CN107945194A - Bill dividing method based on OpenCV technologies - Google Patents
Bill dividing method based on OpenCV technologies Download PDFInfo
- Publication number
- CN107945194A CN107945194A CN201711046410.XA CN201711046410A CN107945194A CN 107945194 A CN107945194 A CN 107945194A CN 201711046410 A CN201711046410 A CN 201711046410A CN 107945194 A CN107945194 A CN 107945194A
- Authority
- CN
- China
- Prior art keywords
- bill
- edge
- picture
- opencv
- scanned copy
- 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 28
- 238000005516 engineering process Methods 0.000 title claims abstract description 17
- 238000003708 edge detection Methods 0.000 claims abstract description 18
- 238000006243 chemical reaction Methods 0.000 claims abstract description 11
- 238000001914 filtration Methods 0.000 claims abstract description 11
- 230000009466 transformation Effects 0.000 claims abstract description 11
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims abstract description 9
- 230000002146 bilateral effect Effects 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000013459 approach Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 18
- 230000008569 process Effects 0.000 abstract description 4
- 230000011218 segmentation Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000013461 design Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G06T3/147—
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20028—Bilateral filtering
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Abstract
The invention discloses the bill dividing method based on OpenCV technologies, it is related to computer image processing technology field.Comprise the following steps:Step 1:Picture pretreatment is carried out to scanned copy picture, the pretreatment includes the denoising to scanned copy image content and binary conversion treatment, the denoising includes bilateral filtering, medium filtering carries out smoothly, the binary conversion treatment, the gray-scale map content of picture is specially first obtained, then carries out binary conversion treatment further according to rational threshold value;Step 2:Edge detection is carried out to scanned copy using Canny operators, obtains bill edge line of the bill in whole picture, its minimum outer rectangular is then obtained according to bill edge line computation;Step 3:According to the bill edge line detected and its minimum outer rectangular, sola bill is partitioned into using the affine transformation function in Opencv.Method proposed by the invention then only needs marginal information to complete the above process, not only saves computing resource, also improves the speed of bill processing.
Description
Technical field
Embodiments of the present invention are related to computer image processing technology field, more specifically, embodiments of the present invention
Relate to the use of OpenCV and realize a kind of high accuracy, high efficiency, the method for versatile automatic segmentation bill.
Background technology
The financial staff of big companies needs to handle substantial amounts of bill cumbersomely daily, with the lifting of corporate business amount,
Company may be faced with financial staff shortage, business processing not in time the problem of, at this moment we are just needed by computer vision
Middle OCR technique carries out automatic identification and processing.But bill and irregular stickup in scanned copy, using common reimbursement bill as
Example, we often many bills mix and it is irregular be attached on the paper of one or more A4 paper sizes, then to this
A little paper for pasting bill are scanned, then carry out follow-up identifying processing.But the OCR of bill identifications are not with scanned copy
For recognition unit, but a recognition unit is used as using sola bill.Here just need to split using proposed bill
Method, i.e., handled the scanned copy of an A4 paper size, and each bill above is split, and in order to improve
OCR recognition correct rates are, it is necessary to which backed bill deflection angle is as small as possible.
The content of the invention
The purpose of the present invention is for the defects of above-mentioned background technology, there is provided a kind of bill based on OpenCV technologies point
Segmentation method, i.e., based on computer vision technique, bill in automatic segmentation scanned copy is realized by OpenCV.Due to the bill of processing
All it is color image, needs first to carry out the pretreatment of bill piece before being corrected, then carried by edge detection algorithm
The profile information of bill is taken out, the minimum outer rectangular of profile information is then calculated, finally utilizes wherein three of the rectangle
Vertex carries out affine transformation and obtains final " Founder " bill.
In order to reach above-mentioned technique effect, the present invention takes following technical scheme:Bill based on OpenCV technologies point
Segmentation method, comprises the following steps:
Step 1:Picture pretreatment is carried out to scanned copy picture, the pretreatment includes removing scanned copy image content
To make an uproar processing and binary conversion treatment, the denoising includes bilateral filtering, medium filtering carries out smooth, the binary conversion treatment,
The gray-scale map content of picture is specially first obtained, then carries out binary conversion treatment further according to rational threshold value;
Step 2:Edge detection is carried out to scanned copy using Canny operators, obtains bill of the bill in whole picture
Edge line, then obtains its minimum outer rectangular according to bill edge line computation;
Step 3:According to the bill edge line detected and its minimum outer rectangular, the affine transformation in Opencv is utilized
Function is partitioned into sola bill.
Bill dividing method based on OpenCV technologies, its general principles are:Automatic segmentation bill is realized by opencv,
Since the bill of processing is all color image, needs first to carry out the pretreatment of bill piece before being corrected, then pass through
Edge detection algorithm extracts the profile information i.e. bill edge line of bill, then is gone out based on bill edge line computation outside its minimum
Rectangle;The affine transformation based on rectangle vertex is finally utilized to obtain sola bill.
Opencv (Open Source Computer Vision Library) be one based on BSD permitted it is issuable across
Platform computer vision storehouse, may operate in Linux, Windows, Android and Mac OS operating systems.Its lightweight and
And efficiently --- it is made of a series of C functions and a small amount of C++ class, while provides connecing for the language such as Python, Ruby, MATLAB
Mouthful, realize many general-purpose algorithms in terms of image procossing and computer vision.
Edge (edge) refers to that image local intensity changes most significant part.It is primarily present in target and target, target
It is the graphical analyses such as image segmentation, textural characteristics and shape facility between background, region and region (including different color)
Important foundation.In order to which bill is identified from background, it would be desirable to edge detection is used, wherein common edge detection is calculated
Method has:Sobel operators, Roberts operators, Prewitt operators, Laplacian operators, Canny operators.Wherein Soble operators
Image subject and Beijing cannot strictly be separated, Roberts algorithms are not very high to the precision that edge positions, and Prewitt is calculated
Son has noise inhibitory action, but edge detection precision is still inadequate;Laplacian operators because using second dervative,
So the operator has unacceptable sensitiveness to noise;And used Canny operators are suppressing noise in the present invention, and
Edge detection precision has preferable effect.
Further technical solution is:Marginal information point is obtained using Canny edge detections in step 2, is recycled more
Side shape fitting algorithm obtains more complete marginal information to edge fitting.
Further technical solution is:One is obtained to the edge calculations after fitting using function boundingRect (args..)
A complete rectangle frame, i.e., minimum outer rectangular.
Compared with prior art, the present invention with following beneficial effect:Traditional picture segmentation technology is simply by inspection
The edge of target image is surveyed, is then extracted target area using stingy diagram technology, the process and without the concern for angle
Degree problem.Bill images segmentation is but drawn a bill evidence according to edge extracting exactly on the contrary, not requiring nothing more than, it is also necessary to which bill can
" Founder ".Consider that, when splitting bill, we just need to calculate two important informations from operational angle:Marginal information, angle
Information.
Conventional bill cutting techniques go out area-of-interest first with edge extraction, then according to angle information to carrying
The image of taking-up carries out the rotation of an angle, finally just obtains us and wants image.Method proposed by the invention then only needs
Want marginal information to complete the above process, not only save computing resource, also improve the speed of bill processing.
Brief description of the drawings
Fig. 1 is the bill segmentation flow chart of the present invention;
Fig. 2 is scanned copy design sketch;
Fig. 3 is pretreatment denoising effect figure;
Fig. 4 is pretreatment binaryzation design sketch;
Fig. 5 is bill edge detection design sketch in scanned copy;
Fig. 6 is the minimum outer rectangular design sketch of bill edge in scanned copy;
Fig. 7 is that minimum outer rectangular carries out affine transformation schematic diagram;
Fig. 8 is the bill design sketch after cutting.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to
Limit the present invention.
Embodiment:
With reference to figure 1, the bill dividing method based on OpenCV technologies, comprises the following steps:
Step 1:Picture pretreatment is carried out to scanned copy picture, which is included to scanned copy image content
A. denoising, including bilateral filtering, medium filtering carry out smoothly;
B. binary conversion treatment, specially first obtains the gray-scale map content of picture, then carries out two further according to rational threshold value
Value is handled;
Step 2:Edge detection is carried out to scanned copy using Canny operators, obtains position of the bill in whole picture
(Fig. 5 edge lines), then obtains its minimum outer rectangular (Fig. 6 edge lines) according to edge calculations;
Step 3:According to the minimum outer rectangular of the bill edge and edge detected, we utilize imitative in Opencv
Penetrate transforming function transformation function and be partitioned into sola bill, so as to carry out OCR identifying processings to bill behind being more advantageous to.
Make more detailed illustrate below:
OpenCV is used as in the widely applied open source software storehouse of image processing field, there is provided the figure that largely can be used directly
As processing basic skills, such as denoising, conversion, binaryzation, so we to each basic algorithm with regard to without carrying out local reality
It is existing, development efficiency has not only been saved, also can guarantee that higher accuracy.Substantially our common image processing algorithms can be
Corresponding method is found in OpenCV, and according to regulation form input picture, parameter, it is possible to obtain the result that we want.
It is being to be realized using OpenCV to image processing techniques involved in the bill dividing method.
This technology realizes that flow is broadly divided into two essential parts:First input picture is pre-processed, such as denoising,
Regularization etc., this is the indispensable step of image processing field, then recycles us core methed to be carried out to image
Processing, finally obtains desired result.It is specific as follows:
1. picture pre-processes;
With reference to figure 2- Fig. 4, which includes the denoising smooth, gray processing, binaryzation to scanned copy image content.Specifically adopt
With bilateral filtering, medium filtering, both pretreatment filtering modes are relatively conventional in image preprocessing, and effect compared with
It is good, so do not repeat excessively, directly using function bilateralFilter (args..) in OpenCV image procossings storehouse,
MedianBlur (args..) is realized.
2. bill edge detection in scanned copy;
With reference to figure 5 and Fig. 6, which includes edge detection and minimum outer rectangular.Edge detection algorithm species is various, respectively
There are advantage and disadvantage, wherein Canny algorithms have obvious advantage, and are used widely, here using function Canny in OpenCV
(args..).Marginal information point is obtained, recycles polygon approach algorithm approxPolyDP (args..) to intend edge
Close, to obtain more complete marginal information, bill edge at this time very close rectangle;To prevent losing for billing information
Lose, a complete rectangle frame obtain the edge calculations after fitting using boundingRect (args..) --- minimum exterior square
Shape.
3. utilize marginal information segmentation bill;
With reference to figure 7- Fig. 8, which includes carrying out affine transformation to minimum outer rectangular, finally obtains bill images.Such as 7
Shown in figure, there is deflection angle in reimbursement train ticket position on expense report, by previous step outside obtained minimum
Rectangle, including the length and width information of rectangle and deflection angle information.Our target is exactly to split rectangle src from the expense report,
It is understood that affine transformation can not only be translated, can also be rotated, just can be light as long as obtaining corresponding transformation matrix
And easily lift and try to achieve target image dst.On three vertex of known rectangular aspect, three vertex of original rectangular and target rectangle,
We are with regard to that can try to achieve affine transformation matrix
The method is related to the edge detection to scanned copy, splits accuracy to improve bill edge detection and bill, builds
View carries out bill stickup using the A4 paper high with bill color contrast as far as possible in the specific implementation.
Although reference be made herein to invention has been described for explanatory embodiment of the invention, however, it is to be understood that ability
Field technique personnel can be designed that a lot of other modifications and embodiment, these modifications and embodiment will fall in the application public affairs
Within the spirit and spirit opened.More specifically, can be to the group of theme combination layout in the range of disclosure
A variety of variations and modifications are carried out into component and/or layout.In addition to the variations and modifications carried out to building block and/or layout,
To those skilled in the art, other purposes also will be apparent.
Claims (3)
1. the bill dividing method based on OpenCV technologies, it is characterised in that comprise the following steps:
Step 1:Picture pretreatment is carried out to scanned copy picture, the pretreatment is included at the denoising to scanned copy image content
Reason and binary conversion treatment, the denoising includes bilateral filtering, medium filtering carries out smooth, the binary conversion treatment, specifically
First to obtain the gray-scale map content of picture, then binary conversion treatment is carried out further according to rational threshold value;
Step 2:Edge detection is carried out to scanned copy using Canny operators, obtains bill edge of the bill in whole picture
Line, then obtains its minimum outer rectangular according to bill edge line computation;
Step 3:According to the bill edge line detected and its minimum outer rectangular, the affine transformation function in Opencv is utilized
It is partitioned into sola bill.
2. the bill dividing method according to claim 1 based on OpenCV technologies, it is characterised in that:Adopted in step 2
Marginal information point is obtained with Canny edge detections, recycles polygon approach algorithm to obtain more complete side to edge fitting
Edge information.
3. the bill dividing method according to claim 2 based on OpenCV technologies, it is characterised in that:Using function
BoundingRect (args..) obtains the edge calculations after fitting one complete rectangle frame, i.e., minimum outer rectangular.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711046410.XA CN107945194A (en) | 2017-10-31 | 2017-10-31 | Bill dividing method based on OpenCV technologies |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711046410.XA CN107945194A (en) | 2017-10-31 | 2017-10-31 | Bill dividing method based on OpenCV technologies |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107945194A true CN107945194A (en) | 2018-04-20 |
Family
ID=61936018
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711046410.XA Pending CN107945194A (en) | 2017-10-31 | 2017-10-31 | Bill dividing method based on OpenCV technologies |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107945194A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109064304A (en) * | 2018-08-03 | 2018-12-21 | 四川长虹电器股份有限公司 | Finance reimbursement bill automated processing system and method |
CN109460762A (en) * | 2018-10-19 | 2019-03-12 | 南京理工大学 | A kind of answering card methods of marking based on image recognition |
CN109657665A (en) * | 2018-10-31 | 2019-04-19 | 广东工业大学 | A kind of invoice batch automatic recognition system based on deep learning |
CN109740548A (en) * | 2019-01-08 | 2019-05-10 | 北京易道博识科技有限公司 | A kind of reimbursement bill images dividing method and system |
CN110288655A (en) * | 2019-06-28 | 2019-09-27 | 深圳市同为数码科技股份有限公司 | The method and device of test pattern position in a kind of automatic identification chart picture |
CN110322395A (en) * | 2019-06-18 | 2019-10-11 | 电子科技大学中山学院 | Part outline shape detection method and device based on image processing and affine transformation |
CN110400321A (en) * | 2019-07-26 | 2019-11-01 | 广东工业大学 | The extracting method of leather material profile based on machine vision and actual size |
CN110427932A (en) * | 2019-08-02 | 2019-11-08 | 杭州睿琪软件有限公司 | The method and device of multiple document fields in a kind of identification image |
CN111062317A (en) * | 2019-12-16 | 2020-04-24 | 中国计量大学上虞高等研究院有限公司 | Method and system for cutting edges of scanned document |
WO2020248497A1 (en) * | 2019-06-12 | 2020-12-17 | 平安科技(深圳)有限公司 | Picture scanning document processing method and apparatus, computer device, and storage medium |
CN112801098A (en) * | 2019-11-14 | 2021-05-14 | 临沂市拓普网络股份有限公司 | Contour technology-based mathematical symbol identification method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20080101058A (en) * | 2007-05-15 | 2008-11-21 | 엘지엔시스(주) | Apparatus for media recognition and method for media access direction estimating with the same |
CN102930265A (en) * | 2012-09-19 | 2013-02-13 | 广州市中崎商业机器有限公司 | Method and device for scanning multiple identity cards |
CN104112128A (en) * | 2014-06-19 | 2014-10-22 | 中国工商银行股份有限公司 | Digital image processing system applied to bill image character recognition and method |
CN104981105A (en) * | 2015-07-09 | 2015-10-14 | 广东工业大学 | Detecting and error-correcting method capable of rapidly and accurately obtaining element center and deflection angle |
CN104990926A (en) * | 2015-06-25 | 2015-10-21 | 哈尔滨工业大学 | TR element locating and defect detecting method based on vision |
CN107169488A (en) * | 2017-05-03 | 2017-09-15 | 四川长虹电器股份有限公司 | A kind of correction system and antidote of bill scan image |
-
2017
- 2017-10-31 CN CN201711046410.XA patent/CN107945194A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20080101058A (en) * | 2007-05-15 | 2008-11-21 | 엘지엔시스(주) | Apparatus for media recognition and method for media access direction estimating with the same |
CN102930265A (en) * | 2012-09-19 | 2013-02-13 | 广州市中崎商业机器有限公司 | Method and device for scanning multiple identity cards |
CN104112128A (en) * | 2014-06-19 | 2014-10-22 | 中国工商银行股份有限公司 | Digital image processing system applied to bill image character recognition and method |
CN104990926A (en) * | 2015-06-25 | 2015-10-21 | 哈尔滨工业大学 | TR element locating and defect detecting method based on vision |
CN104981105A (en) * | 2015-07-09 | 2015-10-14 | 广东工业大学 | Detecting and error-correcting method capable of rapidly and accurately obtaining element center and deflection angle |
CN107169488A (en) * | 2017-05-03 | 2017-09-15 | 四川长虹电器股份有限公司 | A kind of correction system and antidote of bill scan image |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109064304A (en) * | 2018-08-03 | 2018-12-21 | 四川长虹电器股份有限公司 | Finance reimbursement bill automated processing system and method |
CN109460762A (en) * | 2018-10-19 | 2019-03-12 | 南京理工大学 | A kind of answering card methods of marking based on image recognition |
CN109460762B (en) * | 2018-10-19 | 2022-05-06 | 南京理工大学 | Answer sheet scoring method based on image recognition |
CN109657665A (en) * | 2018-10-31 | 2019-04-19 | 广东工业大学 | A kind of invoice batch automatic recognition system based on deep learning |
CN109657665B (en) * | 2018-10-31 | 2023-01-20 | 广东工业大学 | Invoice batch automatic identification system based on deep learning |
CN109740548A (en) * | 2019-01-08 | 2019-05-10 | 北京易道博识科技有限公司 | A kind of reimbursement bill images dividing method and system |
WO2020248497A1 (en) * | 2019-06-12 | 2020-12-17 | 平安科技(深圳)有限公司 | Picture scanning document processing method and apparatus, computer device, and storage medium |
CN110322395A (en) * | 2019-06-18 | 2019-10-11 | 电子科技大学中山学院 | Part outline shape detection method and device based on image processing and affine transformation |
CN110288655B (en) * | 2019-06-28 | 2021-06-15 | 深圳市同为数码科技股份有限公司 | Method and device for automatically identifying position of test pattern in chart picture |
CN110288655A (en) * | 2019-06-28 | 2019-09-27 | 深圳市同为数码科技股份有限公司 | The method and device of test pattern position in a kind of automatic identification chart picture |
CN110400321A (en) * | 2019-07-26 | 2019-11-01 | 广东工业大学 | The extracting method of leather material profile based on machine vision and actual size |
CN110427932A (en) * | 2019-08-02 | 2019-11-08 | 杭州睿琪软件有限公司 | The method and device of multiple document fields in a kind of identification image |
CN112801098A (en) * | 2019-11-14 | 2021-05-14 | 临沂市拓普网络股份有限公司 | Contour technology-based mathematical symbol identification method |
CN112801098B (en) * | 2019-11-14 | 2023-01-10 | 临沂市拓普网络股份有限公司 | Contour technology-based mathematical symbol identification method |
CN111062317A (en) * | 2019-12-16 | 2020-04-24 | 中国计量大学上虞高等研究院有限公司 | Method and system for cutting edges of scanned document |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107945194A (en) | Bill dividing method based on OpenCV technologies | |
Gandhi et al. | Preprocessing of non-symmetrical images for edge detection | |
CN104361336A (en) | Character recognition method for underwater video images | |
CN107169488A (en) | A kind of correction system and antidote of bill scan image | |
Shen et al. | Improving OCR performance with background image elimination | |
CN107491730A (en) | A kind of laboratory test report recognition methods based on image procossing | |
CN103208004A (en) | Automatic recognition and extraction method and device for bill information area | |
WO2017012581A1 (en) | Method and system for decoding qr code based on weighted average grey method | |
CN105374015A (en) | Binary method for low-quality document image based on local contract and estimation of stroke width | |
Chen et al. | Shadow-based Building Detection and Segmentation in High-resolution Remote Sensing Image. | |
Harraj et al. | OCR accuracy improvement on document images through a novel pre-processing approach | |
CN110119741A (en) | A kind of card card image information recognition methods having powerful connections | |
CN113160257A (en) | Image data labeling method and device, electronic equipment and storage medium | |
CN110674812B (en) | Civil license plate positioning and character segmentation method facing complex background | |
US11263752B2 (en) | Computer-implemented method of detecting foreign object on background object in an image, apparatus for detecting foreign object on background object in an image, and computer-program product | |
Shedlovska et al. | Shadow detection and removal using a shadow formation model | |
CN113505702A (en) | Pavement disease identification method and system based on double neural network optimization | |
CN115272306A (en) | Solar cell panel grid line enhancement method utilizing gradient operation | |
CN110533049B (en) | Method and device for extracting seal image | |
CN112364863B (en) | Character positioning method and system for license document | |
Salunkhe et al. | Recognition of multilingual text from signage boards | |
Lai et al. | Binarization by local k-means clustering for Korean text extraction | |
Nomura et al. | Morphological preprocessing method to thresholding degraded word images | |
Gun et al. | A contour detector with improved corner detection | |
Jin et al. | Towards an automatic system for road lane marking extraction in large-scale aerial images acquired over rural areas by hierarchical image analysis and Gabor filter |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180420 |