CN103699876A - Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images - Google Patents
Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images Download PDFInfo
- Publication number
- CN103699876A CN103699876A CN201310613538.5A CN201310613538A CN103699876A CN 103699876 A CN103699876 A CN 103699876A CN 201310613538 A CN201310613538 A CN 201310613538A CN 103699876 A CN103699876 A CN 103699876A
- Authority
- CN
- China
- Prior art keywords
- character
- image
- license number
- feature
- carried out
- 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.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
- Character Input (AREA)
Abstract
The invention provides a method for identifying a vehicle number based on linear array CCD (Charge Coupled Device) images. The method comprises the following steps: acquiring a real-time image of the vehicle number; acquiring the approximate location of the vehicle number from screenshot of the real-time image; determining the accurate location of the vehicle number; dividing the vehicle number in the image into single characters; extracting the features of the divided single characters; comparing the extracted features with the features in a character library to obtain a result. The method provided by the invention can effectively improve vehicle number acquisition accuracy through image capture, and can greatly improve the identification speed by correspondingly reducing the area of image for identification in the technical scheme.
Description
Technical field
The invention relates to image processing field, particularly a kind of method and device based on linear array CCD image identification license number
Background technology
In organization of rail transport, reading, check locomotive identification is a job of wasting time and energy, and the way that manually reads record usually there will be again artificial unnecessary mistake.Along with the development of bullet train in China, some website vehicles while passings are frequent, the exercises of calculating vehicle, and arrange and organize according to it work that becomes a mixed and disorderly complexity.Important in ring---the automatic identification of license number seems particularly important as in Information-based Railway. Digital Image Processing because its processing accuracy is high, contents processing is abundant, can carry out complicated nonlinear operation and good flexibility.Become the license number first-selection of identification automatically.But how the corresponding character of being identified as of image font size accurate stable is processed and remained a difficult problem for computing machine.Line array CCD is simple in structure, and cost is lower.Can store a line TV signal simultaneously. because the number of its single photosensitive unit can be done a lot, under the prerequisite of equal measuring accuracy, it is larger that its measurement range can be done, and due to line array CCD real-time Transmission light-to-current inversion signal with self-scanning speed is fast, frequency response is high, can realize kinetic measurement, and can under low-light (level), work, so line array CCD is widely used in many fields such as product size measurement and classification, noncontact dimension measurement, bar code.
Summary of the invention
The problem that the invention will solve be how by picture catching, to obtain license number fast and accurately respective digital information for system.
For solving the problems of the technologies described above, the technical scheme that the invention adopts is: a kind of method based on linear array CCD image identification license number, described method comprises the steps:
Obtain the realtime graphic of license number;
From the sectional drawing of realtime graphic, obtain the Position Approximate of license number;
Determine license number position accurately;
License number in picture is divided into single character;
Single character after cutting apart is carried out to feature extraction;
Feature in the feature of extraction and character repertoire is compared, obtain result.
Further, the described Position Approximate that obtains license number from sectional drawing comprises the steps:
The image that is positioned at license number position height in the realtime graphic of license number is intercepted;
Truncated picture is carried out to gaussian filtering;
Image after gaussian filtering is processed carries out the operation of Sobel operator;
Search the central point in the highest region of brightness in the image after processing;
According to the region breadth extreme of license number and maximum height, set rectangle;
The rectangular centre point of setting is overlapped with territory, brightness highest region central point, take the Position Approximate that rectangular area is license number.
Further, described definite license number position accurately comprises the steps:
The sectional drawing obtaining after Position Approximate is carried out, based on the operation of Canny operator, obtaining edge-detected image;
Character pitch distance and two predetermined threshold value of character height (DX, DY) are set;
Edge detected image is carried out Y-direction histogram analysis, searches the horizontal seat mark – X ' that meets character pitch predetermined threshold value;
Edge detected image is carried out directions X histogram analysis, searches the ordinate-Y ' that meets character height predetermined threshold value;
Determine license number position accurately.
Further, the described license number by picture is divided into single character and comprises the steps:
Image after spotting is carried out to binary conversion treatment;
Suitable inter-character space predetermined threshold value is set;
Image after binary conversion treatment is carried out to the histogram analysis of Y-direction, search the coordinate that meets inter-character space predetermined threshold value;
According to meeting inter-character space coordinate, divide character.
Further, the described single character to after cutting apart carries out feature extraction and comprises the steps:
Character after cutting apart is carried out to Corner Detection;
The proper vector of the character after extracting each and cutting apart.
Further, the described feature by the feature of extraction and character repertoire is compared, and obtains result and comprises the steps:
Character feature in the character feature of extraction and character repertoire is carried out to distance to be calculated;
The character of selected characteristic vector distance minimum is matching result.
Further, described characteristic character storehouse is set up and is comprised the steps:
The image pattern that includes license number is divided into single character;
Single character picture is carried out to gaussian filtering;
The image that carried out gaussian filtering is carried out to binary conversion treatment;
Image after above-mentioned processing is carried out to interpolation conversion, make the wide height of image consistent with the wide high standard of template image
By the proper vector of Corner Detection operator extraction character;
Repeat a plurality of image patterns that comprise license number to carry out aforesaid operations, generate character feature storehouse.
Further, the proper vector of described character comprises profile corner location, angle point distance, angle point angle.
Further, described gaussian filtering is 2-d gaussian filters
Further, described Sobel operator is
Further, describedly character after cutting apart carried out to Corner Detection adopt harris algorithm, Harris operator:
I
xfor image is at directions X difference result, I
yfor image is in Y-direction difference result
Angle point amount is calculated:
According to a further aspect in the invention, also provide a kind of device based on linear array CCD image identification license number, having comprised:
License number image acquiring device, for obtaining the realtime graphic that comprises license number image;
The about position of license number image acquiring device, obtains for obtain about position the sectional drawing of license number from realtime graphic;
License number accurate location image acquiring device, for obtaining license number accurate location from the about position of license number sectional drawing and sectional drawing obtains;
Character segmentation device, for being single character combination by the image Character segmentation that comprises license number accurate location;
Character feature extraction element, for extracting the proper vector of single character picture;
Character feature comparison match device, for comparing the character feature vector of extraction to mate with character feature in character repertoire; And
Character repertoire, for storing the character feature that can be used for comparison match.
Further, in the device of described image recognition license number, the about position of license number image acquiring device comprises:
Height image capture device, intercepts for the realtime graphic of license number being positioned to license number position height image;
Gaussian filtering device, for carrying out gaussian filtering operation to intercepting license number position height image;
Sobel operator device, carries out the operation of Sobel operator for the image after gaussian filtering is processed;
Is device searched in brightness, for searching the central point in the highest region of image brightness after processing?
Rectangle setting device, for setting rectangle according to the region breadth extreme of license number and maximum height;
Coincidence arrangement, for the rectangular centre point of setting is overlapped with territory, brightness highest region central point, take the Position Approximate that rectangular area is license number.
Further, in the device of described image recognition license number, license number accurate location image acquiring device comprises:
Edge detecting device, for carrying out the rim detection based on Canny operator to the sectional drawing obtaining after Position Approximate is processed;
Threshold value setting device, for arranging two threshold values of character pitch height and width;
Device is searched in Y-direction analysis, for edge detected image, carries out Y-direction histogram analysis, searches the coordinate that meets character interval threshold;
Device is searched in directions X analysis, for edge detected image, carries out directions X histogram analysis, searches the coordinate that meets character height threshold.
Further, described Character segmentation device comprises:
Binary conversion treatment device, for carrying out binary conversion treatment by the image after spotting;
Inter-character space threshode devices, for arranging suitable inter-character space threshold value;
Y-direction analysis and coordinate are searched device, carry out the histogram of Y-direction for the image to after binary conversion treatment, search the coordinate that meets inter-character space;
Device divided in character, for dividing character according to meeting inter-character space coordinate.
Further, described character feature extraction element comprises:
Corner Detection device, carries out Corner Detection for the character to after cutting apart;
Feature-vector extraction means, for the proper vector of the character after extracting each and cutting apart.
Further, described character feature comparison match device comprises:
Apart from calculation element, for the character feature of extraction and character repertoire character feature are carried out to distance calculating;
Result coalignment is matching result for the character of selected characteristic vector distance minimum.
Further, the device of described image recognition license number also comprises character repertoire apparatus for establishing, and described character repertoire apparatus for establishing comprises:
Character segmentation device, for being divided into single character by the image pattern that includes license number;
Gaussian filtering device, for carrying out gaussian filtering by single character picture;
Binaryzation device, for carrying out binary conversion treatment by the image that carried out gaussian filtering;
Normalized device, carries out interpolation conversion for the image to after above-mentioned processing, makes the wide height of image consistent with the wide high standard of template image
Feature-vector extraction means, for passing through the proper vector of Corner Detection operator extraction character;
Character feature storehouse, for storing a plurality of character feature vectors.
Advantage and good effect that the invention has are: adopt the technical program, can effectively improve the accuracy rate of obtaining license number by picture catching, due to the corresponding image area of identifying that reduced also in the technical program, can increase substantially recognition speed.
Accompanying drawing explanation
Fig. 1 is the image pattern schematic diagram providing in an embodiment in the present invention
Fig. 2 is the motor-car license number image schematic diagram gathering in an embodiment in the present invention
Fig. 3 sets up the schematic flow sheet in character feature storehouse in an embodiment in the present invention
Fig. 4 is the schematic flow sheet to image recognition character in an embodiment in the present invention
embodiment
For to the more deep understanding of the invention, enumerate a specific embodiment below, and by reference to the accompanying drawings, the invention is described in further detail.
In the present embodiment, first by image pattern, gather, and recognition system is trained, in order to set up corresponding character feature storehouse.
As shown in Figure 1, the example that Fig. 1 is the image pattern that provides in this example, in fact, trains recognition system for reaching, in order to set up the object in corresponding character feature storehouse, adopted multinomial figure decent for.The image pattern gathering can be from photo or alternate manner.
First sample license number is divided into single character, can license number be divided into single character by manual type or alternate manner, should be as much as possible according to the single character font complete display after cutting apart, and the size of each character picture is identical, to facilitate the later stage that corresponding character feature can be provided accurately.
For the single character picture of having cut apart, carry out gaussian filtering operation, generally adopt 2-d gaussian filters operation, can adopt following formula:
Image is carried out to 2-d gaussian filters operation, and the fundamental purpose of this step is to eliminate Gaussian noise, for to image pattern noise abatement, facilitates follow-up operation.
In general, image pattern may be gray level image, is likely also coloured image, for colour, should be translated into as far as possible gray scale, facilitates post-processed, can to it, carry out binaryzation by the gray-scale value of pixel, and the formula of binaryzation is as follows:
For the picture as sample, it is very important meeting correct size, if slightly distortion brings larger error will to the processing in later stage, for the picture that does not meet size, can utilize method of interpolation that picture is expanded, make it to reach standard size.Method of interpolation is the pixel according to original image, according to certain compute mode, calculates, and produces the pixel making new advances, and is inserted into the contiguous gap of original pixel, thereby realizes the object that has increased pixel total amount and increased picture element density.
By the proper vector V of Corner Detection operator extraction character
i, proper vector comprises: profile corner location, angle point distance, angle point angle V
i=(X
i, Y
i, L
i, θ
i), and store all Corner Feature vectors of this character;
Harris operator:
I
xfor image is at directions X difference result, I
yfor image is in Y-direction difference result
Angle point amount is calculated:
By the proper vector V of each character outline
icarry out classification based training, generate final character feature storehouse.Character feature storehouse can constantly increase new image is practised, and the scope that makes it character feature remains on rationally, level accurately.
The motor-car license number image of Fig. 2 for gathering in this example, red block is to find out license number exact image position, for caught image, if search contrast for whole image, technical degree of accuracy and operand all can become large problem.
For the image capturing, first will determine its corresponding accurate location with font size image, because the height of motor-car is fixed, and camera head position and highly also fixing, in general, the position that font size occurs at the picture collecting is also relatively fixing, can this part of picture be intercepted out by default height.
The above-mentioned image intercepting out is carried out to gaussian filtering, Sobel operator operation:
2-d gaussian filters formula:
Sobel operator:
Image after above-mentioned processing, license number regional luminance value is high, and the rectangle of W*H is set, and roughly picture position of license number is determined in the highest region of mean flow rate in detected image.(W is license number region breadth extreme, and H is license number region maximum height), by this step operation, can determine the Position Approximate of font size in image, and this Position Approximate should be greater than physical size, still needs next step operation can obtain position accurately.
License number image is carried out based on Canny rim detection, by the histogram analysis of the histogram analysis of Y-direction marginal information, directions X marginal information being carried out to the accurate location of license number image.
First image is carried out to the rim detection based on Canny operator;
Character pitch distance and two predetermined threshold value of character height (DX, DY) are set;
This preset value is that we set according to the actual conditions in history image.(preset value using in this patent: DX=30, DY=85) edge detected image is carried out Y-direction histogram analysis, searches and meets license number region and the interregional coordinate-X ' every predetermined threshold value DX of Chinese character;
Edge detected image is carried out directions X histogram analysis, searches the Zuo Biao – Y ' that meets license number character height predetermined threshold value;
Definite license number Wei Zhi – accurately [X ', Y '].
After completing aforesaid operations, each font size need to be split from picture, cut apart and can adopt with the following method:
Symbol image binaryzation;
The predetermined threshold value D of character pitch is set, and preset value can be set according to the interval of character in real image.The preset value here using: D=10.
Binary image carries out the histogram analysis of Y-direction, searches the coordinate that meets inter-character space, and character is cut apart.Finally the character after cutting apart is carried out to feature extraction, its extracting mode is identical with the above-mentioned method of setting up character repertoire, at this, do not repeat, character feature in the character feature of extraction and character repertoire is carried out to distance and calculate, choosing minimal characteristic vector distance is final recognition result.
Min(D
i)={||V-V
i||}
Above the embodiment of the invention is had been described in detail, but described content is only the preferred embodiment of the invention, can not be considered to for limiting practical range of the present invention.All equalization variations of doing according to the invention scope and improvement etc., within all should still belonging to this patent covering scope.
Claims (10)
1. the method based on linear array CCD image identification license number, is characterized in that described method comprises the steps:
Obtain the realtime graphic of license number;
From the sectional drawing of realtime graphic, obtain the Position Approximate of license number;
Determine license number position accurately;
License number in picture is divided into single character;
Single character after cutting apart is carried out to feature extraction;
Feature in the feature of extraction and character repertoire is compared, obtain result; The wherein said Position Approximate that obtains license number from sectional drawing comprises the steps:
The image that is positioned at license number position height in the realtime graphic of license number is intercepted;
Truncated picture is carried out to gaussian filtering;
Image after gaussian filtering is processed carries out the operation of Sobel operator;
Search the central point in the highest region of brightness in the image after processing;
According to the region breadth extreme of license number and maximum height, set rectangle;
The rectangular centre point of setting is overlapped with territory, brightness highest region central point, take the Position Approximate that rectangular area is license number;
Described determines that license number position comprises the steps: accurately
The sectional drawing obtaining after Position Approximate is processed is operated based on Canny operator, obtain edge-detected image;
Character pitch distance and two threshold values of character height are set;
Edge detected image is carried out Y-direction histogram analysis, searches the horizontal ordinate X that meets character pitch predetermined threshold value;
Edge detected image is carried out directions X histogram analysis, searches the ordinate Y that meets character height predetermined threshold value;
Determine license number position accurately;
The described license number by picture is divided into single character and comprises the steps:
Image after spotting is carried out to binary conversion treatment;
Suitable inter-character space threshold value is set;
Image after binary conversion treatment is carried out to the histogram analysis of Y-direction, search the coordinate that meets inter-character space predetermined threshold value;
According to meeting inter-character space coordinate, divide character;
The described single character to after cutting apart carries out feature extraction and comprises the steps:
Character after cutting apart is carried out to Corner Detection;
The proper vector of the character after extracting each and cutting apart.
The described feature by the feature of extraction and character repertoire is compared, and obtains result and comprises the steps:
Character feature in the character feature of extraction and character repertoire is carried out to distance to be calculated;
The character of selected characteristic vector distance minimum is matching result.
2. the method based on linear array CCD image identification license number according to claim 1, is characterized in that described characteristic character storehouse foundation comprises the steps:
The image pattern that includes license number is divided into single character;
Single character picture is carried out to gaussian filtering;
The image that carried out gaussian filtering is carried out to binary conversion treatment;
Image after above-mentioned processing is carried out to interpolation conversion, make the wide height of image consistent with the wide high standard of template image
By the proper vector of Corner Detection operator extraction character;
Repeat a plurality of image patterns that comprise license number to carry out aforesaid operations, generate character feature storehouse.
3. the method based on linear array CCD image identification license number according to claim 7, is characterized in that: the proper vector of described character comprises profile corner location angle point distance, angle point angle.
4. the method based on linear array CCD image identification license number according to claim 2, is characterized in that: described gaussian filtering is 2-d gaussian filters
5. the method based on linear array CCD image identification license number according to claim 2, is characterized in that: described Sobel operator is
。
6. according to claim 5 or the method based on linear array CCD image identification license number claimed in claim 7, it is characterized in that described character after cutting apart is carried out to Corner Detection adopt harris algorithm, Harris operator:
I
xfor image is at directions X difference result, I
yfor image is in Y-direction difference result
Angle point amount is calculated:
7. based on linear array CCD image, identify a device for license number, it is characterized in that comprising:
License number image acquiring device, for obtaining the realtime graphic that comprises license number image;
The about position of license number image acquiring device, obtains for obtain about position the sectional drawing of license number from realtime graphic;
License number accurate location image acquiring device, for obtaining license number accurate location from the about position of license number sectional drawing and sectional drawing obtains;
Character segmentation device, for being single character combination by the image Character segmentation that comprises license number accurate location;
Character feature extraction element, for extracting the proper vector of single character picture;
Character feature comparison match device, for comparing the character feature vector of extraction to mate with character feature in character repertoire; And
Character repertoire, for storing the character feature that can be used for comparison match; Wherein
In the device of described image recognition license number, the about position of license number image acquiring device comprises:
Height image capture device, intercepts for the realtime graphic of license number being positioned to license number position height image;
Gaussian filtering device, for carrying out gaussian filtering operation to intercepting license number position height image;
Sobel operator device, carries out the operation of Sobel operator for the image after gaussian filtering is processed;
Device is searched in brightness, for searching the central point in the highest region of image brightness after processing;
Rectangle setting device, for setting rectangle according to the region breadth extreme of license number and maximum height;
Coincidence arrangement, for the rectangular centre point of setting is overlapped with territory, brightness highest region central point, take the Position Approximate that rectangular area is license number;
In the device of described image recognition license number, license number accurate location image acquiring device comprises:
Edge detecting device, for carrying out rim detection to the sectional drawing obtaining after Position Approximate is processed;
Threshold value setting device, for arranging two threshold values of character pitch height and width;
Device is searched in Y-direction analysis, for edge detected image, carries out Y-direction histogram analysis, searches the coordinate that meets character interval threshold;
Device is searched in directions X analysis, for edge detected image, carries out directions X histogram analysis, searches the coordinate that meets character height threshold.
Described Character segmentation device comprises:
Binary conversion treatment device, for carrying out binary conversion treatment by the image after spotting; Inter-character space threshode devices, for arranging suitable inter-character space threshold value;
Y-direction analysis and coordinate are searched device, carry out the histogram of Y-direction for the image to after binary conversion treatment, search the coordinate that meets inter-character space;
Device divided in character, for dividing character according to meeting inter-character space coordinate.
8. the device based on linear array CCD image identification license number according to claim 7, is characterized in that described character feature extraction element comprises:
Corner Detection device, carries out Corner Detection for the character to after cutting apart;
Feature-vector extraction means, for the proper vector of the character after extracting each and cutting apart.
9. the device based on linear array CCD image identification license number according to claim 7, is characterized in that described character feature comparison match device comprises: apart from calculation element, for the character feature of extraction and character repertoire character feature are carried out to distance calculating;
Result coalignment is matching result for the character of selected characteristic vector distance minimum.
10. the device based on linear array CCD image identification license number according to claim 7, is characterized in that the device of described image recognition license number also comprises character repertoire apparatus for establishing, and described character repertoire apparatus for establishing comprises:
Character segmentation device, for being divided into single character by the image pattern that includes license number;
Gaussian filtering device, for carrying out gaussian filtering by single character picture;
Binaryzation device, for carrying out binary conversion treatment by the image that carried out gaussian filtering;
Normalized device, carries out interpolation conversion for the image to after above-mentioned processing, makes the wide height of image consistent with the wide high standard of template image
Feature-vector extraction means, for passing through the proper vector of Corner Detection operator extraction character;
Character feature storehouse, for storing a plurality of character feature vectors.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310613538.5A CN103699876B (en) | 2013-11-26 | 2013-11-26 | Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310613538.5A CN103699876B (en) | 2013-11-26 | 2013-11-26 | Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103699876A true CN103699876A (en) | 2014-04-02 |
CN103699876B CN103699876B (en) | 2017-05-17 |
Family
ID=50361399
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310613538.5A Active CN103699876B (en) | 2013-11-26 | 2013-11-26 | Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103699876B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107203768A (en) * | 2017-06-12 | 2017-09-26 | 歌尔股份有限公司 | LED display digital automatic identification method and system |
CN107967479A (en) * | 2016-10-19 | 2018-04-27 | 深圳怡化电脑股份有限公司 | A kind of band is stained the character identifying method and system of bill |
CN109492641A (en) * | 2018-09-18 | 2019-03-19 | 上海延华智能科技(集团)股份有限公司 | Energy bills input method and system, storage medium, server based on image recognition |
CN110095296A (en) * | 2019-03-22 | 2019-08-06 | 南宁中车轨道交通装备有限公司 | A kind of control system and method for testing erosion control for the dynamic debugging of city rail vehicle |
CN111782552A (en) * | 2020-08-07 | 2020-10-16 | 广州极点三维信息科技有限公司 | Automatic testing method and device based on region division |
CN113327426A (en) * | 2021-05-26 | 2021-08-31 | 国能朔黄铁路发展有限责任公司 | Vehicle type code identification method and device and vehicle number identification method and device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050179776A1 (en) * | 2003-03-17 | 2005-08-18 | Fujitsu Limited | Vehicle identification method and device |
CN101872416A (en) * | 2010-05-06 | 2010-10-27 | 复旦大学 | Vehicle license plate recognition method and system of road image |
CN102043959A (en) * | 2010-12-28 | 2011-05-04 | 青岛海信网络科技股份有限公司 | License plate character segmentation method |
CN102096821A (en) * | 2010-04-15 | 2011-06-15 | 西安理工大学 | Number plate identification method under strong interference environment on basis of complex network theory |
CN102693423A (en) * | 2012-05-15 | 2012-09-26 | 公安部第三研究所 | Method for precise positioning of license plate in strong light conditions |
CN102722704A (en) * | 2012-06-12 | 2012-10-10 | 厦门宸天电子科技有限公司 | Method and system for recognizing vehicle license plate by integrating video dynamic tracking |
-
2013
- 2013-11-26 CN CN201310613538.5A patent/CN103699876B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050179776A1 (en) * | 2003-03-17 | 2005-08-18 | Fujitsu Limited | Vehicle identification method and device |
CN102096821A (en) * | 2010-04-15 | 2011-06-15 | 西安理工大学 | Number plate identification method under strong interference environment on basis of complex network theory |
CN101872416A (en) * | 2010-05-06 | 2010-10-27 | 复旦大学 | Vehicle license plate recognition method and system of road image |
CN102043959A (en) * | 2010-12-28 | 2011-05-04 | 青岛海信网络科技股份有限公司 | License plate character segmentation method |
CN102693423A (en) * | 2012-05-15 | 2012-09-26 | 公安部第三研究所 | Method for precise positioning of license plate in strong light conditions |
CN102722704A (en) * | 2012-06-12 | 2012-10-10 | 厦门宸天电子科技有限公司 | Method and system for recognizing vehicle license plate by integrating video dynamic tracking |
Non-Patent Citations (2)
Title |
---|
俞大海,等: ""基于线阵CCD图像纹理特征的铁路货车货物分割算法研究"", 《铁道学报》 * |
罗键: ""复杂背景下的车辆牌照定位算法研究及实现"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107967479A (en) * | 2016-10-19 | 2018-04-27 | 深圳怡化电脑股份有限公司 | A kind of band is stained the character identifying method and system of bill |
CN107967479B (en) * | 2016-10-19 | 2021-11-12 | 深圳怡化电脑股份有限公司 | Character recognition method and system with stained bill |
CN107203768A (en) * | 2017-06-12 | 2017-09-26 | 歌尔股份有限公司 | LED display digital automatic identification method and system |
CN109492641A (en) * | 2018-09-18 | 2019-03-19 | 上海延华智能科技(集团)股份有限公司 | Energy bills input method and system, storage medium, server based on image recognition |
CN110095296A (en) * | 2019-03-22 | 2019-08-06 | 南宁中车轨道交通装备有限公司 | A kind of control system and method for testing erosion control for the dynamic debugging of city rail vehicle |
CN111782552A (en) * | 2020-08-07 | 2020-10-16 | 广州极点三维信息科技有限公司 | Automatic testing method and device based on region division |
CN113327426A (en) * | 2021-05-26 | 2021-08-31 | 国能朔黄铁路发展有限责任公司 | Vehicle type code identification method and device and vehicle number identification method and device |
Also Published As
Publication number | Publication date |
---|---|
CN103699876B (en) | 2017-05-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110909732B (en) | Automatic extraction method of data in graph | |
CN103955694B (en) | Image recognition meter reading system and method | |
JP6904614B2 (en) | Object detection device, prediction model creation device, object detection method and program | |
CN103699876A (en) | Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images | |
CN102704215B (en) | Automatic cutting method of embroidery cloth based on combination of DST file parsing and machine vision | |
CN109426814B (en) | Method, system and equipment for positioning and identifying specific plate of invoice picture | |
CN111382704A (en) | Vehicle line-pressing violation judgment method and device based on deep learning and storage medium | |
CN105913093A (en) | Template matching method for character recognizing and processing | |
CN111191611B (en) | Traffic sign label identification method based on deep learning | |
CN104166841A (en) | Rapid detection identification method for specified pedestrian or vehicle in video monitoring network | |
CN109376740A (en) | A kind of water gauge reading detection method based on video | |
CN104809481A (en) | Natural scene text detection method based on adaptive color clustering | |
CN105303153A (en) | Vehicle license plate identification method and apparatus | |
CN103207987A (en) | Indicating value identification method of dial instrument | |
Soomro et al. | Vehicle number recognition system for automatic toll tax collection | |
CN105976392B (en) | Vehicle tyre detection method and device based on maximum output probability | |
CN106127205A (en) | A kind of recognition methods of the digital instrument image being applicable to indoor track machine people | |
CN104766078A (en) | Slant angle detecting method and slant angle detecting device of target image | |
CN110598566A (en) | Image processing method, device, terminal and computer readable storage medium | |
CN108257125B (en) | Depth image quality non-reference evaluation method based on natural scene statistics | |
CN111539330B (en) | Transformer substation digital display instrument identification method based on double-SVM multi-classifier | |
CN104331693A (en) | Symmetry detecting method and system of printing matter | |
CN105069451A (en) | License plate identifying and positioning method based on binocular camera | |
CN108009574A (en) | A kind of rail clip detection method | |
CN104966047A (en) | Method and device for identifying vehicle license |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |