CN103268493A - Vehicle license plate image location method in RGB format - Google Patents
Vehicle license plate image location method in RGB format Download PDFInfo
- Publication number
- CN103268493A CN103268493A CN2013102054904A CN201310205490A CN103268493A CN 103268493 A CN103268493 A CN 103268493A CN 2013102054904 A CN2013102054904 A CN 2013102054904A CN 201310205490 A CN201310205490 A CN 201310205490A CN 103268493 A CN103268493 A CN 103268493A
- Authority
- CN
- China
- Prior art keywords
- license plate
- image
- component
- rgb
- color
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000005286 illumination Methods 0.000 claims abstract description 12
- 238000001914 filtration Methods 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 3
- 239000003086 colorant Substances 0.000 abstract description 2
- 238000009432 framing Methods 0.000 abstract 3
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
- Character Input (AREA)
Abstract
The invention relates to the technical field of vehicle license plate recognition, and discloses a framing method for a license plate in an RGB format. The framing method includes the following steps of converting a license plate image from RGB space to HSV space, separating an HSV component of the image from the image, conducting homomorphic filtering on an luminance component V, converting the image HSV component from the HSV space to an RGB component in the RGB space, determining a luminance threshold value of the RGB component, scanning the license plate image in a line direction and a row direction, recording pixel points of colors dropping into a luminance threshold value range, determining lines and rows where a license plate range is located according to pixel points in each line and pixel points in each row, and displaying pixel points of the lines and rows where the license plate range is located. According to the framing method for the license plate in the RGB format, preprocessing is conducted on a vehicle image with a poor light condition, excessively bright or excessively dark or shaded influence caused by uneven illumination, polarized light, side light, highlight and the like on the vehicle image can be eliminated, and the accuracy rate of license plate location is improved.
Description
Technical field
The present invention relates to the license plate image position method in automotive license plate recognition technology field, particularly a kind of rgb format.
Background technology
Rapid increase along with socioeconomic fast development, automobile quantity has proposed new challenge to traffic control, safety management, toll administration.License plate is unique " identity " sign of vehicle, therefore, the research of car plate identification is become the hot issue of intelligent transportation system.At present, mainly both at home and abroad adopt following a few class algorithms to carry out the car plate location: based on the method for rim detection, based on the method for color characteristic, based on the method for mathematical morphology, based on neural network method, based on the method for genetic algorithm etc.Because complicacy and the not first-class influence of illumination condition of vehicle background of living in increase the labile factor of car plate location, thereby influence the performance of Vehicle License Plate Recognition System, and these prior art calculation of complex, effect is general.
Summary of the invention
To the objective of the invention is in order solving the problems of the technologies described above, a kind of license plate image position method of rgb format to be provided, in the hope of by the illumination compensation technology license plate being identified effectively.
The technical scheme that the present invention takes is:
A kind of license plate image position method of rgb format is characterized in that, comprises the steps:
The first step: the license plate image is transformed into the HSV space from rgb space;
Second step: luminance component V, saturation degree component S and the tone component H of image are separated from image respectively;
The 3rd step: described luminance component V is carried out homomorphic filtering;
The 4th step: the RGB component that the saturation degree component S of image and tone component H and the luminance component V that handles in the 3rd step is converted to rgb space from the HSV space;
The 5th step: the luminance threshold of determining its RGB component according to the color of license plate;
The 6th step: press the described license plate image of ranks scanning direction, the record color falls into the pixel in the described luminance threshold scope;
The 7th step: the ranks of determining car plate scope place according to the quantity of the each row and column pixel of record in the 6th step;
The 8th step: the interior pixel of ranks that shows described car plate scope place.
Further, the homomorphic filtering process in described the 3rd step is the variation range by the incident component of compressed image, and the contrast of the reflecting component of increase image realizes.
Further, in described the 5th step, the definite of described luminance threshold finishes by following steps:
First small step: the color of determining license plate;
Second small step: choose a plurality of license plates as sample, the color of described license plate is the color that described first small step is determined;
The 3rd small step: selected license plate is carried out even illumination and take pictures obtaining the license plate image;
The 4th small step: the RGB component of adjusting the color of determining in described first small step according to the color of sample license plate image obtains luminance threshold.
Further, the quantity of described sample is 30 to 100, and the color of the car body of described sample is 3 to 10 kinds.
Further, in described the 6th step, the method that scans described license plate image is image array to be converted to the double precision matrix carry out comparing with described luminance threshold again.
Further, in described the 6th step and the 7th step, be divided into respectively by row with by row two steps operation and finish.
The invention has the beneficial effects as follows:
By illumination compensation, the imperfect vehicle image of illumination condition is done pre-service, can eliminate because uneven illumination is even, polarisation, sidelight, Gao Guang etc. cause that vehicle image bright excessively, dark with excessivelying, the influence of shade, the accuracy rate raising that car plate is located.
Description of drawings
Accompanying drawing 1 is schematic flow sheet of the present invention;
Accompanying drawing 2 is RGB License Plate Image illumination compensation schematic flow sheet;
Accompanying drawing 3 is that schematic flow sheet is determined in the ranks zone.
Embodiment
Elaborate below in conjunction with the embodiment of accompanying drawing to the license plate image position method of rgb format of the present invention.
Referring to accompanying drawing 1, License Plate Image localization method of the present invention comprises the steps.
The first step: the license plate image is transformed into HSV space (S01 step Fig. 1) from rgb space.
This step can be referring to Yuan Fenjie, " RGB and HSV color space transformation algorithm based on FPGA are realized " (electron device, 2010 that Zhou Xiao, Ding Jun etc. write, 33 (4): 493-497.), it is transformed into HSV space with image from rgb space by the following map using formula.
The formula of the tone H in HSV space is:
0°,max=min
max=R,G<B
The formula of saturation degree S is:
0,max=0
The formula of brightness V is:
V=max
In the formula, R, G, B are normalized value, and max is maximal value wherein, and min is minimum value wherein.The span of H is [0,360 °], and the span of S, V is [0,1].
Second step: luminance component V, saturation degree component S and the tone component H of image are separated (S02 step among Fig. 1) respectively from image.
Extract light intensity level V, saturation degree component S and tone component H from the HSV space of license plate image, wherein luminance component will be used in subsequent step, and saturation degree component S and tone component H are stored the wait subsequent calls.
The 3rd step: described luminance component V is carried out homomorphic filtering (S03 step among Fig. 1).
The homomorphic filtering process of this step is the variation range by the incident component of compressed image, and the contrast of the reflecting component of increase image realizes.The homomorphic filtering process is finished by following formula:
The 4th step: the saturation degree component S of image and the luminance component V of tone component H and processing in the 3rd step are transformed into rgb space (S04 step Fig. 1) from the HSV space.
Referring to accompanying drawing 2, accompanying drawing 2 is the flow processs in above-mentioned one to four step, obtains the RGB license plate figure behind the illumination compensation at last.
The 5th step: the luminance threshold (S05 step among Fig. 1) of determining its RGB component according to the color of license plate.
The definite of luminance threshold finishes by following steps:
First small step: the color of determining license plate.
Because the color of automotive license plate is more fixing, is generally blueness, green, yellow, black etc.
Second small step: choose 30 to 100 license plates as sample, a certain same color of determining above the color of these license plates.
The 3rd small step: selected license plate is carried out even illumination and take pictures obtaining the license plate image.
The 4th small step: the RGB component of adjusting the color of determining in described first small step according to the color of sample license plate image obtains luminance threshold.
Be example with blue licence plate sheet, choose the vehicle image of the uniform different car body colors of 50 width of cloth illumination as training sample, constantly adjust the brightness statistics threshold value of blue RGB component, comprehensive determine suitable threshold value (R ∈ [28,65], G ∈ [60,150], B ∈ [140,255]).
The 6th step: press the described license plate image of ranks scanning direction, the record color falls into the pixel (Fig. 1 S06 step) in the described luminance threshold scope.
The method of scanning license plate image is image array to be converted to the double precision matrix carry out comparing with described luminance threshold again.Extract the capable j of i row as follows, namely pixel (i, each components R of color characteristic j) (i, j), G (i, j), B (i, j), and compare by pointwise and threshold value.
R(i,j)=I
1(i,j,1)
G(i,j)=I
1(i,j,2)
B(i,j)=I
1(i,j,3)
The 7th step: the ranks (S07 step among Fig. 1) of determining car plate scope place according to the quantity of the each row and column pixel of record in the 6th step.
In above-mentioned six, seven liang of steps, can be divided into respectively by row with by row two steps operation and finishing.
The 8th step: the interior pixel (S08 step among Fig. 1) of ranks that shows car plate scope place.
Referring to accompanying drawing 3, accompanying drawing 3 the 6th to eight is an embodiment of rapid flow process step by step, after the image input, extracts row, column and Pixel Information, the pixel of lining by line scan, in the ordinate Y-direction, add up the pixel that each row meets luminance threshold in the 5th step, be example with the blueness, add up the pixel number that each row meets blue RGB brightness range, add up the row that the blue pixel point value meets the car plate scope then, like this, the license plate area of Y-direction is determined.After Y-direction is determined, in the same way directions X is carried out the zone and determine, determine at last to demonstrate car plate by license plate area.
The above only is preferred implementation of the present invention; should be pointed out that for those skilled in the art, under the prerequisite that does not break away from the principle of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (6)
1. the license plate image position method of a rgb format is characterized in that: comprise the steps:
The first step: the license plate image is transformed into the HSV space from rgb space;
Second step: luminance component V, saturation degree component S and the tone component H of image are separated from image respectively;
The 3rd step: described luminance component V is carried out homomorphic filtering;
The 4th step: the RGB component that the saturation degree component S of image and tone component H and the luminance component V that handles in the 3rd step is converted to rgb space from the HSV space;
The 5th step: the luminance threshold of determining its RGB component according to the color of license plate;
The 6th step: press the described license plate image of ranks scanning direction, the record color falls into the pixel in the described luminance threshold scope;
The 7th step: the ranks of determining car plate scope place according to the quantity of the each row and column pixel of record in the 6th step;
The 8th step: the interior pixel of ranks that shows described car plate scope place.
2. the license plate image position method of rgb format according to claim 1 is characterized in that: the homomorphic filtering process in described the 3rd step is the variation range by the incident component of compressed image, increases that the contrast of the reflecting component of image realizes.
3. the license plate image position method of rgb format according to claim 1 and 2 is characterized in that: in described the 5th step, the determining of described luminance threshold finished by following steps:
First small step: the color of determining license plate;
Second small step: choose a plurality of license plates as sample, the color of described license plate is the color that described first small step is determined;
The 3rd small step: selected license plate is carried out even illumination and take pictures obtaining the license plate image;
The 4th small step: the RGB component of adjusting the color of determining in described first small step according to the color of sample license plate image obtains luminance threshold.
4. the license plate image position method of rgb format according to claim 3, it is characterized in that: the quantity of described sample is 30 to 100, the color of the car body of described sample is 3 to 10 kinds.
5. the license plate image position method of rgb format according to claim 1, it is characterized in that: in described the 6th step, the method that scans described license plate image is image array to be converted to the double precision matrix carry out comparing with described luminance threshold again.
6. the license plate image position method of rgb format according to claim 1 is characterized in that: in described the 6th step and the 7th step, be divided into respectively by row with by row two steps operation and finish.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013102054904A CN103268493A (en) | 2013-05-29 | 2013-05-29 | Vehicle license plate image location method in RGB format |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013102054904A CN103268493A (en) | 2013-05-29 | 2013-05-29 | Vehicle license plate image location method in RGB format |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103268493A true CN103268493A (en) | 2013-08-28 |
Family
ID=49012120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013102054904A Pending CN103268493A (en) | 2013-05-29 | 2013-05-29 | Vehicle license plate image location method in RGB format |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103268493A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484661A (en) * | 2015-01-03 | 2015-04-01 | 武传胜 | Car registration number positioning system and method |
| CN105719365A (en) * | 2016-02-14 | 2016-06-29 | 海安欣凯富机械科技有限公司 | Adjustment method for automobile driving record video red, green and blue three-primary-color mixed degree |
| CN105761327A (en) * | 2016-02-14 | 2016-07-13 | 海安欣凯富机械科技有限公司 | Driving recorder for automobile |
| CN105760873A (en) * | 2016-02-14 | 2016-07-13 | 海安欣凯富机械科技有限公司 | Automobile driving recorder |
| CN106067020A (en) * | 2016-06-02 | 2016-11-02 | 广东工业大学 | The system and method for quick obtaining effective image under real-time scene |
| CN106780428A (en) * | 2016-11-11 | 2017-05-31 | 北京理工大学珠海学院 | A kind of number of chips detection method and system based on colour recognition |
| CN107292898A (en) * | 2017-05-04 | 2017-10-24 | 浙江工业大学 | A kind of car plate shadow Detection and minimizing technology based on HSV |
| CN107578387A (en) * | 2017-10-16 | 2018-01-12 | 湖南友哲科技有限公司 | A kind of homomorphic filtering Enhancement Method based on hsv color space |
| CN107798323A (en) * | 2016-08-29 | 2018-03-13 | 北京君正集成电路股份有限公司 | A kind of license plate image localization method and equipment |
| CN109949248A (en) * | 2019-03-26 | 2019-06-28 | 北京字节跳动网络技术有限公司 | Modify method, apparatus, equipment and the medium of the color of vehicle in the picture |
| CN110793564A (en) * | 2018-08-02 | 2020-02-14 | 昆山博威泰克电子科技有限公司 | Visual inspection apparatus and visual inspection method |
| CN114219723A (en) * | 2021-11-19 | 2022-03-22 | 浙江大华技术股份有限公司 | Image enhancement method, image enhancement device and computer readable storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1085455A2 (en) * | 1999-09-15 | 2001-03-21 | Siemens Corporate Research, Inc. | License plate recognition with an intelligent camera |
-
2013
- 2013-05-29 CN CN2013102054904A patent/CN103268493A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1085455A2 (en) * | 1999-09-15 | 2001-03-21 | Siemens Corporate Research, Inc. | License plate recognition with an intelligent camera |
Non-Patent Citations (2)
| Title |
|---|
| 沈全鹏: ""基于数字图像处理的车牌定位研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 焦竹青、徐保国: ""HSV变换和同态滤波的彩色图像光照补偿"", 《计算机工程与应用》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484661A (en) * | 2015-01-03 | 2015-04-01 | 武传胜 | Car registration number positioning system and method |
| CN105719365A (en) * | 2016-02-14 | 2016-06-29 | 海安欣凯富机械科技有限公司 | Adjustment method for automobile driving record video red, green and blue three-primary-color mixed degree |
| CN105761327A (en) * | 2016-02-14 | 2016-07-13 | 海安欣凯富机械科技有限公司 | Driving recorder for automobile |
| CN105760873A (en) * | 2016-02-14 | 2016-07-13 | 海安欣凯富机械科技有限公司 | Automobile driving recorder |
| CN106067020A (en) * | 2016-06-02 | 2016-11-02 | 广东工业大学 | The system and method for quick obtaining effective image under real-time scene |
| CN107798323B (en) * | 2016-08-29 | 2020-12-29 | 北京君正集成电路股份有限公司 | License plate image positioning method and device |
| CN107798323A (en) * | 2016-08-29 | 2018-03-13 | 北京君正集成电路股份有限公司 | A kind of license plate image localization method and equipment |
| CN106780428B (en) * | 2016-11-11 | 2020-01-14 | 北京理工大学珠海学院 | Chip quantity detection method and system based on color recognition |
| CN106780428A (en) * | 2016-11-11 | 2017-05-31 | 北京理工大学珠海学院 | A kind of number of chips detection method and system based on colour recognition |
| CN107292898A (en) * | 2017-05-04 | 2017-10-24 | 浙江工业大学 | A kind of car plate shadow Detection and minimizing technology based on HSV |
| CN107578387A (en) * | 2017-10-16 | 2018-01-12 | 湖南友哲科技有限公司 | A kind of homomorphic filtering Enhancement Method based on hsv color space |
| CN110793564A (en) * | 2018-08-02 | 2020-02-14 | 昆山博威泰克电子科技有限公司 | Visual inspection apparatus and visual inspection method |
| CN109949248A (en) * | 2019-03-26 | 2019-06-28 | 北京字节跳动网络技术有限公司 | Modify method, apparatus, equipment and the medium of the color of vehicle in the picture |
| CN114219723A (en) * | 2021-11-19 | 2022-03-22 | 浙江大华技术股份有限公司 | Image enhancement method, image enhancement device and computer readable storage medium |
| CN114219723B (en) * | 2021-11-19 | 2025-07-08 | 浙江大华技术股份有限公司 | Image enhancement method, image enhancement device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103268493A (en) | Vehicle license plate image location method in RGB format | |
| Hu et al. | IoT-driven automated object detection algorithm for urban surveillance systems in smart cities | |
| CN101193317B (en) | Method and device for automatic white balance processing of the image | |
| CN102375982B (en) | Multi-character characteristic fused license plate positioning method | |
| US8237589B2 (en) | Adjusting system and method for traffic light | |
| Omachi et al. | Detection of traffic light using structural information | |
| CN108154160A (en) | Color recognizing for vehicle id method and system | |
| DE102018110430A1 (en) | METHOD AND DEVICE FOR DETECTING AND CLASSIFYING OBJECTS IN CONNECTION WITH A VEHICLE | |
| CN102722733A (en) | Identification method and device of license plate types | |
| DE102015108498A1 (en) | PROVIDING A VEHICLE MANUAL INFORMATION USING AN OBJECT DETECTION TO A MOBILE DEVICE | |
| US20160057367A1 (en) | Method for extracting rgb and nir using rgbw sensor | |
| CN103886297B (en) | Dynamic optical detection method for true and false fingerprints | |
| CN113873229B (en) | Image dead pixel detection method, system and device | |
| CN103530608A (en) | Vehicle type judgment method and vehicle type judgment device | |
| CN113537203B (en) | Test paper identification method, device, storage medium and equipment | |
| CN105488797A (en) | License plate location method for HSV space | |
| CN103544716B (en) | A kind of pixel to image carries out method and the device of color classification | |
| CN108090459A (en) | A kind of road traffic sign detection recognition methods suitable for vehicle-mounted vision system | |
| WO2014034313A1 (en) | On-vehicle image capture device | |
| CN102073854A (en) | Color license plate positioning method | |
| CN103530640A (en) | Unlicensed vehicle detection method based on AdaBoost and SVM (support vector machine) | |
| DE102022124245A1 (en) | Generation of artificial color images from narrowband spectral data onboard a camera-equipped vehicle | |
| Chowdhury et al. | An adaptive technique for computer vision based vehicles license plate detection system | |
| CN111144405A (en) | New energy vehicle identification method and device | |
| CN104156703A (en) | License plate location method and system based on color texture |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130828 |