CN109670498A - A kind of license plate locating method - Google Patents
A kind of license plate locating method Download PDFInfo
- Publication number
- CN109670498A CN109670498A CN201811334969.7A CN201811334969A CN109670498A CN 109670498 A CN109670498 A CN 109670498A CN 201811334969 A CN201811334969 A CN 201811334969A CN 109670498 A CN109670498 A CN 109670498A
- Authority
- CN
- China
- Prior art keywords
- license plate
- image
- carries out
- locating method
- picture
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Abstract
The present invention proposes a kind of license plate locating method, comprising the following steps: step S1 obtains vehicle pictures；Step S2 carries out License Plate according to the colouring information of vehicle in the vehicle pictures, and exports the first image block；Step S3 successively judges whether the first image block of the output is license plate；Step S4, judges whether license plate quantity is greater than preset license plate number, if it is not, S5 is thened follow the steps, if so, thening follow the steps S7；Step S5 carries out License Plate according to the License Plate method at edge, and exports the second image block；Step S6 successively judges whether the second image block of the output is license plate；Step S7 carries out accurate License Plate according to the positioning mode of target detection.The present invention is incorporated into improving License Plate the efficiency and accuracy of License Plate using the color characteristics, style characteristic, the method based on target detection of license plate.
Description
Technical field
The present invention relates to field of image processings, are specifically related to a kind of color, the vehicle that edge and target detection combine
Board detection method.
Background technique
With the fast development of Modern Traffic, the modern management of vehicle is increasingly tended to automate, vehicle is examined automatically
Survey, the demand of identifying system increasingly increases, for example, high speed crossing charging aperture, cell automatic parking lot management etc..It is existing in order to adapt to
For the development of traffic, intelligentized traffic control system is come into being, and one of important link is namely based on the identification of license plate
Method.The identification technology of license plate is a very important research topic in modern intelligent transportation field, for complicated license plate
How correctly image quickly, is effectively performed License Plate, is one of most important task of current Car license recognition.
The position of license plate is detected in a picture containing vehicle and is split the vehicle based on gray level image
Board localization method.License plate locating method based on gray level image mainly uses edge detection operator to carry out edge inspection to gray level image
It surveys, to obtain candidate license plate.Such as a kind of license plate locating method based on complicated panorama sketch of Chinese patent CN102999753,
Have a wide range of application, it is anti-interference small, still, since domestic license plate mainly has yellow bottom black word and blue two kinds of wrongly written or mispronounced character of bottom, thus may be used
It is positioned with directly detecting the color of license plate, but some blue vehicles are blue license plates, yellow vehicle is yellow license plate
Deng, such color detection can all detected whole vehicle, detection effect inaccuracy.
Summary of the invention
Based on the above issues, the purpose of the present invention aims to solve at least one of described technological deficiency.It is proposed that a kind of license plate is fixed
Position method, makes full use of the color characteristics of license plate and style characteristic to be incorporated into improving the method for License Plate
The accuracy of detection.To achieve the above object, the present invention adopts the following technical scheme:
A kind of license plate locating method, comprising the following steps:
Step S1 obtains vehicle pictures；
Step S2 carries out License Plate according to the colouring information of vehicle in the vehicle pictures, and exports the first image block；
Step S3 successively judges whether the first image block of the output is license plate；
Step S4, judges whether license plate quantity is greater than preset license plate number, if it is not, S5 is thened follow the steps, if so, executing
Step S7；
Step S5 carries out License Plate according to the License Plate method at edge, and exports the second image block；
Step S6 successively judges whether the second image block of the output is license plate；
Step S7 carries out accurate License Plate according to the positioning mode of target detection.
Preferably, the step S2 includes:
Step S21, the vehicle pictures that will acquire are filtered, and the color space of filtered picture is converted by RGB
HSV；
Step S22, the picture that will transition to HSV carry out histogram equalization processing；
Step S23, to treated, picture carries out binary conversion treatment, generates corresponding bianry image；
Step S24 carries out morphology closed operation to the bianry image, then extracts all profiles of the image；
Step S25 takes minimum circumscribed rectangle to each profile, then according to the tilt angle of license plate and the preliminary mistake of length-width ratio
Some underproof candidate license plates are filtered, finally the size of license plate is standardized, obtain license plate.
Preferably, it is described to the bianry image carry out morphology closed operation, be the step of region similar in connection by
The panorama sketch is divided into multiple regions, wherein different closed operation parameters is respectively adopted to carry out morphology respectively in different regions
Closed operation.
Preferably, the step S5 includes:
Step S51 carries out the processed filter interference noise of Gaussian mode gelatinization to the license plate picture of acquisition；
Step S52 carries out gray proces to filtered picture；
Step S53 extracts horizontal and vertical edge by image of the Sobel operator to gray proces respectively, obtains license plate
Edge image；
Step S54 successively carries out binaryzation, closed operation processing to the license plate edge image of acquisition, then extracts all wheels
It is wide；
Step S55 takes minimum circumscribed rectangle to each profile, while according to the tilt angle of license plate and the preliminary mistake of length-width ratio
Some underproof candidate license plates are filtered, then the size of remaining candidate license plate is standardized, obtain license plate.
Preferably, step S25 and step S55 respectively include:
To the image after standardization carry out affine transformation with the rectangle guaranteed be it is horizontal, reduce subsequent license plate judgement
With the difficulty of character recognition.
Preferably, the step S7 includes:
Step S71 carries out gray processing to the license plate picture of acquisition, obtains gray level image；
Step S72 carries out multilevel binary to the gray level image, and analyzes connection region；
Step S73 takes minimum circumscribed rectangle to connection region, draws the angle point of rectangle；
Step S74 is fitted by RANSAC algorithm；
Step S75 cuts the region after fitting, obtains license plate.
Preferably, the step S74 includes:
Some angle points are randomly selected, a model is established, according to the remaining point of the model measurement, if the data point of test exists
In the range of error allows, then the data point is judged to available point, is otherwise judged to noise；
If illustrating that these data point sets this time chosen reach when the number of available point has reached the threshold value of some setting
Acceptable degree has been arrived, has otherwise continued all steps after randomly selecting point set of front, constantly repeats this process, until
Find selection these data point sets reached acceptable degree until, the model obtained at this time can be considered to data
The optimal models building of point；
The angle point generated in step S73 is fitted using RANSAC algorithm, finds coboundary and lower boundary.
Scheme in compared with the existing technology, advantages of the present invention:
The license plate locating method that the embodiment of the present invention proposes is examined using the color characteristics of license plate, style characteristic, based on target
The method of survey is incorporated into improving License Plate the efficiency and accuracy of License Plate.
Detailed description of the invention
The invention will be further described with reference to the accompanying drawings and embodiments:
Fig. 1 is a kind of flow diagram of license plate locating method of the present invention.
Fig. 2 is the idiographic flow schematic diagram of step S2 in Fig. 1 of the present invention.
Fig. 3 is the idiographic flow schematic diagram of step S5 in Fig. 1 of the present invention.
Fig. 4 is the idiographic flow schematic diagram of step S7 in Fig. 1 of the present invention
Specific embodiment
Above scheme is described further below in conjunction with specific embodiment.It should be understood that these embodiments are for illustrating
The present invention and be not limited to limit the scope of the invention.Implementation condition used in the examples can be done such as the condition of specific producer into
One successive step, the implementation condition being not specified are usually the condition in routine experiment.
This application discloses a kind of license plate locating methods, please refer to Fig. 1 and show a kind of license plate locating method of the present invention
Flow diagram, comprising the following steps:
Step S1 obtains vehicle pictures, and in a wherein embodiment of the invention, the figure of vehicle is acquired by camera
Piece.
Step S2 carries out License Plate according to the colouring information of vehicle in the vehicle pictures, and exports the first image block,
The present invention carries out coarse localization to license plate using colouring information.
In a wherein embodiment of the invention, please refers to Fig. 2 and show step S2 of the present invention and include the steps that:
Step S21, the vehicle pictures that will acquire are filtered, and the color space of filtered picture is converted by RGB
HSV。
Picture is filtered, it is subsequent to improve the purpose is to inhibit the noise in image as far as possible before handling image
The validity and reliability of image procossing.Specifically, the embodiment of the present invention uses median filtering, the characteristic of median filtering is
Isolated noise can be effectively removed, and can be very good to keep the marginal information of image.
Picture is converted into HSV by RGB three primary colours picture, wherein H represents coloration, and S represents saturation degree, is worth bigger, representative
It is more saturated, V represents lightness, and value is bigger, and color is brighter.Rgb format picture is converted into HSV format picture by the present invention, can be with
Reduce influence of the illumination to license plate.
Step S22, the picture that will transition to HSV carry out histogram equalization processing.By histogram equalization processing, subtract
Few illumination shade caused by picture, light and shade influence.
Step S23, to treated, picture carries out binary conversion treatment, generates corresponding bianry image.
Specifically, by the distribution of setting H component and being S, whether V given threshold determines the pixel in picture
Belong to blue license plate or yellow license plate, and makes its binaryzation.
1) positive binaryzation calculation formula: if x < t then x=0；If x >=t then x=1
Anti- binaryzation calculation formula: if x < t then x=1；If x >=t then x=0
2) on the contrary value that positive binaryzation means pixel is closer to 0, may more be assigned 0, then be 1.Blue license plate word
According with color is white, and for background compared with character color depth, the gray value of background is greater than the gray value of character, so can be to blue board using just
Binarization method, color is 1 (white), color after the lesser character binaryzation of gray value after the biggish background binary of gray value
For 0 (black).
3) anti-binaryzation is meant that the value of pixel closer to 0, may more be assigned 1.Yellow characters on license plate color is black
Color, background is shallow compared with character color, and the gray value of background is less than the gray value of character, so anti-binaryzation side can be used to yellow card
Method, color is 0 (black) after the biggish character binaryzation of gray value, and color is 1 (white after the lesser background binary of gray value
Color).
4) after binaryzation, the background of yellow card and blue board is 1 (white), and character is 0 (black), is facilitated at unified
Reason.
Step S24 carries out morphology closed operation to the bianry image, then extracts all profiles of the image.
In the present invention, closed operation: license plate letter is connected into the rectangle local of a completion, facilitates next contouring
Operation, closed operation can make the form of image change, be corroded again by expanding bianry image first, can make many close figures
Block is connected to unpolarized connected domain.The purpose of contouring is to delineate the periphery of connected domain in the present invention, forms boundary rectangle.
Step S25 takes minimum circumscribed rectangle to each profile, then according to the tilt angle of license plate and the preliminary mistake of length-width ratio
Some underproof candidate license plates are filtered, finally the size of license plate is standardized, obtain license plate.
The present invention is the further region for excluding to be unlikely to be license plate according to the purpose of the tilt angle primary filtration of license plate,
An angle threshold is set, rotation angle gives up the region if being greater than the threshold value if the region.Tilt angle filtering and then
Carry out affine transformation, it is therefore an objective to the rectangle for being less than angle threshold is adjusted to horizontal extent, be convenient for uniform sizes.Uniform sizes:
Before importing in machine learning model, need to carry out license plate size unification, otherwise the picture can not be by machine learning model
Processing.The size of Chinese license plate is generally 440mm*140mm, the ratio of width to height 3.14.One maximum the ratio of width to height Rmax and most is set
Small the ratio of width to height Rmin, judges whether rectangular area within the ratio of width to height can determine whether the region is likely to be license plate.
The present invention carries out morphology closed operation to bianry image, to be by described image point the step of region similar in connection
At multiple regions, wherein different closed operation parameters is respectively adopted to carry out morphology closed operation respectively in different regions.
Step S3 successively judges whether the first image block of the output is license plate.
Step S4, judges whether license plate quantity is greater than preset license plate number, if it is not, this executes step S5, if so, executing
Step S7.
Step S5 carries out License Plate according to the License Plate method at edge, and exports the second image block.
In a wherein embodiment of the invention, please refers to Fig. 3 and show step S5 of the present invention and include the steps that:
Step S51 carries out the processed filter interference noise of Gaussian mode gelatinization to the license plate picture of acquisition.
The purpose of Gaussian mode gelatinization processing of the present invention is to carry out denoising to image, can allow image in post-processing
It is easier to detect marginal point, Gaussian Blur is not used using gaussian sum by comparison, system, which orients " license plate " quantity, is
Different, using Gaussian Blur, License Plate is accurate, is not likely to produce extra positioning result, and Gaussian Blur is not used, then can
Orient a large amount of unrelated rectangle frame.
Step S52 carries out gray proces to filtered picture.Wherein, the purpose of gray processing processing is that edge detection is calculated
Method requires to use the environment of gray processing, and the effect of this step is exactly that color image is processed into gray scale picture.
Step S53 extracts horizontal and vertical edge by image of the Sobel operator to gray proces respectively, obtains license plate
Edge image.
The purpose of Sobel operator of the present invention is the vertical edge detected in gray scale picture, to distinguish license plate.Sobel is calculated
The algorithm of son is the derivative for asking gray level image vertical and horizontal direction, with this to determine whether being vertical edge.Detection is vertical
When edge, vertical and horizontal directional derivative directly is not asked to image, but periphery has been used to be worth weighted sum method, i.e. " volume
Product ".
Step S54 successively carries out binaryzation, closed operation processing to the license plate edge image of acquisition, then extracts all wheels
It is wide.
Each of the gray level image that binaryzation of the present invention generates Sobel operator pixel carries out threshold process, generates
Binary image.Using threshold, (one threshold value T of setting is, it is specified that when the value x of pixel meets following condition then: if x < t
Then x=0；If x >=t then x=1) function does adaptive thresholding to each pixel of image, so that pixel
Value only has { 0,1 } two kinds of values, to do morphological operation to image later.
Closed operation of the present invention is the rectangle local that license plate letter is connected into a completion, and next contouring is facilitated to grasp
Make, closed operation can make the form of image change, be corroded again by expanding bianry image first, can make many close segments
It is connected to unpolarized connected domain.It specifically includes: first establishing rectangle template, the width and high setting of rectangle are odd number；Call form
Handling function is learned, parameter is set as MOP_CLOSE and represents closed operation.
Step S55 takes minimum circumscribed rectangle to each profile, while according to the tilt angle of license plate and the preliminary mistake of length-width ratio
Some underproof candidate license plates are filtered, then the size of remaining candidate license plate is standardized, obtain license plate.
In a wherein embodiment of the invention, an angle threshold is set, if region rotation angle is greater than the threshold
Value then gives up the region.Tilt angle filtering and then progress affine transformation, it is therefore an objective to which the rectangle that will be less than angle threshold adjusts
To horizontal extent, it is convenient for uniform sizes.In carrying out size judgement, a deviation ratio error is set up, according to this deviation ratio meter
Minimum and maximum the ratio of width to height rmax, rmin.Judge whether the r of rectangle meets between rmax, rmin.
Set a Maximum Area max and area minimum value min.Judge whether the area area of rectangle meets in max
Between min.
The boundary rectangle of profile all in image is traversed, while meet above-mentioned two condition is license plate.
The general size of Chinese license plate is 440*140 (unit: mm), area 440*140, the ratio of width to height 3.14.One maximum is set
The ratio of width to height Rmax and minimum the ratio of width to height Rmin, judges whether rectangular area within the ratio of width to height can determine whether the region has
It may be license plate.
It may be rectangle of the image block progress affine transformation of license plate to guarantee that above-mentioned steps, which further include by what is obtained,
Be it is horizontal, reduce the difficulty of subsequent license plate judgement and character recognition.
Step S6 successively judges whether the second image block of the output is license plate.
Step S7 carries out accurate License Plate according to the positioning mode of target detection.
In a wherein embodiment of the invention, please refers to Fig. 4 and show step S7 of the present invention and include the steps that:
Step S71 carries out gray processing to the license plate picture of acquisition, obtains gray level image.
Step S72 carries out multilevel binary to the gray level image, and analyzes connection region.
Step S73 takes minimum circumscribed rectangle to connection region, draws the angle point of rectangle.
Step S74 is fitted by RANSAC algorithm.Specifically, we are only due to when doing connected domain analysis
Using only the figure of Aspect Ratio is met fastly as Rule of judgment, so certain noise can be brought, RANSAC algorithm can be helped
We reject these noise spots.
In a wherein embodiment of the invention, the step of RANSAC (random sampling is consistent) algorithm, includes:
The first random some angle points of selection go to establish a model, then go to test with this model remaining with these points
The data point is judged to available point, is otherwise judged to noise by point if the data point of test is to the extent permitted by the error.
If the number of available point has reached the threshold value of some setting, illustrate that these data point sets this time chosen reach
Otherwise acceptable degree continues all steps after randomly selecting point set of front, this process is constantly repeated, until looking for
Until these data point sets of selection have reached acceptable degree, the model obtained at this time can be considered to data point
Optimal models building.
It is fitted using angle point of the RANSAC algorithm to generation, finds coboundary and lower boundary
Step S75 cuts the region after fitting, obtains license plate.
The present invention is incorporated into using the color characteristics, style characteristic, the method based on target detection of license plate to vehicle
Board positioning, improves the efficiency and accuracy of License Plate.
The above embodiments merely illustrate the technical concept and features of the present invention, and its object is to allow person skilled in the art
It is to can understand the content of the present invention and implement it accordingly, it is not intended to limit the scope of the present invention.All such as present invention essences
The equivalent transformation or modification that refreshing essence is done, should be covered by the protection scope of the present invention.
Claims (8)
1. a kind of license plate locating method, which comprises the following steps:
Step S1 obtains vehicle pictures；
Step S2 carries out License Plate according to the colouring information of vehicle in the vehicle pictures, and exports the first image block；
Step S3 successively judges whether the first image block of the output is license plate；
Step S4, judges whether license plate quantity is greater than preset license plate number, if it is not, S5 is thened follow the steps, if so, thening follow the steps
S7；
Step S5 carries out License Plate according to the License Plate method at edge, and exports the second image block；
Step S6 successively judges whether the second image block of the output is license plate；
Step S7 carries out accurate License Plate according to the positioning mode of target detection.
2. license plate locating method according to claim 1, which is characterized in that the step S2 includes:
Step S21, the vehicle pictures that will acquire are filtered, and the color space of filtered picture is converted into HSV by RGB；
Step S22, the picture that will transition to HSV carry out histogram equalization processing；
Step S23, to treated, picture carries out binary conversion treatment, generates corresponding bianry image；
Step S24 carries out morphology closed operation to the bianry image, then extracts all profiles of the image；
Step S25 takes minimum circumscribed rectangle to each profile, then according to the tilt angle of license plate and length-width ratio primary filtration one
A little underproof candidate license plates, are finally standardized the size of license plate, obtain license plate.
3. license plate locating method according to claim 2, which is characterized in that described to carry out morphology to the bianry image
Closed operation, to be that described image is divided into multiple regions the step of region similar in connection, wherein different regions is respectively adopted
Different closed operation parameters to carry out morphology closed operation respectively.
4. license plate locating method according to claim 1, which is characterized in that the step S5 includes:
Step S51 carries out the processed filter interference noise of Gaussian mode gelatinization to the license plate picture of acquisition；
Step S52 carries out gray proces to filtered picture；
Step S53 extracts horizontal and vertical edge by image of the Sobel operator to gray proces respectively, obtains the side of license plate
Edge image；
Step S54 successively carries out binaryzation, closed operation processing to the license plate edge image of acquisition, then extracts all profiles；
Step S55 takes minimum circumscribed rectangle to each profile, while according to the tilt angle of license plate and length-width ratio primary filtration one
A little underproof candidate license plates, are then standardized the size of remaining candidate license plate, obtain license plate.
5. license plate locating method according to claim 2, which is characterized in that step S25 includes:
To the image after standardization carry out affine transformation with the rectangle guaranteed be it is horizontal, reduce subsequent license plate judgement and word
Accord with the difficulty of identification.
6. license plate locating method according to claim 4, which is characterized in that step S55 respectively include:
To the image after standardization carry out affine transformation with the rectangle guaranteed be it is horizontal, reduce subsequent license plate judgement and word
Accord with the difficulty of identification.
7. license plate locating method according to claim 1, which is characterized in that the step S7 includes:
Step S71 carries out gray processing to the license plate picture of acquisition, obtains gray level image；
Step S72 carries out multilevel binary to the gray level image, and analyzes connection region；
Step S73 takes minimum circumscribed rectangle to connection region, draws the angle point of rectangle；
Step S74 is fitted by RANSAC algorithm；
Step S75 cuts the region after fitting, obtains license plate.
8. license plate locating method according to claim 7, which is characterized in that the step S74 includes:
Some angle points are randomly selected, a model is established, according to the remaining point of the model measurement, if the data point of test is in error
In the range of permission, then the data point is judged to available point, is otherwise judged to noise；
If illustrating that these data point sets this time chosen reach when the number of available point has reached the threshold value of some setting
Otherwise acceptable degree continues all steps after randomly selecting point set of front, this process is constantly repeated, until finding
Until these data point sets chosen have reached acceptable degree, the model obtained at this time can be considered to data point
Optimal models building；
The angle point generated in step S73 is fitted using RANSAC algorithm, finds coboundary and lower boundary.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811334969.7A CN109670498A (en) | 2018-11-10 | 2018-11-10 | A kind of license plate locating method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811334969.7A CN109670498A (en) | 2018-11-10 | 2018-11-10 | A kind of license plate locating method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109670498A true CN109670498A (en) | 2019-04-23 |
Family
ID=66142723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811334969.7A Pending CN109670498A (en) | 2018-11-10 | 2018-11-10 | A kind of license plate locating method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109670498A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079744A (en) * | 2019-12-06 | 2020-04-28 | 鲁东大学 | Intelligent vehicle license plate identification method and device suitable for complex illumination environment |
| CN111382704A (en) * | 2020-03-10 | 2020-07-07 | 北京以萨技术股份有限公司 | Vehicle line-pressing violation judgment method and device based on deep learning and storage medium |
| CN111401364A (en) * | 2020-03-18 | 2020-07-10 | 深圳市市政设计研究院有限公司 | License plate positioning algorithm based on combination of color features and template matching |
| CN113095320A (en) * | 2021-04-01 | 2021-07-09 | 湖南大学 | License plate recognition method and system and computing device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999753A (en) * | 2012-05-07 | 2013-03-27 | 腾讯科技（深圳）有限公司 | License plate locating method |
| CN106650553A (en) * | 2015-10-30 | 2017-05-10 | 比亚迪股份有限公司 | License plate recognition method and system |
| CN108537099A (en) * | 2017-05-26 | 2018-09-14 | 华南理工大学 | A kind of licence plate recognition method of complex background |
-
2018
- 2018-11-10 CN CN201811334969.7A patent/CN109670498A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999753A (en) * | 2012-05-07 | 2013-03-27 | 腾讯科技（深圳）有限公司 | License plate locating method |
| CN106650553A (en) * | 2015-10-30 | 2017-05-10 | 比亚迪股份有限公司 | License plate recognition method and system |
| CN108537099A (en) * | 2017-05-26 | 2018-09-14 | 华南理工大学 | A kind of licence plate recognition method of complex background |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079744A (en) * | 2019-12-06 | 2020-04-28 | 鲁东大学 | Intelligent vehicle license plate identification method and device suitable for complex illumination environment |
| CN111079744B (en) * | 2019-12-06 | 2020-09-01 | 鲁东大学 | Intelligent vehicle license plate identification method and device suitable for complex illumination environment |
| CN111382704A (en) * | 2020-03-10 | 2020-07-07 | 北京以萨技术股份有限公司 | Vehicle line-pressing violation judgment method and device based on deep learning and storage medium |
| CN111382704B (en) * | 2020-03-10 | 2023-12-15 | 以萨技术股份有限公司 | Vehicle line pressing violation judging method and device based on deep learning and storage medium |
| CN111401364A (en) * | 2020-03-18 | 2020-07-10 | 深圳市市政设计研究院有限公司 | License plate positioning algorithm based on combination of color features and template matching |
| CN111401364B (en) * | 2020-03-18 | 2023-07-25 | 深圳市市政设计研究院有限公司 | License plate positioning algorithm based on combination of color features and template matching |
| CN113095320A (en) * | 2021-04-01 | 2021-07-09 | 湖南大学 | License plate recognition method and system and computing device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670498A (en) | A kind of license plate locating method | |
| CN107545239B (en) | Fake plate detection method based on license plate recognition and vehicle characteristic matching | |
| CN109657632B (en) | Lane line detection and identification method | |
| CN108564814B (en) | Image-based parking lot parking space detection method and device | |
| CN112487898B (en) | Automatic determination method, equipment and system for alignment of inlet and discharge openings of stirring truck of stirring station | |
| CN107423735B (en) | License plate positioning method utilizing horizontal gradient and saturation | |
| CN111695373B (en) | Zebra stripes positioning method, system, medium and equipment | |
| CN109919002A (en) | The recognition methods of yellow stop forbidden line, device, computer equipment and storage medium | |
| CN106650611B (en) | Method and device for recognizing color of vehicle body | |
| CN103093229B (en) | Car is demarcated method for position and device | |
| CN114387591A (en) | License plate recognition method, system, equipment and storage medium | |
| CN115272199A (en) | PCB carrier plate defect detection method and system, electronic equipment and medium | |
| CN116310845A (en) | Intelligent monitoring system for sewage treatment | |
| CN117094975A (en) | Method and device for detecting surface defects of steel and electronic equipment | |
| CN111667509B (en) | Automatic tracking method and system for moving target under condition that target and background colors are similar | |
| CN107066929B (en) | Hierarchical recognition method for parking events of expressway tunnel integrating multiple characteristics | |
| CN113569859B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN106384103A (en) | Vehicle face recognition method and device | |
| CN116363097A (en) | Defect detection method and system for photovoltaic panel | |
| Ishizuka et al. | Segmentation of road sign symbols using opponent-color filters | |
| CN112991284B (en) | Temperature controller guide frame defect detection method and system | |
| CN111626180B (en) | Lane line detection method and device based on polarization imaging | |
| CN114359597A (en) | Oil tank inner cover identification and pose parameter sensing method based on vision | |
| CN110321973B (en) | Combined vehicle detection method based on vision | |
| CN114373147A (en) | Detection method for low-texture video license plate |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |