CN107688810A - A kind of pseudo- licence plate traffic allowance detection method - Google Patents
A kind of pseudo- licence plate traffic allowance detection method Download PDFInfo
- Publication number
- CN107688810A CN107688810A CN201710798439.7A CN201710798439A CN107688810A CN 107688810 A CN107688810 A CN 107688810A CN 201710798439 A CN201710798439 A CN 201710798439A CN 107688810 A CN107688810 A CN 107688810A
- Authority
- CN
- China
- Prior art keywords
- blocks
- mser
- pseudo
- licence plate
- traffic allowance
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention proposes a kind of pseudo- licence plate traffic allowance detection method, comprises the following steps:S1, input picture, initiation parameter;S2, gray processing, binary conversion treatment are carried out to the image of input;S3, different connected regions is divided an image into, complete the extraction of MSER blocks;Whether MSER blocks are maximum stable extremal region in S4, judgment step S3;Distance in S5, calculation procedure S4 between adjacent MSER blocks, if distance in setting range value, by two merged blocks into a new MSER block;The ratio of width to height of the MSER blocks merged in S6, calculation procedure S5, if the ratio of width to height in setting range value, retains the MSER blocks of merging;S7, thickness detection is carried out to the MSER blocks of reservation using morphologic filtering, completes pseudo- licence plate traffic allowance detection.The pseudo- licence plate traffic allowance detection method algorithm design is simple, and accuracy of detection is higher, accurately and quickly can carry out detection positioning to pseudo- licence plate traffic allowance.
Description
Technical field
The present invention relates to Car license recognition field, and in particular to a kind of pseudo- licence plate traffic allowance detection method.
Background technology
License Plate is the important component of Car license recognition, due to the interference of extraneous factor, makes Car license recognition more tired
It is difficult.Extraneous factor mainly includes natural cause and human factor.Natural cause mainly includes illumination, blocked, complex background etc.;People
Mainly include pseudo- licence plate traffic allowance, coverage etc. for factor.
Common pseudo- licence plate traffic allowance is made up of Chinese character and picture, in irregular shape;Car plate is made up of Chinese character, letter and number,
It is shaped as rectangle.There is common component in them, so pseudo- licence plate traffic allowance has a great influence to car plate detection, how effectively to exclude puppet
Licence plate traffic allowance region is the difficult point of car plate detection.
At present, it is most of that pseudo- licence plate traffic allowance detection is carried out using MSER algorithms for the interference of human factor.MSER algorithms
With affine-invariant features, illumination adaptability, multiple scale detecting and to characteristics such as illumination-insensitives, domestic and foreign scholars, which have been done, largely grinds
Study carefully.Yet with the variation of present pseudo- licence plate traffic allowance, detection also has non-character area except license plate area, so the essence of algorithm
True rate is relatively low.
The content of the invention
In order to overcome defect present in above-mentioned prior art, it is an object of the invention to provide a kind of design of algorithm simply,
The higher pseudo- licence plate traffic allowance detection method of accurate rate.
In order to realize the above-mentioned purpose of the present invention, the invention provides a kind of pseudo- licence plate traffic allowance detection method, including it is following
Step:
S1, input picture, initiation parameter;
S2, gray processing, binary conversion treatment are carried out to the image of input;
S3, different connected regions is divided an image into, mark these regions, complete the extraction of MSER blocks;
Whether MSER blocks are maximum stable extremal region in S4, judgment step S3, if carrying out step S5, otherwise return to step
S3;
Distance in S5, calculation procedure S4 between adjacent MSER blocks, if distance in setting range value, by two merged blocks into one
Individual new MSER blocks;Otherwise, do not process;
The ratio of width to height of the MSER blocks merged in S6, calculation procedure S5, if the ratio of width to height in setting range value, retains what is merged
MSER blocks, otherwise remove the MSER blocks of merging;
S7, thickness detection is carried out to the MSER blocks of reservation using morphologic filtering, completes pseudo- licence plate traffic allowance detection.
The pseudo- licence plate traffic allowance detection method algorithm design is simple, and accuracy of detection is higher, can be accurately and quickly to pseudo- licence plate
Traffic allowance carries out detection positioning.
Further, the calculation formula of image gray processing is in the step S2:Gray value.Gray processing calculation formula letter
It is single, gray proces quickly can be carried out to image.
Further, the calculation formula of image binaryzation is in the step S2:, wherein, T is
The threshold value of binaryzation setting.The binaryzation calculation formula is simple, quickly can carry out binary conversion treatment to image.
Further, the step S3 points are following steps:
S3-1, threshold pixels are gradually incremented by from 0 to 255, different connected regions is divided an image into, marks these regions,
Complete the division of MSER blocks;
S3-2, the area change rate of MSER blocks is calculated, complete the extraction of MSER blocks, computational methods are, its
In,Represent that threshold value isWhen a certain connected region,For the variable quantity of threshold value,It is for threshold valueWhen connected region
Domain rate of change, i.e. area change rate.
The calculation formula of the area change rate is borderline region and the difference in areas of interior zone and the ratio of interior zone area
Value, on the one hand maintain MSER and detect original characteristic, on the other hand simplify the complexity of algorithm, it is effect to improve detection
Rate.
Further, in the step S4, whenWhen being worth minimum,For maximum stable extremal region.The judgement is maximum
The method of stable extremal region is simple, direct, helps to carry out pseudo- licence plate traffic allowance quickly detection positioning.
The additional aspect and advantage of the present invention will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
The above-mentioned and/or additional aspect and advantage of the present invention will become in the description from combination accompanying drawings below to embodiment
Substantially and it is readily appreciated that, wherein:
Fig. 1 is the flow chart of the present invention;
Fig. 2 is the image after gray processing;
Fig. 3 is the image after binaryzation;
Fig. 4 is the MSER blocks of extraction.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, is only used for explaining the present invention, and is not considered as limiting the invention.
In the description of the invention, unless otherwise prescribed with limit, it is necessary to explanation, term " installation ", " connected ",
" connection " should be interpreted broadly, for example, it may be mechanical connection or electrical connection or the connection of two element internals, can
To be to be joined directly together, can also be indirectly connected by intermediary, for the ordinary skill in the art, can basis
Concrete condition understands the concrete meaning of above-mentioned term.
As shown in figure 1, the invention provides a kind of pseudo- licence plate traffic allowance detection method, comprise the following steps:
The first step, input picture, initiation parameter.The pseudo- licence plate traffic allowance image generally captured by video camera is all RGB image,
The information content that RGB image includes is larger, and storage overhead is very big, and the execution speed of system can be also reduced in processing, and RGB is schemed
Internal memory and reduction run time can be saved as being transformed to gray level image.
Second step, gray processing, binary conversion treatment are carried out to the image of input.
The calculation formula of wherein image gray processing is:Gray value
, Fig. 2 is by the image after the gray processing calculation formula gray processing.
The calculation formula of image binaryzation is:, wherein, T is the threshold value of binaryzation setting.Fig. 3
To use the image after the calculation formula binaryzation of image binaryzation.
3rd step, different connected regions is divided an image into, mark these regions, complete the extraction of MSER blocks.
Specific method is:
S3-1, threshold pixels are gradually incremented by from 0 to 255, different connections is divided an image into according to different threshold pixels
Region, these regions are marked, complete the division of MSER blocks.Specifically, using but be not limited to the different connected region of oval marks.
S3-2, the area change rate of MSER blocks is calculated, complete the extraction of MSER blocks, computational methods are
, wherein,Represent that threshold value isWhen a certain connected region,For the variable quantity of threshold value,It is for threshold valueWhen company
Logical local change frequency.
Because pseudo- licence plate traffic allowance and car plate have Chinese character, and the change of the pixel of character is more stable, so each character
A MSER block can be regarded as.Thus, the existing pseudo- licence plate traffic allowance of MSER blocks extracted from image has car plate, and pseudo- licence plate traffic allowance again
Shape is more.China's characters on license plate is highly 90mm, and width 45mm, shared region length-width ratio is 2:1, separator " " it is straight
Footpath is 10mm.Fig. 4 is the MSER blocks of extraction.
4th step, judge whether MSER blocks are maximum stable extremal region in the 3rd step, if carrying out the 5th step, otherwise return
Return the 3rd step.In the present embodiment, whenWhen being worth minimum,For maximum stable extremal region.
5th step, calculate the distance between adjacent MSER blocks in the 4th step, if distance in setting range value, by two blocks
It is merged into a new MSER block;Otherwise, do not process.
During using the different connected region of oval marks, Europe of the distance between two oval centers of circle between adjacent MSER blocks
Formula distance, calculation formula are:,For oval central coordinate of circle.
Gauged distance between China's characters on license plate is 12mm, the distance between adjacent MSER blocks is calculated, if distance is in 12-32mm
Between, then by two merged blocks into a new MSER block;Otherwise, do not process.
6th step, the ratio of width to height of the MSER blocks merged in the 5th step is calculated, if the ratio of width to height retains in setting range value
The MSER blocks of merging, otherwise remove the MSER blocks of merging.
During using the different connected region of oval marks, the ratio of width to height of the MSER blocks of merging for ellipse short shaft and major axis it
Than.
The ratio of width to height of China's car plate is 3.14, first, the ratio of width to height of the MSER blocks merged in the 5th step is calculated, if the ratio of width to height
Between 2.9-3.3, then retain the MSER blocks of merging, otherwise remove the MSER blocks of merging.
7th step, thickness detection is carried out to the MSER blocks of reservation using morphologic filtering, completes pseudo- licence plate traffic allowance detection.This
In morphologic filtering thickness detection carried out to the MSER blocks of reservation calculated using existing method, including expansion, rotten
Erosion, opening operation, closed operation.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Necessarily refer to identical embodiment or example.Moreover, specific features, structure, material or the feature of description can be any
One or more embodiments or example in combine in an appropriate manner.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that:Not
In the case of departing from the principle and objective of the present invention a variety of change, modification, replacement and modification can be carried out to these embodiments, this
The scope of invention is limited by claim and its equivalent.
Claims (5)
1. a kind of pseudo- licence plate traffic allowance detection method, it is characterised in that comprise the following steps:
S1, input picture, initiation parameter;
S2, gray processing, binary conversion treatment are carried out to the image of input;
S3, different connected regions is divided an image into, mark these regions, complete the extraction of MSER blocks;
Whether MSER blocks are maximum stable extremal region in S4, judgment step S3, if carrying out step S5, otherwise return to step
S3;
Distance in S5, calculation procedure S4 between adjacent MSER blocks, if distance in setting range value, by two merged blocks into one
Individual new MSER blocks;Otherwise, do not process;
The ratio of width to height of the MSER blocks merged in S6, calculation procedure S5, if the ratio of width to height in setting range value, retains what is merged
MSER blocks, otherwise remove the MSER blocks of merging;
S7, thickness detection is carried out to the MSER blocks of reservation using morphologic filtering, completes pseudo- licence plate traffic allowance detection.
2. pseudo- licence plate traffic allowance detection method according to claim 1, it is characterised in that image gray processing in the step S2
Calculation formula be:Gray value。
3. pseudo- licence plate traffic allowance detection method according to claim 1, it is characterised in that image binaryzation in the step S2
Calculation formula be:, wherein, T is the threshold value of binaryzation setting.
4. pseudo- licence plate traffic allowance detection method according to claim 1, it is characterised in that the step S3 points are following step
Suddenly:
S3-1, threshold pixels are gradually incremented by from 0 to 255, different connected regions is divided an image into, marks these regions,
Complete the division of MSER blocks;
S3-2, the area change rate of MSER blocks is calculated, complete the extraction of MSER blocks, computational methods are, its
In, a certain connected region when threshold value is is represented, for the variable quantity of threshold value, connected region rate of change when being for threshold value.
5. pseudo- licence plate traffic allowance detection method according to claim 4, it is characterised in that in the step S4, when value is minimum
When, it is maximum stable extremal region.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710798439.7A CN107688810A (en) | 2017-09-07 | 2017-09-07 | A kind of pseudo- licence plate traffic allowance detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710798439.7A CN107688810A (en) | 2017-09-07 | 2017-09-07 | A kind of pseudo- licence plate traffic allowance detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107688810A true CN107688810A (en) | 2018-02-13 |
Family
ID=61156160
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710798439.7A Pending CN107688810A (en) | 2017-09-07 | 2017-09-07 | A kind of pseudo- licence plate traffic allowance detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107688810A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111027544A (en) * | 2019-11-29 | 2020-04-17 | 武汉虹信技术服务有限责任公司 | MSER license plate positioning method and system based on visual saliency detection |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101859382A (en) * | 2010-06-03 | 2010-10-13 | 复旦大学 | License plate detection and identification method based on maximum stable extremal region |
CN105654140A (en) * | 2016-01-04 | 2016-06-08 | 哈尔滨工程大学 | Complex industrial environment-oriented wagon number positioning and identifying method for railway tank wagon |
CN106650731A (en) * | 2016-12-23 | 2017-05-10 | 中山大学 | Robust license plate and logo recognition method |
CN107045633A (en) * | 2016-12-26 | 2017-08-15 | 上海大学 | A kind of digital locating segmentation method of the energy measurement table tool based on ST MSER |
-
2017
- 2017-09-07 CN CN201710798439.7A patent/CN107688810A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101859382A (en) * | 2010-06-03 | 2010-10-13 | 复旦大学 | License plate detection and identification method based on maximum stable extremal region |
CN105654140A (en) * | 2016-01-04 | 2016-06-08 | 哈尔滨工程大学 | Complex industrial environment-oriented wagon number positioning and identifying method for railway tank wagon |
CN106650731A (en) * | 2016-12-23 | 2017-05-10 | 中山大学 | Robust license plate and logo recognition method |
CN107045633A (en) * | 2016-12-26 | 2017-08-15 | 上海大学 | A kind of digital locating segmentation method of the energy measurement table tool based on ST MSER |
Non-Patent Citations (3)
Title |
---|
H. ZHU 等: "Specularity detection method based on MSER", 《ELECTRONICS LETTERS》 * |
杨波: "商品包装上的文字检测和识别", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
肖意: "基于最大稳定极值区域的车牌识别系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111027544A (en) * | 2019-11-29 | 2020-04-17 | 武汉虹信技术服务有限责任公司 | MSER license plate positioning method and system based on visual saliency detection |
CN111027544B (en) * | 2019-11-29 | 2023-09-29 | 武汉虹信技术服务有限责任公司 | MSER license plate positioning method and system based on visual saliency detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103366167B (en) | System and method for processing image for identifying alphanumeric characters present in a series | |
Li et al. | Nighttime lane markings recognition based on Canny detection and Hough transform | |
CN106446894A (en) | Method for recognizing position of spherical object based on contour | |
CN103198319B (en) | For the blurred picture Angular Point Extracting Method under the wellbore environment of mine | |
CN106156749A (en) | Method for detecting human face based on selective search and device | |
CN103544502A (en) | High-resolution remote-sensing image ship extraction method based on SVM | |
CN105447489A (en) | Character and background adhesion noise elimination method for image OCR system | |
CN103021179B (en) | Based on the Safe belt detection method in real-time monitor video | |
CN103793921B (en) | Moving object extraction method and moving object extraction device | |
CN106683062A (en) | Method of checking the moving target on the basis of ViBe under a stationary camera | |
CN105447863A (en) | Residue detection method based on improved VIBE | |
CN107369162A (en) | A kind of generation method and system of insulator candidate target region | |
CN107688810A (en) | A kind of pseudo- licence plate traffic allowance detection method | |
Xiaolin et al. | Unstructured road detection based on region growing | |
CN108510513A (en) | A kind of PCB image circle detection method based on PCA and segmentation RHT | |
CN103164857B (en) | A kind of efficient detection method of the short-distance large-deflection circular target based on image | |
CN108009480A (en) | A kind of image human body behavioral value method of feature based identification | |
CN112418226A (en) | Method and device for identifying opening and closing states of fisheyes | |
CN106778675B (en) | A kind of recognition methods of target in video image object and device | |
CN106339709A (en) | Real-time image extraction method | |
CN107341830A (en) | A kind of method and device for determining shell hole ring value | |
Zhe et al. | A Traffic signs' detection method of contour approximation based on concave removal | |
Kim | License plate location method unaffected by variation in size and aspect ratio | |
Jun et al. | A vehicle license plate location and correction method based the characteristics of license plate | |
CN106845488A (en) | A kind of license plate image processing method and processing device |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180213 |
|
RJ01 | Rejection of invention patent application after publication |