CN105354570B - A kind of pinpoint method and system of license plate right boundary - Google Patents
A kind of pinpoint method and system of license plate right boundary Download PDFInfo
- Publication number
- CN105354570B CN105354570B CN201510674167.0A CN201510674167A CN105354570B CN 105354570 B CN105354570 B CN 105354570B CN 201510674167 A CN201510674167 A CN 201510674167A CN 105354570 B CN105354570 B CN 105354570B
- Authority
- CN
- China
- Prior art keywords
- license plate
- boundary
- image
- margin
- fitting
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000006243 chemical reaction Methods 0.000 claims abstract description 38
- 238000007689 inspection Methods 0.000 claims abstract description 23
- 239000011159 matrix material Substances 0.000 description 4
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- 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
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
This application provides a kind of pinpoint methods of license plate right boundary, obtain the target license plate image Jing Guo Rough Inspection；The target license plate image is transformed into YCbCr color space；Extract the target license plate image corresponding Cb component in YCbCr color space；Binary conversion treatment is carried out to the Cb component by maximum variance between clusters, obtains bianry image；Up-and-down boundary positioning is carried out to the bianry image；When the up-and-down boundary positions successfully, binary conversion treatment is carried out by maximum variance between clusters to the image by up-and-down boundary positioning；The scanning of effective trip point is carried out to the image after binary conversion treatment；Effective trip point of every a line left margin and right margin is fitted respectively, obtains best left margin and best right margin.Effectively improve the problem that the positioning of license plate right boundary is inaccurate in complex background.
Description
Technical field
This application involves Car license recognition field, in particular to a kind of pinpoint method and system of license plate right boundary.
Background technique
With the development of technology, the requirement that people position license plate right boundary is higher and higher.
Current license plate locating method mainly includes following several: (1) based on the license plate locating method of edge detection: such
Method positioning is more accurate, and speed is slower, and missing inspection is higher, and false detection rate is also higher；(2) based on the localization method of mathematical morphology: should
Class method is suitable for certain specific occasions, may fail for complex scene, the structure size of Morphological scale-space is not easily-controllable
System, speed are slower；(3) license plate locating method based on license plate color feature: such method characteristic is accurate positioning, and precision is high,
But bad adaptability can not make situations such as colour cast and background color interference and be effectively treated, not be used alone generally, (4)
License plate locating method based on machine learning, such as using SVM, the car plate detection device of the classifier trainings such as Adaboost is such
Method accurate positioning, adaptability is preferable, but speed is very slow, uses general with Rough Inspection.
Currently by the strategy of Rough Inspection and essence inspection, License Plate can reach practical level, but still have
Complex background or the not accurate problem of License Plate with outer rim, the especially right boundary of license plate are accurately positioned problem.
Summary of the invention
The technical problem to be solved by the application is to provide a kind of pinpoint method and system of license plate right boundary, solutions
It has determined problem not accurate for some complex backgrounds or License Plate with outer rim in the prior art, especially license plate
Right boundary is accurately positioned problem.
Its concrete scheme is as follows:
A kind of pinpoint method of license plate right boundary, this method comprises:
Obtain the target license plate image Jing Guo Rough Inspection；
The target license plate image is transformed into YCbCr color space；
Extract the target license plate image corresponding Cb component in YCbCr color space；
Binary conversion treatment is carried out to the Cb component by maximum variance between clusters, obtains bianry image；
Boundary alignment is carried out to the bianry image；
When boundary alignment success, the image Jing Guo boundary alignment is carried out at binaryzation by maximum variance between clusters
Reason；
The scanning of effective trip point is carried out to the image after binary conversion treatment；
Effective trip point of every a line left margin and right margin is fitted respectively, obtains best left margin and the best right side
Boundary.
Above-mentioned method, it is preferred that described that boundary alignment is carried out to the bianry image, comprising:
The boundary up and down for meeting threshold value is obtained from the bianry image；
Judge whether the wide height of license plate meets preset condition, if it is not, then setting the warp for the boundary up and down of license plate
Cross the boundary up and down of the target license plate image of Rough Inspection；
Carry out up-and-down boundary positioning.
Above-mentioned method, it is preferred that described that the boundary up and down for meeting threshold value, packet are obtained from the bianry image
It includes:
Floor projection and upright projection are carried out to the bianry image；
From left to right, from right to left, from the top down and the bottom up, upright projection image and floor projection image are traversed；
The boundary up and down for meeting threshold value is obtained, and a certain proportion of extend out is carried out to the boundary up and down.
Above-mentioned method, it is preferred that the described pair of image after binary conversion treatment carries out the scanning of effective trip point, packet
It includes:
Effectively jump spot scan is carried out to the image after binary conversion treatment by row, records effective trip point letter
Breath；
Judge whether effective trip point information meets threshold condition, if so, retaining effective trip point information, otherwise, then
Abandon effective trip point information of current line.
Above-mentioned method, it is preferred that effective trip point to every a line left margin and right margin is fitted respectively,
Obtain best left margin and best right margin, comprising:
Effective trip point of every a line left margin and right margin is fitted respectively, the left margin after being fitted and quasi-
Right margin after conjunction；
Whether the right margin after left margin and the fitting after judging the fitting meets the requirement of license plate width；
When the left margin after the fitting and the right margin after the fitting meet the requirement of license plate width, described in determination
Left margin after fitting is best left margin, and the right margin after the fitting is best right margin.
A kind of pinpoint system of license plate right boundary, the system include:
First acquisition unit, for obtaining the target license plate image Jing Guo Rough Inspection；
Converting unit, for the target license plate image to be transformed into YCbCr color space；
Extracting unit, for extracting the target license plate image corresponding Cb component in YCbCr color space；
First binary conversion treatment unit, for carrying out binary conversion treatment to the Cb component by maximum variance between clusters,
Obtain bianry image；
Positioning unit, for carrying out boundary alignment to the bianry image；
Second binary conversion treatment unit, for passing through maximum to the image Jing Guo boundary alignment when boundary alignment success
Ostu method carries out binary conversion treatment；
Scanning element, for carrying out the scanning of effective trip point to the image after binary conversion treatment；
Fitting unit is fitted respectively for effective trip point to every a line left margin and right margin, is obtained best
Left margin and best right margin.
Above-mentioned system, it is preferred that the positioning unit includes:
Second acquisition unit, for obtaining the boundary up and down for meeting threshold value from the bianry image；
First judging unit, for judging whether the wide height of license plate meets preset condition, if it is not, then up and down by license plate
Boundary is set as the boundary up and down of the target license plate image by Rough Inspection；
Locator unit, for carrying out up-and-down boundary positioning.
Above-mentioned system, it is preferred that the second acquisition unit includes:
Projecting cell, for carrying out floor projection and upright projection to the bianry image；
Traversal Unit, for from left to right, from right to left, from the top down and the bottom up, traversing upright projection image and water
Flat projected image；
Second obtains subelement, for obtaining the boundary up and down for meeting threshold value, and to the boundary up and down into
Row is a certain proportion of to be extended out.
Above-mentioned system, it is preferred that the scanning element includes:
Subelement is scanned, for carrying out effectively jump spot scan, note to the image after binary conversion treatment by row
Record effective trip point information；
Second judgment unit is effectively jumped for judging whether effective trip point information meets threshold condition if so, retaining
Otherwise height information then abandons effective trip point information of current line.
Above-mentioned system, it is preferred that the fitting unit includes:
It is fitted subelement, is fitted, is intended respectively for effective trip point to every a line left margin and right margin
The right margin after left margin and fitting after conjunction；
Third judging unit, for judging whether the left margin after the fitting and the right margin after the fitting meet vehicle
The requirement of board width；
Determination unit meets wanting for license plate width for the left margin after fitting and the right margin after the fitting
When asking, the left margin after determining the fitting is best left margin, and the right margin after the fitting is best right margin.
In the pinpoint method of license plate right boundary provided by the present application, the target license plate image Jing Guo Rough Inspection is obtained；
The target license plate image is transformed into YCbCr color space；The target license plate image is extracted in YCbCr color space
Corresponding Cb component；Binary conversion treatment is carried out to the Cb component by maximum variance between clusters, obtains bianry image；To described
Bianry image carries out up-and-down boundary positioning；It is logical to the image by up-and-down boundary positioning when the up-and-down boundary positions successfully
It crosses maximum variance between clusters and carries out binary conversion treatment；The scanning of effective trip point is carried out to the image after binary conversion treatment；
Effective trip point of every a line left margin and right margin is fitted respectively, obtains best left margin and best right margin.This
In application, the target license plate image Jing Guo Rough Inspection is converted, obtains corresponding Cb component, using Cb component binaryzation into
Then the positioning of row bound carries out the fitting of the effective trip point in left and right boundary, obtain optimal left margin and right margin, completes
The accurate positioning of license plate right boundary effectively improves the problem that the positioning of license plate right boundary is inaccurate in complex background.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those of ordinary skill in the art, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is a kind of flow chart of pinpoint embodiment of the method for license plate right boundary of the application；
Fig. 2 is a kind of pinpoint method specific implementation procedure chart of license plate right boundary of the application；
Fig. 3 is a kind of schematic diagram of pinpoint system embodiment of license plate right boundary of the application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
With reference to Fig. 1, a kind of flow chart of the pinpoint embodiment of the method for license plate right boundary of the application is shown, it can be with
The following steps are included:
Step S101: the target license plate image Jing Guo Rough Inspection is obtained.
In the application, Rough Inspection is carried out to license plate image first, obtains the license plate image after Rough Inspection, then to by thick
License plate image after inspection carries out a series of processing, obtains accurate right boundary.
Step S102: the target license plate image is transformed into YCbCr color space.
Step S103: the target license plate image corresponding Cb component in YCbCr color space is extracted.
When using RGB model, it is based on RGB color, can use formula Cb=-0.1482*R-0.2910*G+
0.4392*B+128+0.5 directly calculates Cb component.
Step S104: binary conversion treatment is carried out to the Cb component by maximum variance between clusters, obtains bianry image.
Cb component image is split using maximum variance between clusters, maximum variance between clusters are that a kind of stabilization is common
Algorithm, herein without detailed description.
Step S105: boundary alignment is carried out to the bianry image.
In the application, boundary alignment includes the accurate positioning of the coarse positioning and up-and-down boundary on boundary up and down.
Step S106: when boundary alignment success, the image Jing Guo boundary alignment is carried out by maximum variance between clusters
Binary conversion treatment.
Step S107: the scanning of effective trip point is carried out to the image after binary conversion treatment.
Step S108: effective trip point of every a line left margin and right margin is fitted respectively, obtains the best left side
Boundary and best right margin.
In the pinpoint method of license plate right boundary provided by the present application, the target license plate image Jing Guo Rough Inspection is carried out
Conversion, obtains corresponding Cb component, and the positioning on boundary is carried out using the binaryzation of Cb component, it is effective then to carry out left and right boundary
The fitting of trip point obtains optimal left margin and right margin, completes the accurate positioning of license plate right boundary, effective to improve
The inaccurate problem of license plate right boundary positioning in complex background.
With reference to Fig. 2, a kind of pinpoint method specific implementation procedure chart of license plate right boundary of the application is shown.
It is described that boundary alignment is carried out to the bianry image in the application, comprising:
The boundary up and down for meeting threshold value is obtained from the bianry image.
Specifically:
Floor projection and upright projection are carried out to the bianry image, obtain floor projection and upright projection image.
From left to right, from right to left, from the top down and the bottom up, upright projection image and floor projection image are traversed.
The boundary up and down for meeting threshold value is obtained, and a certain proportion of extend out is carried out to the boundary up and down.
Judge whether the wide height of license plate meets preset condition, if it is not, then setting the warp for the boundary up and down of license plate
Cross the boundary up and down of the target license plate image of Rough Inspection.
Carry out up-and-down boundary positioning.
Assuming that the width of license plate is W, it is highly H, the abscissa value of right boundary is leftX and rightX, up-and-down boundary
Ordinate value be respectively topY and bottomY, the abscissa value and ordinate value of a certain position are indicated with x and y respectively.
Scanned to the right from bianry image left margin and determine license plate left margin, when the corresponding upright projection value of x be greater than H/8 and 0 <
When x < W/2, leftX=x；It is scanned determining license plate right margin to the left from bianry image right margin, when the corresponding upright projection of x
When value is greater than H/8 and W/2≤X < W, rightX=x；Determining license plate coboundary is scanned downwards from coboundary, when Y is corresponding
When floor projection value is greater than W/8 and 0 < Y < H/2, topY=Y；Determining license plate lower boundary is scanned upwards from lower boundary, when Y pairs
When the floor projection value answered is greater than W/8 and H/2≤Y < H, bottomY=Y.
The wide height of new license plate area is judged, up-and-down boundary positioning is carried out if meeting the requirements, is otherwise used
Original image is as the input picture for carrying out up-and-down boundary positioning.
In the application, the described pair of image after binary conversion treatment carries out the scanning of effective trip point, comprising:
Effectively jump spot scan is carried out to the image after binary conversion treatment by row, records effective trip point letter
Breath.
Wherein, effective trip point information includes effective trip point initial position, effective trip point number and redundancy jump
The information such as point number.
Judge whether effective trip point information meets threshold condition, if so, retaining effective trip point information, otherwise, then
Abandon effective trip point information of current line.
The jump spot scan of every a line is carried out from left to right, and two neighboring pixel absolute value of the difference defines latter for 255
A point is trip point.It is scanned to the right from first trip point continuation, if between second trip point and first trip point
Distance is less than 2.5*H, and H here is the license plate height after up-and-down boundary positioning, then it is assumed that and the two points are effective trip point, after
It is continuous to be scanned in this approach.Effective trip point is all saved as if the requirement that subsequent point meets above, when some jump
When point is unsatisfactory for required distance with a upper trip point, effective trip point of all records in front is emptied, at this time with current jump
Height re-starts the scanning of effective trip point as starting point, until all pixels of a line are scanned.In the mistake of scanning
Need to record the horizontal direction coordinate of effective trip point in every a line in journey, the total N of effective trip point is continuously unsatisfactory for effectively
The trip point maximum number maxN of trip point rule.
Judge the number of effective trip point and whether is completely continuously unsatisfactory for the trip point maximum number of effective trip point rule
Sufficient threshold requirement, current line belongs to effective row if N>14 and maxN<4, retains all the points information of current line；Otherwise it abandons
The information of current line.
In the application, effective trip point to every a line left margin and right margin is fitted respectively, is obtained best
Left margin and best right margin, comprising:
Effective trip point of every a line left margin and right margin is fitted respectively, the left margin after being fitted and quasi-
Right margin after conjunction.
Whether the right margin after left margin and the fitting after judging the fitting meets the requirement of license plate width.
When the left margin after the fitting and the right margin after the fitting meet the requirement of license plate width, described in determination
Left margin after fitting is best left margin, and the right margin after the fitting is best right margin.
Right boundary fitting is carried out according to obtained effective row record, for ease of description, is carried out in a matrix fashion effective
Capable expression:Wherein xijIndicate the coordinate value of horizontal direction, 0≤xij≤ w, every a line table in matrix
Show the horizontal coordinate of all effective trip points of certain a line, effective number of transitions of every a line might not be equal, total line number of matrix
No more than the height of image.Left margin fitting is carried out, first element of every a line in matrix is chosen, element set is { x00,
x10,…xn0, using formulaIt sums, it is right when f (t) is maximized
The x answeredtIt is just required left margin；The fitting of right margin is similar with left margin, and details are not described herein again.
Judge whether the right boundary of fitting meets the requirement of license plate width, it is accurately fixed to meet i.e. output license plate right boundary
The coordinate of position, does not meet the right boundary for directly exporting original License Plate.
It is corresponding with method provided by a kind of pinpoint embodiment of the method for license plate right boundary of above-mentioned the application, ginseng
See Fig. 3, present invention also provides a kind of pinpoint system embodiments of license plate right boundary, in the present embodiment, the system
Include:
First acquisition unit 301, for obtaining the target license plate image Jing Guo Rough Inspection.
Converting unit 302, for the target license plate image to be transformed into YCbCr color space.
Extracting unit 303, for extracting the target license plate image corresponding Cb component in YCbCr color space.
First binary conversion treatment unit 304, for being carried out at binaryzation by maximum variance between clusters to the Cb component
Reason, obtains bianry image.
Positioning unit 305, for carrying out boundary alignment to the bianry image.
Second binary conversion treatment unit 306, for passing through most to the image Jing Guo boundary alignment when boundary alignment success
Big Ostu method carries out binary conversion treatment.
Scanning element 307, for carrying out the scanning of effective trip point to the image after binary conversion treatment.
Fitting unit 308 is fitted respectively for effective trip point to every a line left margin and right margin, obtains most
Good left margin and best right margin.
The positioning unit includes:
Second acquisition unit, for obtaining the boundary up and down for meeting threshold value from the bianry image.
First judging unit, for judging whether the wide height of license plate meets preset condition, if it is not, then up and down by license plate
Boundary is set as the boundary up and down of the target license plate image by Rough Inspection.
Locator unit, for carrying out up-and-down boundary positioning.
The second acquisition unit includes:
Projecting cell, for carrying out floor projection and upright projection to the bianry image.
Traversal Unit, for from left to right, from right to left, from the top down and the bottom up, traversing upright projection image and water
Flat projected image.
Second obtains subelement, for obtaining the boundary up and down for meeting threshold value, and to the boundary up and down into
Row is a certain proportion of to be extended out.
The scanning element includes:
Subelement is scanned, for carrying out effectively jump spot scan, note to the image after binary conversion treatment by row
Record effective trip point information.
Second judgment unit is effectively jumped for judging whether effective trip point information meets threshold condition if so, retaining
Otherwise height information then abandons effective trip point information of current line.
The fitting unit includes:
It is fitted subelement, is fitted, is intended respectively for effective trip point to every a line left margin and right margin
The right margin after left margin and fitting after conjunction.
Third judging unit, for judging whether the left margin after the fitting and the right margin after the fitting meet vehicle
The requirement of board width.
Determination unit meets wanting for license plate width for the left margin after fitting and the right margin after the fitting
When asking, the left margin after determining the fitting is best left margin, and the right margin after the fitting is best right margin.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight
Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.
For device class embodiment, since it is basically similar to the method embodiment, so being described relatively simple, related place ginseng
See the part explanation of embodiment of the method.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when application.
As seen through the above description of the embodiments, those skilled in the art can be understood that the application can
It realizes by means of software and necessary general hardware platform.Based on this understanding, the technical solution essence of the application
On in other words the part that contributes to existing technology can be embodied in the form of software products, the computer software product
It can store in storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) executes the certain of each embodiment of the application or embodiment
Method described in part.
Detailed Jie has been carried out to a kind of pinpoint method and system of license plate right boundary provided herein above
It continues, specific examples are used herein to illustrate the principle and implementation manner of the present application, and the explanation of above embodiments is only
It is to be used to help understand the method for this application and its core ideas；At the same time, for those skilled in the art, according to this Shen
Thought please, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not manage
Solution is the limitation to the application.
Claims (8)
1. a kind of pinpoint method of license plate right boundary, which is characterized in that this method comprises:
Obtain the target license plate image Jing Guo Rough Inspection；
The target license plate image is transformed into YCbCr color space；
Extract the target license plate image corresponding Cb component in YCbCr color space；
Binary conversion treatment is carried out to the Cb component by maximum variance between clusters, obtains bianry image；
The boundary up and down for meeting threshold value is obtained from the bianry image；
Judge whether the wide height of license plate meets preset condition, if it is not, then setting described by thick for the boundary up and down of license plate
The boundary up and down of the target license plate image of inspection；
Carry out up-and-down boundary positioning；
When boundary alignment success, binary conversion treatment is carried out by maximum variance between clusters to the image Jing Guo boundary alignment；
The scanning of effective trip point is carried out to the image after binary conversion treatment；
Effective trip point of every a line left margin and right margin is fitted respectively, obtains best left margin and best the right
Boundary.
2. the method according to claim 1, wherein described obtain from the bianry image meets the upper of threshold value
Lower right boundary, comprising:
Floor projection and upright projection are carried out to the bianry image；
From left to right, from right to left, from the top down and the bottom up, upright projection image and floor projection image are traversed；
The boundary up and down for meeting threshold value is obtained, and a certain proportion of extend out is carried out to the boundary up and down.
3. the method according to claim 1, wherein the described pair of image after binary conversion treatment carries out effectively
The scanning of trip point, comprising:
Effectively jump spot scan is carried out to the image after binary conversion treatment by row, records effective trip point information；
Judge whether effective trip point information meets threshold condition, is otherwise then abandoned if so, retaining effective trip point information
Effective trip point information of current line.
4. the method according to claim 1, wherein effective jump to every a line left margin and right margin
Point is fitted respectively, obtains best left margin and best right margin, comprising:
Effective trip point of every a line left margin and right margin is fitted respectively, after the left margin and fitting after being fitted
Right margin；
Whether the right margin after left margin and the fitting after judging the fitting meets the requirement of license plate width；
When the left margin after the fitting and the right margin after the fitting meet the requirement of license plate width, the fitting is determined
Left margin afterwards is best left margin, and the right margin after the fitting is best right margin.
5. a kind of pinpoint system of license plate right boundary, which is characterized in that the system includes:
First acquisition unit, for obtaining the target license plate image Jing Guo Rough Inspection；
Converting unit, for the target license plate image to be transformed into YCbCr color space；
Extracting unit, for extracting the target license plate image corresponding Cb component in YCbCr color space；
First binary conversion treatment unit is obtained for carrying out binary conversion treatment to the Cb component by maximum variance between clusters
Bianry image；
Positioning unit, the positioning unit include: second acquisition unit, meet threshold value for obtaining from the bianry image
Boundary up and down；First judging unit, for judging whether the wide height of license plate meets preset condition, if it is not, then by the upper of license plate
Lower right boundary is set as the boundary up and down of the target license plate image by Rough Inspection；Locator unit, for carrying out
Up-and-down boundary positioning；
Second binary conversion treatment unit is used for when boundary alignment success, passing through maximum kind to the image Jing Guo boundary alignment
Variance method carries out binary conversion treatment；
Scanning element, for carrying out the scanning of effective trip point to the image after binary conversion treatment；
Fitting unit is fitted respectively for effective trip point to every a line left margin and right margin, obtains the best left side
Boundary and best right margin.
6. system according to claim 5, which is characterized in that the second acquisition unit includes:
Projecting cell, for carrying out floor projection and upright projection to the bianry image；
Traversal Unit, for from left to right, from right to left, from the top down and the bottom up, traversal upright projection image and level to be thrown
Shadow image；
Second obtains subelement, carries out one for obtaining the boundary up and down for meeting threshold value, and to the boundary up and down
Certainty ratio extends out.
7. system according to claim 5, which is characterized in that the scanning element includes:
Subelement is scanned, for carrying out effectively jump spot scan to the image after binary conversion treatment by row, record has
Imitate trip point information；
Second judgment unit, for judging whether effective trip point information meets threshold condition, if so, retaining effective trip point
Otherwise information then abandons effective trip point information of current line.
8. system according to claim 5, which is characterized in that the fitting unit includes:
It is fitted subelement, is fitted respectively for effective trip point to every a line left margin and right margin, after obtaining fitting
Left margin and fitting after right margin；
Third judging unit, for judging it is wide whether the left margin after the fitting and the right margin after the fitting meet license plate
The requirement of degree；
Determination unit meets the requirement of license plate width for the left margin after fitting and the right margin after the fitting
When, the left margin after determining the fitting is best left margin, and the right margin after the fitting is best right margin.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510674167.0A CN105354570B (en) | 2015-10-15 | 2015-10-15 | A kind of pinpoint method and system of license plate right boundary |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510674167.0A CN105354570B (en) | 2015-10-15 | 2015-10-15 | A kind of pinpoint method and system of license plate right boundary |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105354570A CN105354570A (en) | 2016-02-24 |
| CN105354570B true CN105354570B (en) | 2019-04-09 |
Family
ID=55330537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510674167.0A Expired - Fee Related CN105354570B (en) | 2015-10-15 | 2015-10-15 | A kind of pinpoint method and system of license plate right boundary |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105354570B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220579B (en) * | 2016-03-21 | 2020-02-04 | 杭州海康威视数字技术股份有限公司 | License plate detection method and device |
| CN108242059B (en) * | 2016-12-26 | 2021-03-12 | 深圳怡化电脑股份有限公司 | Image boundary searching method and device |
| CN106960184B (en) * | 2017-03-08 | 2020-03-31 | 南昌航空大学 | Image positioning method for book frame |
| CN107085707A (en) * | 2017-04-14 | 2017-08-22 | 河海大学 | A license plate location method based on traffic surveillance video |
| CN108805122A (en) * | 2017-05-03 | 2018-11-13 | 迅驰（北京）视讯科技有限公司 | Car plate horizontal tilt antidote, system and car license recognition equipment |
| CN111860496A (en) * | 2020-06-22 | 2020-10-30 | 中国平安财产保险股份有限公司 | License plate recognition method, device, equipment and computer readable storage medium |
| CN118781120B (en) * | 2024-09-12 | 2025-03-18 | 杭州汇萃智能科技有限公司 | A method, system and medium for detecting debonding based on vision technology |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101183427A (en) * | 2007-12-05 | 2008-05-21 | 浙江工业大学 | Device for illegal parking detection based on computer vision |
| CN101587544A (en) * | 2009-06-24 | 2009-11-25 | 钟德胜 | Automotive on-vehicle antitracking device based on computer vision |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4061907B2 (en) * | 2002-01-15 | 2008-03-19 | セイコーエプソン株式会社 | Output and save image processed image data |
-
2015
- 2015-10-15 CN CN201510674167.0A patent/CN105354570B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101183427A (en) * | 2007-12-05 | 2008-05-21 | 浙江工业大学 | Device for illegal parking detection based on computer vision |
| CN101587544A (en) * | 2009-06-24 | 2009-11-25 | 钟德胜 | Automotive on-vehicle antitracking device based on computer vision |
Non-Patent Citations (2)
| Title |
|---|
| 车牌自动识别系统;何斌;《中国优秀硕士学位论文全文数据库信息科技辑》;20080815(第08期);I138-598 |
| 车牌识别系统中定位算法的研究;张洁玮;《中国优秀硕士学位论文全文数据库信息科技辑》;20070115(第01期);I138-332 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105354570A (en) | 2016-02-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105354570B (en) | A kind of pinpoint method and system of license plate right boundary | |
| CN103824066B (en) | A kind of licence plate recognition method based on video flowing | |
| CN108491784B (en) | Single person close-up real-time identification and automatic screenshot method for large live broadcast scene | |
| CN101615252B (en) | Method for extracting text information from adaptive images | |
| CN103186904B (en) | Picture contour extraction method and device | |
| CN103324930B (en) | A license plate character segmentation method based on gray histogram binarization | |
| US7664315B2 (en) | Integrated image processor | |
| CN103793708B (en) | A kind of multiple dimensioned car plate precise positioning method based on motion correction | |
| CN101673338A (en) | Fuzzy license plate identification method based on multi-angle projection | |
| CN103440633B (en) | A kind of digital picture dispels the method for spot automatically | |
| CN105303153A (en) | Vehicle license plate identification method and apparatus | |
| CN105894004A (en) | Complement technology of locating incomplete license plate aiming at license plate identification system | |
| CN103530608A (en) | Vehicle type judgment method and vehicle type judgment device | |
| CN106650729B (en) | A kind of characters on license plate cutting method based on projection | |
| KR101246120B1 (en) | A system for recognizing license plate using both images taken from front and back faces of vehicle | |
| CN103955949A (en) | Moving target detection method based on Mean-shift algorithm | |
| CN102799882A (en) | License plate positioning method based on visual saliency | |
| CN107392139A (en) | A kind of method for detecting lane lines and terminal device based on Hough transformation | |
| CN107423735B (en) | License plate positioning method utilizing horizontal gradient and saturation | |
| CN110458855A (en) | Image extraction method and Related product | |
| CN110472628A (en) | A kind of improvement Faster R-CNN network detection floating material method based on video features | |
| CN104463134A (en) | License plate detection method and system | |
| JP2011165170A (en) | Object detection device and program | |
| CN109583341B (en) | Method and device for detecting multi-person skeleton key points of image containing portrait | |
| CN104268595A (en) | General object detecting method and system |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190409 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |