CN106407980A - Image processing-based bank card number recognition method - Google Patents
Image processing-based bank card number recognition method Download PDFInfo
- Publication number
- CN106407980A CN106407980A CN201610972053.9A CN201610972053A CN106407980A CN 106407980 A CN106407980 A CN 106407980A CN 201610972053 A CN201610972053 A CN 201610972053A CN 106407980 A CN106407980 A CN 106407980A
- Authority
- CN
- China
- Prior art keywords
- bank card
- character
- vertical
- horizontal
- bank
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Character Input (AREA)
Abstract
The present invention discloses an image processing-based bank card number recognition method and belongs to the image processing technical field. According to the image processing-based bank card number recognition method, effective correction processing is performed on a bank card image, and then, character segmentation and character recognition are performed, and therefore, final accuracy can be greatly improved. The method includes the following steps of: 1, bank card segmentation; 2, character area coarse positioning; 3, character segmentation; and 4, character recognition. The method of the present invention can be not only applied to bank card identification, but also applied to identity card identification, driver's license identification, driving license identification and the like.
Description
Technical field
Present invention relates particularly to a kind of bank card number identification method based on image procossing, belong to image processing techniques neck
Domain.
Background technology
Currently, with machine learning, the development of depth learning technology, drive the development of every field, especially in gold
Melt field, be previously required to some information of manual typing, such as ID card information, bank card number information etc., now with skill
The development of art, can be realized automatic input, is greatlyd save manpower and time cost, also improve simultaneously using image photographic identification
The accuracy rate of typing.
Currently there are no the technical scheme of complete set to identify bank card number, prior art generally existing discrimination is low
Problem.
Content of the invention
Therefore, for the above-mentioned deficiency of prior art, the present invention is all providing a kind of bank's card number based on image procossing
Code recognition methods, by carrying out effective correction process to bank's card graphic, then does Character segmentation and character recognition, significantly again
Improve final accuracy rate.
The bank card number identification method based on image procossing that the present invention provides, comprises the following steps,
Step 1 bank card cutting
By edge detection algorithm, find the four edges boundary line of bank card, then navigate to four sides of bank's card graphic
Boundary's point, does perspective transform according to this four points, and bank card correct image is processed;
Step 2 character zone coarse positioning
For the bank's card graphic after correction, the position occurring according to character string, a rectangular area is set, in this area
Adopt canny edge detection algorithm, the horizontal and vertical marginal information in detection zone in domain, find marginal information the abundantest
Region is as further Character segmentation region;
Step 3 Character segmentation
The character zone being determined based on step 2, using sobel vertical edge detection algorithm, detects the vertical edge of character
Information, is then directed to different bank card types, arranges different templates, each template is partitioned into a character string;
Step 4 character recognition
Character is normalized, extracts the gabor feature of character, LDA dimensionality reduction is carried out to gabor feature, then
Carry out match cognization with template in storehouse.
Further, pass through edge detection algorithm in step 1, the four edges boundary line finding bank card is specifically, adopt base
In the method for gray scale difference value, first look for the gradient of horizontal direction, by line search, threshold value T_Hor is set, differentiates each pixel
Two points up and down pixel value, if the absolute value of difference be more than T_Hor threshold value, horizontal edge figure is set to 1,
It is otherwise provided as 0, vertical edge figure is regenerated using identical method, Hough transformation side is adopted on horizontal and vertical edge graph
Method finds horizontal and vertical line segment, chooses two from horizontal and vertical line segment respectively, combined horizontal and vertical segment, generates silver
Row card region, the result choosing the maximum region of area as four edges circle of bank card exports.
The beneficial effects of the present invention is:The bank card Number Reorganization side based on image procossing that patent of the present invention provides
Method, by bank card pretreatment and the correction process of early stage, is effectively increased the accuracy rate of subsequent singulation and identification step, word
Symbol segmentation step employs the method based on multi-template matching, effectively raises the segmentation accuracy rate of dissimilar bank card.
The present invention cannot be only used for bank card identification, can be applied equally to identity card identification, driver's license, the application such as driving license identification
In.
Brief description
Fig. 1 is a kind of schematic diagram of the bank card number identification method based on image procossing of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawings the specific embodiment of the present invention is illustrated:
The present invention is to solve the problems, such as that prior art bank card Number Reorganization rate is low to design, its general principle such as Fig. 1 institute
Show, the present invention is included based on the step of the bank card number identification method of image procossing,
Step 1 bank card cutting
By edge detection algorithm, find the four edges boundary line of bank card, then navigate to four sides of bank's card graphic
Boundary's point, does perspective transform according to this four points, and bank card correct image is processed;
Step 2 character zone coarse positioning
For the bank's card graphic after correction, the position occurring according to character string, a rectangular area is set, in this area
Adopt canny edge detection algorithm, the horizontal and vertical marginal information in detection zone in domain, find marginal information the abundantest
Region is as further Character segmentation region;
Step 3 Character segmentation
The character zone being determined based on step 2, using sobel vertical edge detection algorithm, detects the vertical edge of character
Information, is then directed to different bank card types, arranges different templates, each template is partitioned into a character string;
Step 4 character recognition
Character is normalized, extracts the gabor feature of character, LDA dimensionality reduction is carried out to gabor feature, then
Carry out match cognization with template in storehouse.
Wherein, passing through edge detection algorithm in step 1, finding the four edges boundary line of bank card specifically, adopting based on ash
The method of degree difference, first looks for the gradient of horizontal direction, by line search, arranges threshold value T_Hor, differentiates the upper of each pixel
The pixel value of lower two points, if the absolute value of difference is more than T_Hor threshold value, horizontal edge figure is set to 1, otherwise
It is set to 0, vertical edge figure is regenerated using identical method, horizontal and vertical edge graph is sought using Hough transformation method
The gentle vertical segment of water detection, chooses two from horizontal and vertical line segment respectively, combined horizontal and vertical segment, generates bank card
Region, the result choosing the maximum region of area as four edges circle of bank card exports.
The recognition methods of the present invention, by bank card pretreatment and the correction process of early stage, is effectively increased follow-up point
Cut the accuracy rate with identification step, Character segmentation step employs the method based on multi-template matching, effectively raises difference
The segmentation accuracy rate of type bank card.The present invention cannot be only used for bank card identification, can be applied equally to identity card identification, drives
Sail in the applications such as card, driving license identification.
The above is the preferred embodiment of the present invention it is noted that for those skilled in the art
For, on the premise of without departing from principle of the present invention, some improvements and modifications can also be made, these improvements and modifications
Should be regarded as protection scope of the present invention.
Claims (2)
1. a kind of bank card number identification method based on image procossing is it is characterised in that the method comprising the steps of,
Step 1 bank card cutting
By edge detection algorithm, find the four edges boundary line of bank card, then navigate to four boundary points of bank's card graphic,
Do perspective transform according to this four points, bank card correct image is processed;
Step 2 character zone coarse positioning
For the bank's card graphic after correction, the position occurring according to character string, a rectangular area is set, in this region
Using canny edge detection algorithm, the horizontal and vertical marginal information in detection zone, find marginal information region the abundantest
As further Character segmentation region;
Step 3 Character segmentation
The character zone being determined based on step 2, using sobel vertical edge detection algorithm, detects the vertical edge information of character,
Then it is directed to different bank card types, different templates are set, each template is partitioned into a character string;
Step 4 character recognition
Character is normalized, extracts the gabor feature of character, LDA dimensionality reduction is carried out to gabor feature, then with storehouse
Middle template carries out match cognization.
2. the bank card number identification method based on image procossing as claimed in claim 1 is it is characterised in that lead in step 1
Crossing edge detection algorithm, finding the four edges boundary line of bank card specifically, using the method based on gray scale difference value, first looking for water
Square to gradient, by line search, threshold value T_Hor is set, differentiates the pixel value of two points up and down of each pixel, such as
The absolute value of fruit difference is more than T_Hor threshold value, then be set to 1 on horizontal edge figure, be otherwise provided as 0, using identical method
Regeneration vertical edge figure, adopts Hough transformation method to find horizontal and vertical line segment, from water on horizontal and vertical edge graph
Two are chosen respectively in gentle vertical segment, combined horizontal and vertical segment, generate bank card region, choose the maximum area of area
Domain exports as the result of four edges circle of bank card.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610972053.9A CN106407980A (en) | 2016-11-03 | 2016-11-03 | Image processing-based bank card number recognition method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610972053.9A CN106407980A (en) | 2016-11-03 | 2016-11-03 | Image processing-based bank card number recognition method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106407980A true CN106407980A (en) | 2017-02-15 |
Family
ID=58015024
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610972053.9A Pending CN106407980A (en) | 2016-11-03 | 2016-11-03 | Image processing-based bank card number recognition method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106407980A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107247950A (en) * | 2017-06-06 | 2017-10-13 | 电子科技大学 | A kind of ID Card Image text recognition method based on machine learning |
CN107657230A (en) * | 2017-09-27 | 2018-02-02 | 安徽硕威智能科技有限公司 | A kind of bank self-help robot character recognition device |
CN108427946A (en) * | 2018-03-16 | 2018-08-21 | 福州大学 | The driver's license detection recognition method being laid out based on interior feature and textview field under complex scene |
CN109447059A (en) * | 2018-09-21 | 2019-03-08 | 澳新银行营运服务(成都)有限公司 | A kind of bank card number recognition methods and device |
CN109460767A (en) * | 2018-10-23 | 2019-03-12 | 福州大学 | Rule-based convex print bank card number segmentation and recognition methods |
CN109685074A (en) * | 2018-10-17 | 2019-04-26 | 福州大学 | A kind of bank card number row localization method based on Scharr operator |
CN109886274A (en) * | 2019-03-25 | 2019-06-14 | 山东浪潮云信息技术有限公司 | Social security card identification method and system based on opencv and deep learning |
CN110119741A (en) * | 2019-04-08 | 2019-08-13 | 浙江大学宁波理工学院 | A kind of card card image information recognition methods having powerful connections |
CN111915816A (en) * | 2020-06-03 | 2020-11-10 | 中国建设银行股份有限公司 | Card-swallowing retrieving method and device, electronic equipment and computer-readable storage medium |
CN112507759A (en) * | 2019-09-16 | 2021-03-16 | ***股份有限公司 | Image processing method and image processing device for identifying bank card |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101751785A (en) * | 2010-01-12 | 2010-06-23 | 杭州电子科技大学 | Automatic license plate recognition method based on image processing |
CN101937508B (en) * | 2010-09-30 | 2012-07-04 | 湖南大学 | License plate localization and identification method based on high-definition image |
CN104573616A (en) * | 2013-10-29 | 2015-04-29 | 腾讯科技(深圳)有限公司 | Information identification method and related device and system |
CN104680161A (en) * | 2015-01-09 | 2015-06-03 | 安徽清新互联信息科技有限公司 | Digit recognition method for identification cards |
CN104065639B (en) * | 2013-11-06 | 2015-07-29 | 腾讯科技(深圳)有限公司 | The binding method of bank card and system |
CN104966107A (en) * | 2015-07-10 | 2015-10-07 | 安徽清新互联信息科技有限公司 | Credit card card-number identification method based on machine learning |
CN105139009A (en) * | 2015-07-10 | 2015-12-09 | 安徽清新互联信息科技有限公司 | Credit card number identification method based on edge characteristics |
-
2016
- 2016-11-03 CN CN201610972053.9A patent/CN106407980A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101751785A (en) * | 2010-01-12 | 2010-06-23 | 杭州电子科技大学 | Automatic license plate recognition method based on image processing |
CN101937508B (en) * | 2010-09-30 | 2012-07-04 | 湖南大学 | License plate localization and identification method based on high-definition image |
CN104573616A (en) * | 2013-10-29 | 2015-04-29 | 腾讯科技(深圳)有限公司 | Information identification method and related device and system |
CN104065639B (en) * | 2013-11-06 | 2015-07-29 | 腾讯科技(深圳)有限公司 | The binding method of bank card and system |
CN104680161A (en) * | 2015-01-09 | 2015-06-03 | 安徽清新互联信息科技有限公司 | Digit recognition method for identification cards |
CN104966107A (en) * | 2015-07-10 | 2015-10-07 | 安徽清新互联信息科技有限公司 | Credit card card-number identification method based on machine learning |
CN105139009A (en) * | 2015-07-10 | 2015-12-09 | 安徽清新互联信息科技有限公司 | Credit card number identification method based on edge characteristics |
Non-Patent Citations (1)
Title |
---|
水天一: "基于移动电话的******识别研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107247950A (en) * | 2017-06-06 | 2017-10-13 | 电子科技大学 | A kind of ID Card Image text recognition method based on machine learning |
CN107657230A (en) * | 2017-09-27 | 2018-02-02 | 安徽硕威智能科技有限公司 | A kind of bank self-help robot character recognition device |
CN108427946B (en) * | 2018-03-16 | 2021-11-26 | 福州大学 | Driver license detection and identification method based on internal features and text field layout in complex scene |
CN108427946A (en) * | 2018-03-16 | 2018-08-21 | 福州大学 | The driver's license detection recognition method being laid out based on interior feature and textview field under complex scene |
CN109447059A (en) * | 2018-09-21 | 2019-03-08 | 澳新银行营运服务(成都)有限公司 | A kind of bank card number recognition methods and device |
CN109685074A (en) * | 2018-10-17 | 2019-04-26 | 福州大学 | A kind of bank card number row localization method based on Scharr operator |
CN109685074B (en) * | 2018-10-17 | 2022-05-10 | 福州大学 | Bank card number row positioning method based on Scharr operator |
CN109460767A (en) * | 2018-10-23 | 2019-03-12 | 福州大学 | Rule-based convex print bank card number segmentation and recognition methods |
CN109886274A (en) * | 2019-03-25 | 2019-06-14 | 山东浪潮云信息技术有限公司 | Social security card identification method and system based on opencv and deep learning |
CN110119741A (en) * | 2019-04-08 | 2019-08-13 | 浙江大学宁波理工学院 | A kind of card card image information recognition methods having powerful connections |
CN110119741B (en) * | 2019-04-08 | 2022-09-27 | 浙江大学宁波理工学院 | Card image information identification method with background |
CN112507759A (en) * | 2019-09-16 | 2021-03-16 | ***股份有限公司 | Image processing method and image processing device for identifying bank card |
CN111915816A (en) * | 2020-06-03 | 2020-11-10 | 中国建设银行股份有限公司 | Card-swallowing retrieving method and device, electronic equipment and computer-readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106407980A (en) | Image processing-based bank card number recognition method | |
WO2019169532A1 (en) | License plate recognition method and cloud system | |
CN104751142B (en) | A kind of natural scene Method for text detection based on stroke feature | |
CN102833638B (en) | Automatic video segmentation and annotation method and system based on caption information | |
CN104252620B (en) | The graphical verification code recognition methods of Characters Stuck | |
CN106940799A (en) | Method for processing text images and device | |
CN110598686B (en) | Invoice identification method, system, electronic equipment and medium | |
CN104361336A (en) | Character recognition method for underwater video images | |
CN105426890B (en) | A kind of graphical verification code recognition methods of character distortion adhesion | |
CN107766854B (en) | Method for realizing rapid page number identification based on template matching | |
CN105279506A (en) | Manchu script central axis positioning method | |
CN102663378A (en) | Method for indentifying joined-up handwritten characters | |
CN111401312A (en) | PDF drawing character recognition method, system and equipment | |
CN109086772A (en) | A kind of recognition methods and system distorting adhesion character picture validation code | |
Ali et al. | An efficient character segmentation algorithm for recognition of Arabic handwritten script | |
Mammeri et al. | Road-sign text recognition architecture for intelligent transportation systems | |
CN105404868A (en) | Interaction platform based method for rapidly detecting text in complex background | |
Rajakumar et al. | Eighth century Tamil consonants recognition from stone inscriptions | |
Asad et al. | High performance OCR for camera-captured blurred documents with LSTM networks | |
CN110942063B (en) | Certificate text information acquisition method and device and electronic equipment | |
Hu et al. | A 2D barcode extraction method based on texture direction analysis | |
Ali et al. | A new design based-fusion of features to recognize Arabic handwritten characters | |
Rajithkumar et al. | Template matching method for recognition of stone inscripted Kannada characters of different time frames based on correlation analysis | |
CN109034149A (en) | A kind of character identifying method and device | |
Jia et al. | Segmenting characters from license plate images with little prior knowledge |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170215 |
|
RJ01 | Rejection of invention patent application after publication |