CN106650728A - Shadow license plate image binarization method - Google Patents
Shadow license plate image binarization method Download PDFInfo
- Publication number
- CN106650728A CN106650728A CN201611131239.8A CN201611131239A CN106650728A CN 106650728 A CN106650728 A CN 106650728A CN 201611131239 A CN201611131239 A CN 201611131239A CN 106650728 A CN106650728 A CN 106650728A
- Authority
- CN
- China
- Prior art keywords
- image
- license plate
- region
- width
- height
- 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.)
- Granted
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
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- 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
The invention discloses a shadow license plate image binarization method and belongs to the technical field of intelligent traffic. The method comprises the steps of obtaining a license plate color image subjected to license plate accurate locating; extracting a red channel of the license plate color image to serve as a license plate grayscale image; judging whether the license plate image has a rule shadow or not; if yes, finding a region in which a boundary line of dark and bright regions is located, and obtaining an image binarization result through a regional binarization method; and if not, performing image binarization through a global threshold method to obtain a binarization result. According to the method, the red channel is extracted for performing gray processing on the obtained image, a difference value of grayscale values of a foreground and a background of the image is increased, and the binarization of a shadow license plate is carried out through the regional binarization method, so that an algorithm is simple, and the "artifact" problem can be improved; and different binarization polices are used for the shadow license plate and a general license plate, so that while the binarization result of the shadow license plate is improved, the binarization effect and processing efficiency of the general license plate are not influenced.
Description
Technical field
The invention belongs to technical field of intelligent traffic, specifically a kind of shade license plate image before characters on license plate cutting
Binarization method.
Background technology
With the continuous development of the technologies such as machine vision, Digital Image Processing, pattern-recognition, intelligent transportation system (ITS)
It is increasingly becoming the main path for realizing automatic traffic management.License plate recognition technology is the key technology for realizing intelligent transportation system
One of, it realizes the automatic identification of the number-plate number by the method for image procossing.Image binaryzation is the key of car plate pretreatment
Link, the definition direct relation of binary image the accuracy rate of follow-up characters on license plate cutting and character recognition.
Existing image binaryzation method has a lot, is mainly divided to Global thresholding and the big class of local thresholding method two, global threshold
Value method includes OTSU methods, p-tile methods, gray average method etc., and local thresholding method includes Bernsen methods, varimax etc..Entirely
Office's threshold method operation time is fast, but when there is the car plate of shade for process, it may appear that shadow region character shows incomplete
Or the situation that highlight regions background mistake shows, main cause is the shade car plate gray-scale map that direct gray processing is obtained, and there is the moon
The prospect gray value of dark areas and the very close situation of the background gray levels of highlight regions, it is impossible to realized by single threshold value
The segmentation of display foreground and background, therefore local thresholding method becomes the main binarization method for processing shade car plate.
Car plate rule shadow problem is the subproblem of car plate uneven illumination problem, and in order to solve, car plate uneven illumination is even to ask
Topic, many scholars propose various solutions, and the basic procedure of these methods is all to first pass through certain algorithm for image enhancement
Improve the contrast of image, then carry out image binaryzation using local thresholding method.Such as Ma Chaoyu (the multistage photo-irradiation treatments of fusion
License plate image Binarization methods [J]. computer application, 2013,33 (S2):200-202) first car plate is obtained by weighting method
Gray level image, then using top cap conversion homogenizing background illumination, using Retinex algorithm homogenizing character illumination is strengthened, and is finally led to
Crossing dynamic thresholding method carries out image binaryzation.Although the method can be homogenized illumination, strengthen the contrast of prospect background, move
State threshold method needs the calculating that threshold value is carried out to each pixel, and algorithm complexity is higher, and the binaryzation result of the method
There are problems that " artifact " on bright dark areas line of demarcation, that is, there is adhesion situation.(Recognition of License Plate Characters under natural scene is covered as peaceful
The research [D] of method. Zhengzhou University, 2015) first the gray level image of car plate is obtained by weighting method, then using homomorphic filtering
Method so as to reduce impact of the illumination to image, strengthens picture contrast, finally by improved compressing high frequency enhancement low frequency
Niblack algorithms carry out image binaryzation.The method can be with effectively solving car plate shadow problem, but homomorphic filtering method is in space-time
Take relatively long in the change in domain, and the Binarization methods of the method need also exist for being analyzed each pixel, it is inefficient.Europe
Global Suntech (car plate image binaryzation studies [J] under uneven illumination. Wuhan University Journal, 2006,4 (39):143-147) in gray scale
On the basis of image, using homomorphic filtering method carry out image increase it is clear, then carry out image two-value using improved Bernsen algorithms
Change, the method equally exists efficiency and " artifact " problem.King's Jun etc. (the binaryzation new method [J] under complex illumination. electronics
Design engineering, 2011,19 (22):Part modification 147-150) is carried out on the basis of Ou Yangqing proposed method, while proposing
The improved gradation of image method based on weighting.Chen Liang etc. (improve the license plate image Binarization methods [J] of background compensation. Yangzhou
College journal, 2008,1 (11):55-58) first image enhaucament is carried out with homomorphic filtering method, then by improved background compensation
Binaryzation method carries out image binaryzation, the method relatively sorrow in time efficiency and treatment effect.
In sum, the deficiency that the current scheme for solving the even problem of license plate image uneven illumination is primarily present includes：(1) figure
Image intensifying algorithm and Image binarizing algorithm complexity are higher, and method efficiency is poor；(2) although being calculated by certain image enhaucament
Method can strengthen background, the contrast of prospect, but " artifact " problem still occurs on bright dark areas line of demarcation.
The content of the invention
The purpose of the present invention is to overcome not enough present in general license plate image preprocess method, there is provided one kind can be in car
The shade Binarization of License Plate Images of regular shade is eliminated before board Character segmentation, described regular shade is meant that, by
Car plate top vehicle body blocks the shade for causing, and shade lower boundary tends to level or there is relatively small tilt angle or there is less radian.
Described a kind of shade Binarization of License Plate Images, it is characterised in that comprise the steps：
Step 1：The car plate coloured picture after car plate precise positioning is obtained, the wherein width of license plate image is width, highly
For height, unit is pixel；
Step 2：Extraction step 1) original car plate coloured picture red channel as license plate grey level image；
Step 3：License plate image is judged with the presence or absence of regular shade, if it is present find dark bright area line of demarcation being located
Region, then obtains image binaryzation result by subregion binarization method, if it does not exist, then being entered by Global thresholding
Row image binaryzation, final binaryzation result.
A kind of described shade Binarization of License Plate Images, it is characterised in that step 3) in judge whether license plate image is deposited
In regular shade, if it is present finding dark bright area line of demarcation region, then obtained by subregion binarization method
Image binaryzation result, if it does not exist, then carrying out image binaryzation by Global thresholding, its detailed process is：
Step 3.1：To step 2) license plate grey level image split, obtain for analysing whether to there is regular shade
Four image-region { S1,S2,S3,S4, partitioning scheme is：According to formula (1), image border region is removed, obtain picture centre area
Domain D, then according to formula (2)-(5), picture centre region D is vertically bisected into highly consistent four region { S1,S2,
S3,S4}：
D=(x, y) | x ∈ [0.1 × width, 0.9 × width], y ∈ [0.1 × height, 0.9 × height] } (1)
S1=(x, y) | and x ∈ [0.1 × width, 0.9 × width], y ∈ [0.1 × height, 0.3 × height) } (2)
S2=(x, y) | and x ∈ [0.1 × width, 0.9 × width], y ∈ [0.3 × height, 0.5 × height) } (3)
S3=(x, y) | and x ∈ [0.1 × width, 0.9 × width], y ∈ [0.5 × height, 0.7 × height) } (4)
S4=(x, y) | x ∈ [0.1 × width, 0.9 × width], y ∈ [0.7 × height, 0.9 × height] } (5)；
Step 3.2：{ S is obtained using OTSU algorithms1,S2,S3,S4Four regions most suitable threshold value { t1,t2,t3,t4}；
Step 3.3：Backward travels through threshold set { t1,t2,t3,t4, find and meet condition tx-tx-1＞ 10, x's ∈ { 4,3,2 }
Region Sx-1,Sx, go to step 3.4；If do not found, 3.5 are gone to step；
Step 3.4：According to the region S found in step 3.3x-1,Sx, determine image dark bright area line of demarcation region
Coboundary and lower boundary be respectively Sx-1.above、Sx.below, wherein, Sx-1.above region S is representedx-1Coboundary institute
It is expert at, Sx.below region S is representedxLower boundary is expert at, and image is divided into S' according to this upper and lower border1,S'2,S'3Three areas
Then domain, the scope in each region calculates trizonal binaryzation threshold by formula (6)-(8) determination according to formula (9)-(11)
Value t'1,t'2,t'3, and binaryzation is carried out to regional according to respective threshold value, finally by S'1,S'2,S'3Trizonal two
Value image is spliced, and obtains the binaryzation result of target license plate image；
S'1=(x, y) | and x ∈ [0, width), y ∈ [0, Sx-1.above)} (6)
S'2=(x, y) | and x ∈ [0, width), y ∈ [Sx-1.above,Sx.below)} (7)
S'3=(x, y) | and x ∈ [0, width), y ∈ [Sx.below,height)} (8)
t′2=0.7 × tx-1+0.3×tx (10)
Wherein, x represents the region S determined in step 3.3xSubscript；
Step 3.5：The binary-state threshold t of license plate image is calculated according to formula (12) ", then according to threshold value t " to car plate
Image carries out binaryzation, obtains final binaryzation result：
Wherein, t2,t3It is the S drawn in step 3.22,S3Threshold value corresponding to region.
By the way that using above-mentioned technology, compared with prior art, beneficial effects of the present invention are as follows：The present invention is by using upper
Technology is stated, energy effectively solving car plate rule shadow problem, the accuracy for later stage Character segmentation and Car license recognition provides guarantor
Card, compared with additive method, its advantage is：1) image gray processing is obtained by extracting red channel, before widening image
The difference of the gray value of scape background, then carries out the binaryzation of shade car plate by subregion binarization method, and algorithm is simple, and
" artifact " problem can be effectively improved；2) different binaryzation strategies is used to shade car plate and common car plate, is improving shade car
While the binaryzation result of board, can guarantee that and the binaryzation effect and treatment effeciency of common car plate are not impacted.
Description of the drawings
Fig. 1 is the license plate grey level image that the car plate coloured picture that the embodiment of the present invention is chosen is processed through step 2；
Fig. 2 is the license plate image region segmentation figure that the car plate coloured picture that the embodiment of the present invention is chosen is processed through step 3.1；
Fig. 3 is the license plate image region segmentation figure that the car plate coloured picture that the embodiment of the present invention is chosen is processed through step 3.4；
Fig. 4 is the license plate image binaryzation result that the car plate coloured picture that the embodiment of the present invention is chosen is processed through step 3.4.
Specific embodiment
Elaborate the present invention with reference to Figure of description and embodiment, but protection scope of the present invention and not only limit
In this.
As illustrated, the shade Binarization of License Plate Images of the present invention, specifically includes following steps：
Step 1：A car plate coloured picture after car plate precise positioning is obtained, the wherein width of license plate image is width,
It is highly height, unit is pixel；
Step 2：Extraction step 1) choose original car plate coloured picture red channel as license plate grey level image, red channel
It is the maximum passage of dark prospect and highlighted background gray levels difference, the prospect background occurred after binaryzation can be effectively improved and be mixed
Situation about confusing, it is as shown in Figure 1 according to the license plate grey level image that step 2 is obtained；
Step 3：Judge step 2) license plate grey level image with the presence or absence of regular shade, if it is present finding dark clear zone
Domain line of demarcation region, then obtains image binaryzation result by subregion binarization method, if it does not exist, then passing through
Global thresholding carries out image binaryzation, specially：
Step 3.1：License plate grey level image is split, four images for analysing whether to there is regular shade are obtained
Region { S1,S2,S3,S4, cutting mode is：Image border region is removed first, obtains picture centre region D, it is to avoid marginal zone
Calculating of the miscellaneous side that may be present to threshold value in domain is interfered, and is then vertically bisected into region D highly consistent
Four region { S1,S2,S3,S4, the scope in each region can be determined by formula (1)-(5)：
D=(x, y) | x ∈ [0.1 × width, 0.9 × width], y ∈ [0.1 × height, 0.9 × height] } (1)
S1=(x, y) | and x ∈ [0.1 × width, 0.9 × width], y ∈ [0.1 × height, 0.3 × height) } (2)
S2=(x, y) | and x ∈ [0.1 × width, 0.9 × width], y ∈ [0.3 × height, 0.5 × height) } (3)
S3=(x, y) | and x ∈ [0.1 × width, 0.9 × width], y ∈ [0.5 × height, 0.7 × height) } (4)
S4=(x, y) | x ∈ [0.1 × width, 0.9 × width], y ∈ [0.7 × height, 0.9 × height] } (5)
Car plate gray-scale map is cut according to step 3.1, cutting result as shown in Fig. 2 for asking for threshold value, wherein red
Frame represents region D positions, and blue line represents { S1,S2,S3,S4Four regions line of demarcation.
Step 3.2：{ S is obtained using OTSU algorithms1,S2,S3,S4Four regions most suitable threshold value { t1,t2,t3,t4, Jing
Calculate, region { S can be obtained1,S2,S3,S4Corresponding to most suitable threshold value be { 50,55,133,128 }.
Step 3.3：Backward travels through threshold set { t1,t2,t3,t4, find and meet condition tx-tx-1＞ 10, x's ∈ { 4,3,2 }
Region Sx-1,Sx, go to step 3.4；If do not found, 3.5 are gone to step.
According to step 3.3, it may be determined that meet condition t in Fig. 2x-tx-1The region S of ＞ 10, x ∈ { 4,3,2 }x-1,SxFor
S2,S3, go to step 3.4.
Step 3.4：According to the region S found in step 3.3x-1,Sx, it may be determined that the dark bright area line of demarcation of image is located
The coboundary in region and lower boundary are Sx-1.above、Sx.below, wherein, Sx-1.above region S is representedx-1Coboundary institute
It is expert at, Sx.below region S is representedxLower boundary is expert at, and image can be divided into S' according to this upper and lower border1,S'2,S'3Three
Individual region, the scope in each region can determine by formula (6)-(8), then calculate trizonal two according to formula (9)-(11)
Value threshold value t'1,t'2,t'3, and binaryzation is carried out to regional according to respective threshold value, finally by S'1,S'2,S'3Three areas
The binary image in domain is spliced, and obtains the binaryzation result of target license plate image；
S'1=(x, y) | and x ∈ [0, width), y ∈ [0, Sx-1.above)} (6)
S'2=(x, y) | and x ∈ [0, width), y ∈ [Sx-1.above,Sx.below)} (7)
S'3=(x, y) | and x ∈ [0, width), y ∈ [Sx.below,height)} (8)
t'2=0.7 × tx-1+0.3×tx (10)
Wherein, x represents the region S determined in step 3.3xSubscript；
License plate grey level image is cut again according to step 3.4, is obtained region S'1,S'2,S'3, as shown in figure 3, with
In subregion binaryzation is carried out, wherein 3 horizontal lines represent area limit line.Can be calculated simultaneously trizonal most suitable
Threshold value t't,t'2,t'3For { 50,78.4,128 }.After finally by subregion binaryzation, image mosaic, the license plate image for obtaining
Binaryzation result is as shown in Figure 4.
Step 3.5：The binary-state threshold t of license plate image is calculated according to formula (12) ", then according to threshold value t " to car plate
Image carries out binaryzation, obtains final binaryzation result：
Wherein, t2,t3It is the S drawn in step 3.22,S3Threshold value corresponding to region.
Cited process object in this specification specific implementation method, is merely to illustrate the process of realizing of the present invention, this
The treatable object situation of invention institute is not limited only to example.
Claims (2)
1. a kind of shade Binarization of License Plate Images, it is characterised in that comprise the steps：
Step 1：The car plate coloured picture after car plate precise positioning is obtained, the wherein width of license plate image is width, is highly
Height, unit is pixel；
Step 2：The red channel of original coloured picture is extracted as license plate grey level image；
Step 3：License plate image is judged with the presence or absence of regular shade, if it is present dark bright area line of demarcation region is found,
Then image binaryzation result is obtained by subregion binarization method, if it does not exist, then carrying out figure by Global thresholding
As binaryzation, final binaryzation result is obtained.
2. a kind of shade Binarization of License Plate Images according to claim 1, it is characterised in that step 3) in judgement
License plate image is with the presence or absence of regular shade, if it is present dark bright area line of demarcation region is found, then by subregion
Binarization method obtains image binaryzation result, if it does not exist, then carrying out image binaryzation, concrete mistake by Global thresholding
Cheng Wei：
Step 3.1：To step 2) license plate grey level image split, obtain for analyse whether to there is regular shade four
Image-region { S1,S2,S3,S4, partitioning scheme is：According to formula (1), image border region is removed, obtains picture centre region D,
Then according to formula (2)-(5), region D is vertically bisected into highly consistent four region { S1,S2,S3,S4}：
D=(x, y) | x ∈ [0.1 × width, 0.9 × width], y ∈ [0.1 × height, 0.9 × height] } (1)
S1=(x, y) | and x ∈ [0.1 × width, 0.9 × width], y ∈ [0.1 × height, 0.3 × height) } (2)
S2=(x, y) | and x ∈ [0.1 × width, 0.9 × width], y ∈ [0.3 × height, 0.5 × height) } (3)
S3=(x, y) | and x ∈ [0.1 × width, 0.9 × width], y ∈ [0.5 × height, 0.7 × height) } (4)
S4=(x, y) | x ∈ [0.1 × width, 0.9 × width], y ∈ [0.7 × height, 0.9 × height] } (5)
Step 3.2：{ S is obtained using OTSU algorithms1,S2,S3,S4Four regions most suitable threshold value { t1,t2,t3,t4}；
Step 3.3：Backward travels through threshold set { t1,t2,t3,t4, find and meet condition tx-tx-1The region of ＞ 10, x ∈ { 4,3,2 }
Sx-1,Sx, go to step 3.4；If do not found, 3.5 are gone to step；
Step 3.4：According to the region S found in step 3.3x-1,Sx, determine the top of image dark bright area line of demarcation region
Boundary and lower boundary are Sx-1.above、Sx.below, wherein, Sx-1.above region S is representedx-1Coboundary be expert at,
Sx.below region S is representedxLower boundary is expert at, and image is divided into S' according to this upper and lower border1,S'2,S'3Three regions, respectively
The scope in region can determine by formula (6)-(8), then calculate trizonal binary-state threshold according to formula (9)-(11)
t′1,t'2,t'3, and binaryzation is carried out to regional according to respective threshold value, finally by S'1,S'2,S'3Trizonal two-value
Change image to be spliced, obtain the binaryzation result of target license plate image；
S'1=(x, y) | and x ∈ [0, width), y ∈ [0, Sx-1.above)} (6)
S'2=(x, y) | and x ∈ [0, width), y ∈ [Sx-1.above,Sx.below)} (7)
S'3=(x, y) | and x ∈ [0, width), y ∈ [Sx.below,height)} (8)
t′2=0.7 × tx-1+0.3×tx (10)
Wherein, x represents the region S determined in step 3.3xSubscript；
Step 3.5：The binary-state threshold t of license plate image is calculated according to formula (12) ", then according to threshold value t " to license plate image
Binaryzation is carried out, final binaryzation result is obtained：
Wherein, t2,t3It is the S drawn in step 3.22,S3Threshold value corresponding to region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611131239.8A CN106650728B (en) | 2016-12-09 | 2016-12-09 | A kind of shade Binarization of License Plate Images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611131239.8A CN106650728B (en) | 2016-12-09 | 2016-12-09 | A kind of shade Binarization of License Plate Images |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106650728A true CN106650728A (en) | 2017-05-10 |
| CN106650728B CN106650728B (en) | 2019-06-21 |
Family
ID=58824009
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611131239.8A Active CN106650728B (en) | 2016-12-09 | 2016-12-09 | A kind of shade Binarization of License Plate Images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106650728B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428440A (en) * | 2019-07-23 | 2019-11-08 | 浙江树人学院（浙江树人大学） | A kind of shadow detection method based on gray variance |
| CN111542856A (en) * | 2018-07-16 | 2020-08-14 | 华为技术有限公司 | Skin detection method and electronic equipment |
| CN112837313A (en) * | 2021-03-05 | 2021-05-25 | 云南电网有限责任公司电力科学研究院 | Image segmentation method for foreign matters in power transmission line |
| CN113689710A (en) * | 2021-09-01 | 2021-11-23 | 深圳市博思凯电子有限公司 | Edge calculation method and system used for intelligent parking unattended operation |
| CN113808048A (en) * | 2021-09-23 | 2021-12-17 | 安徽理工大学 | Image enhancement system for excavation simulation field |
| CN117690142A (en) * | 2024-02-01 | 2024-03-12 | 深圳中科精工科技有限公司 | Wafer character preprocessing method, device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050123195A1 (en) * | 2003-11-26 | 2005-06-09 | Shinichi Takarada | Image processing method and image processing apparatus |
| CN1932838A (en) * | 2005-09-12 | 2007-03-21 | 电子科技大学 | Vehicle plate extracting method based on skiagraphy and mathematical morphology |
| CN103488978A (en) * | 2013-09-26 | 2014-01-01 | 浙江工业大学 | License plate positioning method based on gray level jump and character projection interval mode |
-
2016
- 2016-12-09 CN CN201611131239.8A patent/CN106650728B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050123195A1 (en) * | 2003-11-26 | 2005-06-09 | Shinichi Takarada | Image processing method and image processing apparatus |
| CN1932838A (en) * | 2005-09-12 | 2007-03-21 | 电子科技大学 | Vehicle plate extracting method based on skiagraphy and mathematical morphology |
| CN103488978A (en) * | 2013-09-26 | 2014-01-01 | 浙江工业大学 | License plate positioning method based on gray level jump and character projection interval mode |
Non-Patent Citations (1)
| Title |
|---|
| 高星: ""汽车牌照自动识别方法的研究"", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111542856A (en) * | 2018-07-16 | 2020-08-14 | 华为技术有限公司 | Skin detection method and electronic equipment |
| CN112215802A (en) * | 2018-07-16 | 2021-01-12 | 华为技术有限公司 | Skin detection method and electronic equipment |
| CN112215802B (en) * | 2018-07-16 | 2022-04-08 | 荣耀终端有限公司 | Skin detection method and electronic equipment |
| US11798162B2 (en) | 2018-07-16 | 2023-10-24 | Honor Device Co., Ltd. | Skin detection method and electronic device |
| CN111542856B (en) * | 2018-07-16 | 2024-07-12 | 荣耀终端有限公司 | Skin detection method and electronic equipment |
| CN110428440A (en) * | 2019-07-23 | 2019-11-08 | 浙江树人学院（浙江树人大学） | A kind of shadow detection method based on gray variance |
| CN112837313A (en) * | 2021-03-05 | 2021-05-25 | 云南电网有限责任公司电力科学研究院 | Image segmentation method for foreign matters in power transmission line |
| CN113689710A (en) * | 2021-09-01 | 2021-11-23 | 深圳市博思凯电子有限公司 | Edge calculation method and system used for intelligent parking unattended operation |
| CN113808048A (en) * | 2021-09-23 | 2021-12-17 | 安徽理工大学 | Image enhancement system for excavation simulation field |
| CN117690142A (en) * | 2024-02-01 | 2024-03-12 | 深圳中科精工科技有限公司 | Wafer character preprocessing method, device and storage medium |
| CN117690142B (en) * | 2024-02-01 | 2024-05-28 | 深圳中科精工科技有限公司 | Wafer character preprocessing method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106650728B (en) | 2019-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106650728A (en) | Shadow license plate image binarization method | |
| CN102043950B (en) | Vehicle outline recognition method based on canny operator and marginal point statistic | |
| CN101872416B (en) | Vehicle license plate recognition method and system of road image | |
| CN104156731B (en) | Vehicle License Plate Recognition System and method based on artificial neural network | |
| CN103198315B (en) | Based on the Character Segmentation of License Plate of character outline and template matches | |
| CN107301405A (en) | Method for traffic sign detection under natural scene | |
| CN103679168A (en) | Detection method and detection device for character region | |
| CN102915544B (en) | Video image motion target extracting method based on pattern detection and color segmentation | |
| CN104050450A (en) | Vehicle license plate recognition method based on video | |
| CN105160691A (en) | Color histogram based vehicle body color identification method | |
| CN104732211B (en) | A kind of method for traffic sign detection based on adaptive threshold | |
| CN102096821A (en) | Number plate identification method under strong interference environment on basis of complex network theory | |
| CN102254152A (en) | License plate location method based on color change points and color density | |
| CN104732220A (en) | Specific color human body detection method oriented to surveillance videos | |
| CN100385452C (en) | Registration number character dividing method | |
| CN102509095B (en) | Number plate image preprocessing method | |
| CN105005766A (en) | Vehicle body color identification method | |
| CN109886168B (en) | Ground traffic sign identification method based on hierarchy | |
| CN107705254A (en) | A kind of urban environment appraisal procedure based on streetscape figure | |
| CN105809699B (en) | A kind of vehicle window extracting method and system based on figure segmentation | |
| CN108960259A (en) | A kind of license plate preprocess method based on HSV | |
| CN105184294A (en) | Inclination character judgment and identification method based on pixel tracking | |
| CN111401364A (en) | License plate positioning algorithm based on combination of color features and template matching | |
| Chen et al. | License plate recognition for moving vehicles using a moving camera | |
| CN105654140B (en) | The positioning of rail tank car license number and recognition methods towards complex industrial environment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200923 Address after: 310016 19 / F, block B, Jinjiang times building, 217 Wujiang Road, Shangcheng District, Hangzhou City, Zhejiang Province Patentee after: Zhejiang Zhongan Electronic Engineering Co., Ltd Address before: 323000 Zhejiang city of Lishui Province Green Information Industry Park Incubator Building 12 201 Tianning Patentee before: ZHEJIANG HAOTENG ELECTRON TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |