CN107451569A - A kind of automatic identification and the method for cutting bill in scanned copy - Google Patents
A kind of automatic identification and the method for cutting bill in scanned copy Download PDFInfo
- Publication number
- CN107451569A CN107451569A CN201710660780.6A CN201710660780A CN107451569A CN 107451569 A CN107451569 A CN 107451569A CN 201710660780 A CN201710660780 A CN 201710660780A CN 107451569 A CN107451569 A CN 107451569A
- Authority
- CN
- China
- Prior art keywords
- bill
- scanned copy
- profile
- scanned
- automatic identification
- 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 26
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000002146 bilateral effect Effects 0.000 claims description 3
- 230000001427 coherent effect Effects 0.000 claims description 3
- 239000000463 material Substances 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Classifications
-
- 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
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/414—Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Editing Of Facsimile Originals (AREA)
Abstract
The present invention relates to computer graphics disposal technology, it discloses a kind of automatic identification and the method that cuts bill in scanned copy, the efficiency for solving to bring bill scanned copy using artificial treatment mode in conventional art is low, the problem of increasing human and material resources input cost.This method comprises the following steps:A. bill scanned copy is pre-processed;B. the edge of the bill images in bill scanned copy is detected;C. bill is cut from scanned copy according to the edge of the bill images of detection.The present invention be applied to from bill scanned copy quickly, accurately cut out bill.
Description
Technical field
The present invention relates to computer graphics disposal technology, and in particular to a kind of automatic identification simultaneously cuts bill in scanned copy
Method.
Background technology
Current many processing to bill, are all to be carried out according to the scan-image part of bill, because in terms of business
Demand and the daily custom of financial staff, people many bills are mixed when bill book keeping operation reimbursement is carried out, often and
It is irregular to be attached on the paper of one or more A4 paper sizes, then the paper of these stickup bills is scanned, then
These scanned copies are further processed.
In conventional art, the processing for these bill scanned copies is all manually progress frame choosing, is then cut, this
Sample increases the process cycle time, and efficiency is low, also increases human and material resources input cost.
The content of the invention
The technical problems to be solved by the invention are:A kind of automatic identification and the method for cutting bill in scanned copy are proposed,
The efficiency for solving to bring bill scanned copy using artificial treatment mode in conventional art is low, increase human and material resources input into
This problem of.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of automatic identification and the method for cutting bill in scanned copy, comprise the following steps:
A. bill scanned copy is pre-processed;
B. the edge of the bill images in bill scanned copy is detected;
C. bill is cut from scanned copy according to the edge of the bill images of detection;
Step a, step b and step c is automatic business processing step.
Optimize as further, in step a, the pretreatment includes:Denoising, binaryzation, content linear, lines expansion
Processing;
Wherein, denoising includes carrying out bilateral filtering and medium filtering to picture, removes noise;
After binary conversion treatment is obtains the gray-scale map content of picture, gray-scale map is carried out at binaryzation according to the threshold value of setting
Reason;
Content linear processing is to carry out linear profile processing to picture using Canny algorithms;
Lines expansion process is to carry out expansion process to current lines of outline so that current line is more coherent and clear
It is clear.
Optimize as further, in step b, the edge of the bill images in the detection bill scanned copy, specifically include:
All existing continuous profile set in bill images are extracted, too small and excessive wheel is then removed from the set
Exterior feature, the in-profile completely included by other profiles is then removed, remaining in set is exactly bill profile, afterwards to these tickets
Rectangle approximation process is carried out according to profile, obtains the rectangular profile of all bills.
As further optimization, the bill scanned copy be bill is attached to be scanned on colored A4 paper after obtain sweep
Retouch part.
The beneficial effects of the invention are as follows:
By to the bill images automatic identification in bill scanned copy and cutting, reducing manual intervention, can not only improve
Treatment effeciency, human and material resources input cost can also be reduced, while reduce error probability.
Embodiment
The present invention is directed to propose a kind of automatic identification and the method for cutting bill in scanned copy, are solved in conventional art to ticket
The efficiency brought according to scanned copy using artificial treatment mode is low, the problem of increasing human and material resources input cost.
Automatic identification in the present invention and the method for cutting bill in scanned copy, including implemented below step:
1st, bill scanned copy is pre-processed;
In specific implementation, in this step, in order to which noise jamming is reduced or eliminated, identification probability is improved, using denoising, two
Value, content linear, the means of lines expansion process pre-process to bill scanned copy;
Wherein denoising includes carrying out bilateral filtering and medium filtering to picture, removes noise;
After binary conversion treatment is obtains the gray-scale map content of picture, gray-scale map is carried out at binaryzation according to the threshold value of setting
Reason;
Content linear processing is to carry out linear profile processing to picture using Canny algorithms;
Lines expansion process is to carry out expansion process to current lines of outline so that current line is more coherent and clear
It is clear.
If be scanned it should be noted that physical tickets are attached on colored A4 paper, obtained bill scanned copy is carried on the back
Scenery and ticket contents difference are bigger, can so greatly improve bank slip recognition and the accuracy cut.
2nd, the edge of the bill images in bill scanned copy is detected;
In specific implementation, in this step, bill edge in scanned copy is detected, extracts all existing continuous profile collection
Close, too small and excessive profile is then removed from the set, then removes the in-profile completely included by other profiles, collect
Remaining in conjunction is exactly bill profile, left back to carry out rectangle approximation process to these bill profiles, obtains the rectangle of all bills
Profile, to carry out cutting processing in next step.
3rd, bill is cut from scanned copy according to the edge of the bill images of detection;
In specific implementation, in this step, according to the bill rectangular profile detected, scanned copy content is cut,
Finally give the bill picture cut.
Claims (4)
1. a kind of automatic identification and the method for cutting bill in scanned copy, it is characterised in that comprise the following steps:
A. bill scanned copy is pre-processed;
B. the edge of the bill images in bill scanned copy is detected;
C. bill is cut from scanned copy according to the edge of the bill images of detection;
Step a, step b and step c is automatic business processing step.
2. a kind of automatic identification as claimed in claim 1 and the method for cutting bill in scanned copy, it is characterised in that step a
In, the pretreatment includes:Denoising, binaryzation, content linear, lines expansion process;
Wherein, denoising includes carrying out bilateral filtering and medium filtering to picture, removes noise;
After binary conversion treatment is obtains the gray-scale map content of picture, binary conversion treatment is carried out to gray-scale map according to the threshold value of setting;
Content linear processing is to carry out linear profile processing to picture using Canny algorithms;
Lines expansion process is to carry out expansion process to current lines of outline so that current line is more coherent and clear.
3. a kind of automatic identification as claimed in claim 1 and the method for cutting bill in scanned copy, it is characterised in that step b
In, the edge of the bill images in the detection bill scanned copy, specifically include:
All existing continuous profile set in bill images are extracted, too small and excessive profile is then removed from the set,
Then the in-profile completely included by other profiles is removed, remaining in set is exactly bill profile, afterwards to these bills
Profile carries out rectangle approximation process, obtains the rectangular profile of all bills.
4. a kind of automatic identification as described in claim 1-3 any one and the method for cutting bill in scanned copy, its feature
Be, the bill scanned copy be bill is attached to be scanned on colored A4 paper after the scanned copy that obtains.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710660780.6A CN107451569A (en) | 2017-08-04 | 2017-08-04 | A kind of automatic identification and the method for cutting bill in scanned copy |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710660780.6A CN107451569A (en) | 2017-08-04 | 2017-08-04 | A kind of automatic identification and the method for cutting bill in scanned copy |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107451569A true CN107451569A (en) | 2017-12-08 |
Family
ID=60490458
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710660780.6A Pending CN107451569A (en) | 2017-08-04 | 2017-08-04 | A kind of automatic identification and the method for cutting bill in scanned copy |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107451569A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110189348A (en) * | 2019-05-29 | 2019-08-30 | 北京达佳互联信息技术有限公司 | Head portrait processing method, device, computer equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103034848A (en) * | 2012-12-19 | 2013-04-10 | 方正国际软件有限公司 | Identification method of form type |
CN103208004A (en) * | 2013-03-15 | 2013-07-17 | 北京英迈杰科技有限公司 | Automatic recognition and extraction method and device for bill information area |
CN103679638A (en) * | 2013-12-25 | 2014-03-26 | 广州广电运通金融电子股份有限公司 | Correction method for incomplete or deformed quadrangular image |
US8837806B1 (en) * | 2010-06-08 | 2014-09-16 | United Services Automobile Association (Usaa) | Remote deposit image inspection apparatuses, methods and systems |
CN104851085A (en) * | 2014-02-17 | 2015-08-19 | 征图新视(江苏)科技有限公司 | Method and system automatically obtaining detection zone in image |
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
- 2017-08-04 CN CN201710660780.6A patent/CN107451569A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8837806B1 (en) * | 2010-06-08 | 2014-09-16 | United Services Automobile Association (Usaa) | Remote deposit image inspection apparatuses, methods and systems |
CN103034848A (en) * | 2012-12-19 | 2013-04-10 | 方正国际软件有限公司 | Identification method of form type |
CN103208004A (en) * | 2013-03-15 | 2013-07-17 | 北京英迈杰科技有限公司 | Automatic recognition and extraction method and device for bill information area |
CN103679638A (en) * | 2013-12-25 | 2014-03-26 | 广州广电运通金融电子股份有限公司 | Correction method for incomplete or deformed quadrangular image |
CN104851085A (en) * | 2014-02-17 | 2015-08-19 | 征图新视(江苏)科技有限公司 | Method and system automatically obtaining detection zone in image |
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 (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110189348A (en) * | 2019-05-29 | 2019-08-30 | 北京达佳互联信息技术有限公司 | Head portrait processing method, device, computer equipment and storage medium |
CN110189348B (en) * | 2019-05-29 | 2020-12-25 | 北京达佳互联信息技术有限公司 | Head portrait processing method and device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9619872B1 (en) | Systems and methods for removing defects from images | |
Pratikakis et al. | ICDAR 2013 document image binarization contest (DIBCO 2013) | |
CN107945194A (en) | Bill dividing method based on OpenCV technologies | |
CN104299009B (en) | License plate character recognition method based on multi-feature fusion | |
Harraj et al. | OCR accuracy improvement on document images through a novel pre-processing approach | |
CN105374015A (en) | Binary method for low-quality document image based on local contract and estimation of stroke width | |
CN103824373B (en) | A kind of bill images amount of money sorting technique and system | |
CN105588845A (en) | Weld defect characteristic parameter extraction method | |
Jain et al. | Indian currency denomination identification using image processing technique | |
CN107169488A (en) | A kind of correction system and antidote of bill scan image | |
Khodadadi et al. | Text localization, extraction and inpainting in color images | |
CN102645436B (en) | Engineering ceramic grinding surface damage detection method based on grinding grain removal technology | |
CN103679678A (en) | Semi-automatic splicing recovery method for character characteristic rectangular scraps of paper | |
CN103824091A (en) | Vehicle license plate recognition method for intelligent transportation system | |
Lazrus et al. | An efficient method of vehicle number plate detection and recognition | |
CN102073872B (en) | Image-based method for identifying shape of parasite egg | |
CN107195069A (en) | A kind of RMB crown word number automatic identifying method | |
CN113191348B (en) | Template-based text structured extraction method and tool | |
CN101706959A (en) | Method for extracting surface defects of metal sheets and strips on basis of two-dimensional information entropy | |
CN102956029A (en) | Image processing apparatus, image processing method | |
CN105303363A (en) | Data processing method and data processing system | |
CN110889311A (en) | Financial electronic facsimile document identification system and method | |
CN105005969A (en) | Note image correction detecting method and system | |
US7668394B2 (en) | Background intensity correction of a scan of a document | |
Bhuvaneswari et al. | Automatic Detection and Inpainting of Text Images |
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: 20171208 |
|
RJ01 | Rejection of invention patent application after publication |