CN106485248A - A kind of slag-soil truck license plate sloped correcting method - Google Patents
A kind of slag-soil truck license plate sloped correcting method Download PDFInfo
- Publication number
- CN106485248A CN106485248A CN201610922854.4A CN201610922854A CN106485248A CN 106485248 A CN106485248 A CN 106485248A CN 201610922854 A CN201610922854 A CN 201610922854A CN 106485248 A CN106485248 A CN 106485248A
- Authority
- CN
- China
- Prior art keywords
- license plate
- image
- slag
- car plate
- soil truck
- 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 43
- 239000002689 soil Substances 0.000 title claims abstract description 10
- 238000012937 correction Methods 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000006243 chemical reaction Methods 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 6
- 229910052704 radon Inorganic materials 0.000 abstract description 4
- SYUHGPGVQRZVTB-UHFFFAOYSA-N radon atom Chemical compound [Rn] SYUHGPGVQRZVTB-UHFFFAOYSA-N 0.000 abstract description 4
- 239000000203 mixture Substances 0.000 abstract description 2
- 230000011218 segmentation Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation 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
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of slag-soil truck license plate sloped correcting method, comprises the following steps：S21, using bilinear interpolation fitting process be fitted car plate yellow area edge straight line, so as to detect level, the vertical tilt angle of car plate；S22, license plate sloped correction is realized using image Shear Transform method.The present invention is before Image semantic classification, with bilinear interpolation fitting and Shear Transform method, Color License Plate image to coarse positioning realizes level, vertical skew correction, propose bilinear fit function and blend, with Shear Transform, the shortcoming that method avoids the sloped correcting methods such as Hough transform, Radon conversion so that the slant correction of Color License Plate image is realized, effectively.
Description
Technical field
The present invention relates to a kind of slag-soil truck license plate sloped correcting method.
Background technology
Car license recognition (License Plate Recognition, LPR) is one kind typical case of computer image recognition technology
Application, it based on the technology such as Digital Image Processing, pattern-recognition, computer vision, by the license plate in motion from multiple
Extract in miscellaneous background and identify, it is the important component part of intelligent transportation system, has been widely used in automatic charging
Stand, intelligent parking lot, vehicle flowrate monitoring, prohibited security zone management etc. place.
LPR system mainly includes License Plate, slant correction, Character segmentation, four parts of character recognition, Chinese scholars
Substantial amounts of research is carried out around this four processes, and achieved numerous achievements in research.
In image acquisition process, shooting angle can usually cause car plate horizontally or vertically to incline, and this can affect the accurate of character
Segmentation, even results in segmentation failure, it is therefore necessary to carry out license plate sloped correction.Conventional sloped correcting method have Hough transform,
Radon conversion, Harris Corner Detection etc., but said method is solely focused on horizontal tilt correction and ignores vertical tilt school
Just, and higher to Image semantic classification dependence, usually cause calibration result even without frame not because car plate frame is fuzzy
Preferable.
Content of the invention
The technical problem to be solved in the present invention is the defect for overcoming prior art, provides a kind of slag-soil truck license plate sloped correction
Method.
In order to solve above-mentioned technical problem, the invention provides following technical scheme：
A kind of slag-soil truck license plate sloped correcting method of the present invention, which comprises the following steps：
S21, using bilinear interpolation fitting process be fitted car plate yellow area edge straight line, so as to detect the water of car plate
Flat, vertical tilt angle；
S22, license plate sloped correction is realized using image Shear Transform method；
Further, step S21 is specifically referred to：
S211, the car plate coloured image first to coarse positioning are scanned by column from top to bottom line by line or from left to right, record
Each column or row occur the coordinate of yellow pixel point for the first time；
S212, these points are fitted using bilinear interpolation fitting process, a fitting a straight line is just obtained；
S213, the horizontally or vertically angle of inclination of car plate is obtained by the slope of this straight line.
Further, step S22 is concretely comprised the following steps：
With x-axis as relying on the Shear Transform matrix of axle it is
Then the image coordinate after conversion is
Sh in formulax=tan α, α are the angles that level mistake is cut；
With y-axis as relying on the Shear Transform matrix of axle it is
Then the image coordinate after conversion is
Sh in formulay=tan β, β are the angles that faulting is cut.
The beneficial effect reached by the present invention is：
The present invention was fitted with bilinear interpolation and Shear Transform method, the coloured silk to coarse positioning before Image semantic classification
Color license plate image realizes level, vertical skew correction, it is proposed that bilinear fit function blends method to realize coloured silk with Shear Transform
The slant correction of color license plate image, effectively avoids the shortcoming of the sloped correcting methods such as Hough transform, Radon conversion.
Specific embodiment
Hereinafter the preferred embodiments of the present invention are illustrated, it will be appreciated that preferred embodiment described herein is only used
In the description and interpretation present invention, it is not intended to limit the present invention.
A kind of slag-soil truck license plate sloped correcting method, which comprises the following steps：
S21, using bilinear interpolation fitting process be fitted car plate yellow area edge straight line, so as to detect the water of car plate
Flat, vertical tilt angle：
S211, the car plate coloured image first to coarse positioning are scanned from top to bottom line by line (from left to right by column), and record is every
A (row) occurs the coordinate of yellow pixel point for the first time；
S212, these points are fitted using bilinear interpolation fitting process, a fitting a straight line is just obtained；
S213, level (vertical) angle of inclination of car plate is obtained by the slope of this straight line；
Realize license plate sloped correction, it is necessary to first know level, the vertical tilt angle of car plate.The side at detection angle of inclination
Method is to detect the slope of straight line, and conventional method is Hough transform or the Radon change detection based on bianry image at present
Go out the slope of car plate metal edge frame.The present invention is fitted the straight line at car plate yellow area edge using bilinear interpolation fitting process, from
And detect the level of car plate, vertical tilt angle.
To especially prevent the yellow pixel coordinate near car plate frame partially too far away in this process and cause fitting to miss
Difference is excessive.When (by column) Scanning Detction line by line the coordinate of yellow pixel point occurs for the first time per a (row), row (OK) are scanned
Scope beSo permissible
Effectively avoid counting the yellow pixel coordinate near car plate frame, so as to reduce error of fitting.Wherein parameter lambda, γ be all through
Value is tested, λ typically takes that 0.2-1.0 is proper, and it is proper that γ typically takes 4.0-4.8.
License plate area after coarse positioning is had concentrated on around character, and its yellow is projected relatively, is now fitted yellow
The error of pixel edges straight line is substantially reduced.Compared with the existing method based on bianry image detection angle of inclination, should
Method is more accurate.
S22, license plate sloped correction is realized using image Shear Transform method, which concretely comprises the following steps：
With x-axis as relying on the Shear Transform matrix of axle it is
Then the image coordinate after conversion is
Sh in formulax=tan α, α are the angles that level mistake is cut；
With y-axis as relying on the Shear Transform matrix of axle it is
Then the image coordinate after conversion is
Sh in formulay=tan β, β are the angles that faulting is cut；
By (2), (4) Shi Ke get, Shear Transform is twisted similar to parallelogram, and when level mistake is cut, vertical edges are motionless, is hung down
When straight mistake is cut, horizontal sides are motionless, and relative image rotation transformation has obvious advantage.
At present conventional sloped correcting method is obtained behind angle of inclination using image rotation converter technique, and which has the disadvantage entering
Also vertical edge can be rotated during row level correction, when carrying out vertical correction, equally can also rotate horizontal edge.Herein in order to avoid
The shortcoming of image rotation conversion, realizes license plate sloped correction using image Shear Transform method.
As the License Plate process of step S1 only achieves the coarse positioning of car plate, and in actual applications, due to camera
The reason such as shooting angle cause car plate horizontally or vertically to incline, the accurate segmentation of character can be affected, even result in Character segmentation
Failure, therefore license plate sloped correction is most important.And slant correction is actually the process of car plate fine positioning.Conventional inclination school
Bianry image after correction method is all based on greatly Image semantic classification is realized, and the present invention is before Image semantic classification, with double
Linear interpolation fitting and Shear Transform method, the Color License Plate image to coarse positioning realize level, vertical skew correction.
Finally it should be noted that：The preferred embodiments of the present invention are the foregoing is only, the present invention are not limited to,
Although being described in detail to the present invention with reference to the foregoing embodiments, for a person skilled in the art, which still may be used
To modify to the technical scheme described in foregoing embodiments, or equivalent is carried out to which part technical characteristic.
All any modification, equivalent substitution and improvement that within the spirit and principles in the present invention, is made etc., should be included in the present invention's
Within protection domain.
Claims (3)
1. a kind of slag-soil truck license plate sloped correcting method, it is characterised in that comprise the following steps：
S21, using bilinear interpolation fitting process be fitted car plate yellow area edge straight line, so as to detect car plate level, hang down
Straight angle of inclination；
S22, license plate sloped correction is realized using image Shear Transform method.
2. slag-soil truck license plate sloped correcting method according to claim 1, it is characterised in that step S21 is specifically referred to：
S211, the car plate coloured image first to coarse positioning are scanned by column from top to bottom line by line or from left to right, are recorded each
Column or row occur the coordinate of yellow pixel point for the first time；
S212, these points are fitted using bilinear interpolation fitting process, a fitting a straight line is just obtained；
S213, the horizontally or vertically angle of inclination of car plate is obtained by the slope of this straight line.
3. slag-soil truck license plate sloped correcting method according to claim 1, it is characterised in that step S22 is concretely comprised the following steps：
With x-axis as relying on the Shear Transform matrix of axle it is
Then the image coordinate after conversion is
Sh in formulax=tan α, α are the angles that level mistake is cut；
With y-axis as relying on the Shear Transform matrix of axle it is
Then the image coordinate after conversion is
Sh in formulay=tan β, β are the angles that faulting is cut.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610922854.4A CN106485248A (en) | 2016-10-20 | 2016-10-20 | A kind of slag-soil truck license plate sloped correcting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610922854.4A CN106485248A (en) | 2016-10-20 | 2016-10-20 | A kind of slag-soil truck license plate sloped correcting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106485248A true CN106485248A (en) | 2017-03-08 |
Family
ID=58270453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610922854.4A Pending CN106485248A (en) | 2016-10-20 | 2016-10-20 | A kind of slag-soil truck license plate sloped correcting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106485248A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704858A (en) * | 2017-10-31 | 2018-02-16 | 上海集光安防科技股份有限公司 | A kind of detection algorithm of license plate sloped angle |
| CN108682000A (en) * | 2018-02-12 | 2018-10-19 | 中国农业大学 | The long body width detecting method of pig body based on Kinect videos |
| CN109460722A (en) * | 2018-10-26 | 2019-03-12 | 华南理工大学 | A kind of license plate intelligent identification Method |
| CN109509368A (en) * | 2018-12-21 | 2019-03-22 | 深圳信路通智能技术有限公司 | A kind of parking behavior algorithm based on roof model |
| CN110348440A (en) * | 2019-07-09 | 2019-10-18 | 北京字节跳动网络技术有限公司 | Licence plate detection method, device, electronic equipment and storage medium |
| CN111178359A (en) * | 2018-11-09 | 2020-05-19 | 中移（杭州）信息技术有限公司 | License plate number recognition method, device and equipment and computer storage medium |
| CN111639642A (en) * | 2020-05-07 | 2020-09-08 | 浙江大华技术股份有限公司 | Image processing method, device and apparatus |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102867185A (en) * | 2012-10-31 | 2013-01-09 | 江苏大学 | Method and system for identifying automobile tire number |
| CN104156718A (en) * | 2014-08-20 | 2014-11-19 | 电子科技大学 | Vehicle license plate image vertical tilt correction method |
| CN105608455A (en) * | 2015-12-18 | 2016-05-25 | 浙江宇视科技有限公司 | License plate tilt correction method and apparatus |
-
2016
- 2016-10-20 CN CN201610922854.4A patent/CN106485248A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102867185A (en) * | 2012-10-31 | 2013-01-09 | 江苏大学 | Method and system for identifying automobile tire number |
| CN104156718A (en) * | 2014-08-20 | 2014-11-19 | 电子科技大学 | Vehicle license plate image vertical tilt correction method |
| CN105608455A (en) * | 2015-12-18 | 2016-05-25 | 浙江宇视科技有限公司 | License plate tilt correction method and apparatus |
Non-Patent Citations (3)
| Title |
|---|
| 吴礼斌，闫云侠编著: "《经济数学实验与建模》", 31 August 2009, 天津：天津大学出版社 * |
| 杨雪丹: "基于图像分析的车牌与车标定位及识别技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 赵金凯: "车牌定位与识别的研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704858A (en) * | 2017-10-31 | 2018-02-16 | 上海集光安防科技股份有限公司 | A kind of detection algorithm of license plate sloped angle |
| CN108682000A (en) * | 2018-02-12 | 2018-10-19 | 中国农业大学 | The long body width detecting method of pig body based on Kinect videos |
| CN108682000B (en) * | 2018-02-12 | 2020-10-09 | 中国农业大学 | Pig body length and body width detection method based on Kinect video |
| CN109460722A (en) * | 2018-10-26 | 2019-03-12 | 华南理工大学 | A kind of license plate intelligent identification Method |
| CN109460722B (en) * | 2018-10-26 | 2021-11-23 | 华南理工大学 | Intelligent license plate recognition method |
| CN111178359A (en) * | 2018-11-09 | 2020-05-19 | 中移（杭州）信息技术有限公司 | License plate number recognition method, device and equipment and computer storage medium |
| CN109509368A (en) * | 2018-12-21 | 2019-03-22 | 深圳信路通智能技术有限公司 | A kind of parking behavior algorithm based on roof model |
| CN110348440A (en) * | 2019-07-09 | 2019-10-18 | 北京字节跳动网络技术有限公司 | Licence plate detection method, device, electronic equipment and storage medium |
| CN111639642A (en) * | 2020-05-07 | 2020-09-08 | 浙江大华技术股份有限公司 | Image processing method, device and apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106485248A (en) | A kind of slag-soil truck license plate sloped correcting method | |
| US9904856B2 (en) | Method and apparatus for detecting target object in blind area of vehicle | |
| CN104657735B (en) | Method for detecting lane lines, system, lane departure warning method and system | |
| Yan et al. | A method of lane edge detection based on Canny algorithm | |
| CN103324930B (en) | A kind of registration number character dividing method based on grey level histogram binaryzation | |
| Li et al. | Nighttime lane markings recognition based on Canny detection and Hough transform | |
| CN101630360B (en) | Method for identifying license plate in high-definition image | |
| CN108038416B (en) | Lane line detection method and system | |
| CN104700072B (en) | Recognition methods based on lane line historical frames | |
| CN105047019B (en) | A kind of passenger stock prevent rear car overtake other vehicles after lane change determination methods and device suddenly | |
| CN109886896A (en) | A kind of blue License Plate Segmentation and antidote | |
| CN109886175B (en) | Method for detecting lane line by combining straight line and circular arc | |
| CN104899554A (en) | Vehicle ranging method based on monocular vision | |
| CN106887004A (en) | A kind of method for detecting lane lines based on Block- matching | |
| CN108256445B (en) | Lane line detection method and system | |
| CN105488501A (en) | Method for correcting license plate slant based on rotating projection | |
| CN101030256A (en) | Method and apparatus for cutting vehicle image | |
| EP2492868A1 (en) | Far-infrared pedestrian detection device | |
| CN110232835A (en) | A kind of underground garage parking space detection method based on image procossing | |
| CN105966314B (en) | Lane departure warning method based on double inexpensive cameras | |
| CN109583435A (en) | A kind of adaptive ballot method for detecting lane lines | |
| Devane et al. | Lane detection techniques using image processing | |
| CN106503709A (en) | A kind of slag-soil truck characters on license plate intelligent identification Method | |
| CN105303157A (en) | Algorithm to extend detecting range for AVM stop line detection | |
| CN109190483A (en) | A kind of method for detecting lane lines of view-based access control model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170308 |
|
| RJ01 | Rejection of invention patent application after publication |