, with black engraved characters greater than the longest black line segment length, otherwise think that car plate is the black matrix wrongly written or mispronounced character.
(4) determine final license plate binary image according to The above results.If car plate is the black matrix wrongly written or mispronounced character, then final license plate binary image is exactly the license plate image after the preliminary binaryzation; If car plate is a white gravoply, with black engraved characters, then final license plate binary image is obtained by formula f (z)=255-f (y), and wherein, f (y) is the value of the license plate image after the preliminary binaryzation, and f (z) is the value of final license plate binary image.
By above step, we just can be converted into bianry image with the gray level image of car plate, and character and the effective of background separate in the realization car plate.
Need to prove:
1. the license plate image that uses in the step 1 is the gray level image that obtains through behind the car plate finder, does not need to do gradation conversion again and handles.
2. recomputate grey level histogram in the first step of step 2 and be in order to determine in this step that gray level is at preceding 30% point.
3. r in the first step of step 2
1Be the shared ratio of character pixel in the license plate image, r
2Be the shared ratio of background pixels in the license plate image, 0＜r
1＜r
2＜1, r
1+ r
2=1.R in the method
1Value be 0.318, r
2Value be 0.682.
4. why calculating the illumination compensation function in second of step 2 step is because in taking on the spot, license plate image is usually because the influence of factor such as uneven illumination is even, under-exposed or over-exposed situation occur, need revise of the influence of illumination factor by a function to binary-state threshold.
5. because car plate coloured image one has 3 kinds of main types, promptly yellow end surplus, wrongly written or mispronounced character of the blue end and black matrix wrongly written or mispronounced character, after the 3rd step binaryzation through gradation conversion and step 2, license plate image one has 2 types, be white gravoply, with black engraved characters and black matrix wrongly written or mispronounced character, therefore before carrying out character locating, need to come car plate is carried out normalized by the central area scanning method.
The present invention adopts a kind of license plate binary method based on compensation principle and central area scanning, at first carries out conversion by grey level stretching transfer pair license plate area, realizes the enhancing to the character zone in the car plate; Then use the gray level g of character picture element and background pixels point in the car plate after histogram method calculates enhancing
1And g
2Calculate the average and the standard deviation of the license plate image after strengthening then, and utilize average and standard deviation to obtain the illumination compensation factor; Then calculate the illumination compensation function according to the illumination compensation factor; According to illumination compensation 0 function, standard deviation and average, calculate the threshold value of binaryzation then; Use the central area scanning method to judge the type of car plate at last, carry out normalized.
Innovation part of the present invention is:
The present invention adopts a kind of license plate binary method based on compensation principle and central area scanning, the fireballing characteristics of overall dynamic thresholding method binaryzation had both been made full use of, meet the real-time requirement of vehicle license recognition system, introduce the illumination compensation function again and remedied the shortcoming that descends rapidly owing to the even overall dynamic thresholding method performance that causes of uneven illumination, realized separating fully of background pixels and character pixel well.Simultaneously, introduce the car plate of central area scanning method after again and analyze, and make normalized, obtain final binaryzation result preliminary binaryzation.Therefore, method of the present invention is compared with traditional overall dynamic thresholding method, and not only binaryzation speed is fast, and has the robustness height, realizes characteristics such as separating fully of background and character.
Description of drawings
Fig. 1 is the license plate image synoptic diagram that the present invention finally obtains.
Wherein, X1, X2, X3, X4, X5, X6 and X7 represent respectively car plate first, second, the 3rd, the 4th, the 5th, the 6th and the 7th character.
Fig. 2 is the grey level stretching transforming function transformation function.Horizontal ordinate is the gray level before the conversion, and ordinate is the gray level after the conversion.
Fig. 3 is the formula of illumination compensation function.
Fig. 4 is original license plate grey level image.
Fig. 5 is the license plate image after strengthening.
Fig. 6 is the license plate image after the binaryzation.
Embodiment
Adopt method of the present invention, at first use Matlab language compilation car plate identification software and license plate binary software; Adopt the original image of camera head automatic shooting vehicle then at porch, charge station and other any correct positions of highway; Then the vehicle original image that photographs is input in the car plate identification software as source data and handles; The car plate of orienting is exported the result of license plate binary at last again by license plate binary software.Obtain after adopting 320 car plate identification softwares to handle, comprise that vehicle gray level image under the different conditions such as different weather such as rainy day, greasy weather, fine day and car plate level, license plate sloped, vehicle movement, stationary vehicle is as source data, basically can both realize separating fully of character and background well, accuracy rate is near 100%.
In sum, method of the present invention makes full use of the characteristics of global threshold method and illumination compensation principle and the characteristic of centre scan method, thereby realizes the binaryzation of car plate rapidly and accurately.
Claims (2)
1. the present invention relates to a kind of license plate binary method, it is characterized in that comprising the steps: based on compensation principle and central area scanning
Step 1. license plate image strengthens.
Utilization grey level histogram and grey level stretching transfer pair license plate area carry out conversion, realize the enhancing to the character zone in the car plate.
Step 2. adopts the binarization method based on the illumination compensation principle that the car plate after strengthening is carried out binaryzation.Its basic ideas are as follows:
(1) grey level histogram of the license plate image after calculate strengthening, and utilize grey level histogram to calculate the gray level g of character picture element and background pixels point in the car plate after strengthening
1And g
2And the average and the standard deviation of the license plate image after strengthening;
(2) calculate illumination compensation function f (L);
(3) threshold value of calculating binaryzation, and to the license plate image after strengthening is carried out binaryzation;
Step 3. adopts the central area scanning method that car plate is handled.The central area scanning method is a kind of sector scanning method of judging the car plate type.Its concrete thinking is as follows:
(1) determines the position of car plate central area;
(2) calculate two-value license plate area horizontal direction black and white line segment length sum, and statistics is black, the maximum length separately of white line section;
(3) maximum length of relatively black, white line section judges that original car plate type is white gravoply, with black engraved characters or black matrix wrongly written or mispronounced character;
(4) determine final license plate binary image according to The above results;
By above step, we just can be converted into bianry image with the gray level image of car plate, and character and the effective of background separate in the realization car plate.
2. said as claim 1, a kind of license plate binary method based on compensation principle and central area scanning, it is characterized in that: both made full use of the fireballing characteristics of overall dynamic thresholding method binaryzation, meet the real-time requirement of vehicle license recognition system, introduce the illumination compensation function again and remedied the shortcoming that descends rapidly owing to the even overall dynamic thresholding method performance that causes of uneven illumination, realized separating fully of background pixels and character pixel well.Simultaneously, introduce the car plate of central area scanning method after again and analyze, and make normalized, obtain final binaryzation result preliminary binaryzation.Therefore, method of the present invention is compared with traditional overall dynamic thresholding method, and not only binaryzation speed is fast, and has the robustness height, realizes characteristics such as separating fully of background and character.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2006101225309A CN101154270A (en) | 2006-09-30 | 2006-09-30 | License plate binaryzation method based on compensation principle and center section scanning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2006101225309A CN101154270A (en) | 2006-09-30 | 2006-09-30 | License plate binaryzation method based on compensation principle and center section scanning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101154270A true CN101154270A (en) | 2008-04-02 |
Family
ID=39255917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2006101225309A Pending CN101154270A (en) | 2006-09-30 | 2006-09-30 | License plate binaryzation method based on compensation principle and center section scanning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101154270A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101877050B (en) * | 2009-11-10 | 2012-08-22 | 青岛海信网络科技股份有限公司 | Automatic extracting method for characters on license plate |
| CN103034855A (en) * | 2012-12-05 | 2013-04-10 | 曙光信息产业(北京)有限公司 | Method for identifying character zone in picture |
| CN103267498A (en) * | 2013-05-09 | 2013-08-28 | 北京科技大学 | Automatic digital quantizing method for measuring iron ore roughness |
| CN103366167A (en) * | 2012-03-26 | 2013-10-23 | 塔塔顾问服务有限公司 | System and method for processing image for identifying alphanumeric characters present in a series |
| CN103440478A (en) * | 2013-08-27 | 2013-12-11 | 电子科技大学 | Face detection method based on HOG characteristics |
| CN105957037A (en) * | 2016-05-09 | 2016-09-21 | 北京小米移动软件有限公司 | Image enhancing method and image enhancing device |
| CN107358235A (en) * | 2017-07-17 | 2017-11-17 | 深圳源广安智能科技有限公司 | A kind of traffic surveillance and control system for peccancy detection |
| CN111062910A (en) * | 2019-11-13 | 2020-04-24 | 易思维（杭州）科技有限公司 | Local threshold segmentation method and defect detection method |
| CN111539935A (en) * | 2020-04-24 | 2020-08-14 | 江苏大学 | Online cable surface defect detection method based on machine vision |
| CN111832561A (en) * | 2020-07-03 | 2020-10-27 | 深圳思谋信息科技有限公司 | Character sequence recognition method, device, equipment and medium based on computer vision |
-
2006
- 2006-09-30 CN CNA2006101225309A patent/CN101154270A/en active Pending
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101877050B (en) * | 2009-11-10 | 2012-08-22 | 青岛海信网络科技股份有限公司 | Automatic extracting method for characters on license plate |
| CN103366167A (en) * | 2012-03-26 | 2013-10-23 | 塔塔顾问服务有限公司 | System and method for processing image for identifying alphanumeric characters present in a series |
| CN103366167B (en) * | 2012-03-26 | 2017-01-18 | 塔塔顾问服务有限公司 | System and method for processing image for identifying alphanumeric characters present in a series |
| CN103034855A (en) * | 2012-12-05 | 2013-04-10 | 曙光信息产业(北京)有限公司 | Method for identifying character zone in picture |
| CN103267498A (en) * | 2013-05-09 | 2013-08-28 | 北京科技大学 | Automatic digital quantizing method for measuring iron ore roughness |
| CN103267498B (en) * | 2013-05-09 | 2016-04-27 | 北京科技大学 | Iron ore roughness automatic digital measures of quantization method |
| CN103440478B (en) * | 2013-08-27 | 2016-08-10 | 电子科技大学 | A kind of method for detecting human face based on HOG feature |
| CN103440478A (en) * | 2013-08-27 | 2013-12-11 | 电子科技大学 | Face detection method based on HOG characteristics |
| CN105957037A (en) * | 2016-05-09 | 2016-09-21 | 北京小米移动软件有限公司 | Image enhancing method and image enhancing device |
| CN105957037B (en) * | 2016-05-09 | 2018-11-06 | 北京小米移动软件有限公司 | Image enchancing method and device |
| CN107358235A (en) * | 2017-07-17 | 2017-11-17 | 深圳源广安智能科技有限公司 | A kind of traffic surveillance and control system for peccancy detection |
| CN111062910A (en) * | 2019-11-13 | 2020-04-24 | 易思维（杭州）科技有限公司 | Local threshold segmentation method and defect detection method |
| CN111539935A (en) * | 2020-04-24 | 2020-08-14 | 江苏大学 | Online cable surface defect detection method based on machine vision |
| CN111832561A (en) * | 2020-07-03 | 2020-10-27 | 深圳思谋信息科技有限公司 | Character sequence recognition method, device, equipment and medium based on computer vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101154270A (en) | License plate binaryzation method based on compensation principle and center section scanning | |
| KR102030628B1 (en) | Recognizing method and system of vehicle license plate based convolutional neural network | |
| CN109447034B (en) | Traffic sign detection method in automatic driving based on YOLOv3 network | |
| CN105373794B (en) | A kind of licence plate recognition method | |
| Al-Ghaili et al. | Vertical-edge-based car-license-plate detection method | |
| Izidio et al. | An embedded automatic license plate recognition system using deep learning | |
| CN112766188B (en) | Small target pedestrian detection method based on improved YOLO algorithm | |
| CN107273896A (en) | A kind of car plate detection recognition methods based on image recognition | |
| CN109726717B (en) | Vehicle comprehensive information detection system | |
| CN101154271A (en) | License plate character segmentation method based on fast area labeling algorithm and license plate large-spacing locating method | |
| US20040086153A1 (en) | Methods and systems for recognizing road signs in a digital image | |
| CN101334836A (en) | License plate positioning method incorporating color, size and texture characteristic | |
| Xiang et al. | Lightweight fully convolutional network for license plate detection | |
| Shujuan et al. | Real-time vehicle detection using Haar-SURF mixed features and gentle AdaBoost classifier | |
| CN111881832A (en) | Lane target detection method, device, equipment and computer readable storage medium | |
| CN111242046B (en) | Ground traffic sign recognition method based on image retrieval | |
| CN113361467A (en) | License plate recognition method based on field adaptation | |
| CN115601717B (en) | Deep learning-based traffic offence behavior classification detection method and SoC chip | |
| Hatolkar et al. | A survey on road traffic sign recognition system using convolution neural network | |
| CN109460722A (en) | A kind of license plate intelligent identification Method | |
| CN113971792A (en) | Character recognition method, device, equipment and storage medium for traffic sign board | |
| Khan et al. | Performance enhancement method for multiple license plate recognition in challenging environments | |
| CN106663212B (en) | Character recognition device, character recognition method, and computer-readable storage medium | |
| Chen et al. | License plate recognition for moving vehicles using a moving camera | |
| Wang et al. | Smart road vehicle sensing system based on monocular vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20080402 |