CN102750773B - Method for positioning paper money number image region - Google Patents
Method for positioning paper money number image region Download PDFInfo
- Publication number
- CN102750773B CN102750773B CN201210202477.9A CN201210202477A CN102750773B CN 102750773 B CN102750773 B CN 102750773B CN 201210202477 A CN201210202477 A CN 201210202477A CN 102750773 B CN102750773 B CN 102750773B
- Authority
- CN
- China
- Prior art keywords
- region
- image
- pixel
- bank note
- value
- 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.)
- Active
Links
Landscapes
- Inspection Of Paper Currency And Valuable Securities (AREA)
- Character Input (AREA)
Abstract
The invention relates to a method for positioning a paper money number image region. The method comprises the following steps: acquiring a horizontally arranged single paper money image; acquiring the appearing region of the number of the current paper money image, respectively selecting two rows in each region, and acquiring the proportion of the quantity of pixels with the pixel values less than an upper threshold F accounting for the total quantity of the pixels; carrying out [-1, 0, 1] Sobel gradient calculation respectively on the pixels of each row in each region, and acquiring the proportion of the quantity of the pixels with the gradient calculated values larger than a lower threshold G accounting for the total quantity of the pixels; respectively calculating the sums of V1 and V2 of the sampling rows in the four regions, searching for the maximum value of the sums of V1 and V2, and taking the region corresponding to the maximum value as a number region; and amplifying the image of the number region, carrying out slant and longitudinal draw correction on the amplified image, removing the blank region of the image of the number region, and identifying characters of the image of the number region. The method disclosed by the invention has the advantages that the paper money number region can be accurately positioned and the reliability is high.
Description
Technical field
The present invention relates to a kind of image position method.
Background technology
Banknote image hat font size area positioning method is the common step of hat font size identification, in the method for announcing at present, mainly comprises two classes.The first kind is projection localization method, and the image after binaryzation is carried out to level, vertical projection, and the number of the prosperous pixel of each row and each column in statistics level and vertical direction, determines number region with this.This method is subject to the impact of noise spot after binaryzation, easily locates on the upper side or on the lower side.
Equations of The Second Kind is a kind of localization method based on rectangle frame search.During due to shooting sample image, focal length and object distance are certain, so width w and the height H in pure number region are also fixed.Set up the rectangle that a size is w × H pixel, line by line the sum of black pixel point in the rectangular area taking current pixel point as left upper apex in statistical picture.The coordinate of recording the maximum rectangular area of stain sum, this coordinate had been both the coordinate in pure number region.The method easily lost efficacy in the time processing dirty coin, old coin image.
Summary of the invention
Easily occur the shortcoming of locate failure for overcoming prior art, the invention provides one can be exactly to bank note hat font size zone location, the localization method of the bank note hat font size image-region that reliability is high.
The localization method of bank note hat font size image-region, comprises the following steps:
1), obtain individual banknote image of horizontal positioned, banknote image and bank note in perspective;
2), obtain first area, second area, the 3rd region and the four-range area image of current banknote image, when just putting, corresponding bank note front, first area is preced with the band of position of font size, when positive inversion of the corresponding bank note of second area, be preced with the band of position of font size, when the corresponding bank note reverse side in the 3rd region is just being put, be preced with the band of position of font size, when the corresponding bank note reverse side in the 4th region is inverted, be preced with the band of position of font size;
3), in each region, at least select respectively two row data as sampling row, obtain respectively the pixel value of each sampling row, pixel value refers to the brightness value of the pixel of composition row data, calculating pixel value is less than the quantity of the pixel of upper limit threshold F, and the ratio that the pixel quantity that pixel value is less than to upper limit threshold F accounts for pixel total quantity is designated as V
1;
4), the pixel of the every a line to each region is carried out the Sobel gradient calculation of [1,0,1] respectively, obtain quantity that gradient calculation value is greater than the pixel of lower threshold G and account for the ratio of pixel total quantity, this ratio is designated as V
2; After Sobel calculates, each location of pixels can obtain a gradient calculation value, and gradient calculation value is larger, and the possibility of this corresponding location of pixels in picture material edge is just larger;
5) all sampling row, to four regions, calculate respectively this sampling row V to each sampling row
1+ V
2value, find V
1+ V
2maximal value, using the region at this maximal value place as prefix code region;
6), prefix code area image is amplified, and the image after amplifying is done and longitudinal stretching is proofreaied and correct, reject the white space of prefix code area image, preserve image, identify the character of prefix code area image.
Further, in step 3), each region selects two row data as sampling row.Two row samplings work and have often enough provided correct result, and calculated amount is little, reduces the computation burden of system.
Further, in step 6), candidate region image is amplified to 2 times.
Further, in step 6), by the character string numerical value of OCR character recognition program identification prefix code area image.
Technical conceive of the present invention is: be positive placement or reverse side placement because system cannot be distinguished the bank note of placement, be inverted or just putting, therefore capture four regions of banknote image, four regions are position corresponding to prefix code region when four kinds of modes of emplacements of corresponding bank note respectively.Calculate respectively the pixel value in four regions, to determine the position at prefix code place, finally by crossing OCR character recognition program, the character string of prefix code is identified.
The present invention can identify prefix code region accurately, and reliability is high, and can ensure to complete the prefix code identification of individual bank note in 100ms, is applicable to extensive commercial application.
Brief description of the drawings
Fig. 1 is process flow diagram of the present invention.
Embodiment
With reference to accompanying drawing, further illustrate the present invention:
The localization method of bank note hat font size image-region, comprises the following steps:
1), obtain individual banknote image of horizontal positioned, banknote image and bank note in perspective;
2), obtain first area, second area, the 3rd region and the four-range area image of current banknote image, when just putting, corresponding bank note front, first area is preced with the band of position of font size, when positive inversion of the corresponding bank note of second area, be preced with the band of position of font size, when the corresponding bank note reverse side in the 3rd region is just being put, be preced with the band of position of font size, when the corresponding bank note reverse side in the 4th region is inverted, be preced with the band of position of font size;
3), in each region, at least select respectively two row data as sampling row, obtain respectively the pixel value of each sampling row, pixel value refers to the brightness value of the pixel of composition row data, calculating pixel value is less than the quantity of the pixel of upper limit threshold F, and the ratio that the pixel quantity that pixel value is less than to upper limit threshold F accounts for pixel total quantity is designated as V
1;
4), the pixel of the every a line to each region is carried out the Sobel gradient calculation of [1,0,1] respectively, obtain quantity that gradient calculation value is greater than the pixel of lower threshold G and account for the ratio of pixel total quantity, this ratio is designated as V
2; After Sobel calculates, each location of pixels can obtain a gradient calculation value, and gradient calculation value is larger, and the possibility of this corresponding location of pixels in picture material edge is just larger;
5) all sampling row, to four regions, calculate respectively this sampling row V to each sampling row
1+ V
2value, find V
1+ V
2maximal value, using the region at this maximal value place as prefix code region;
6), prefix code area image is amplified, and the image after amplifying is done and longitudinal stretching is proofreaied and correct, reject the white space of prefix code area image, preserve image, identify the character of prefix code area image.
In step 3), each region selects two row data as sampling row.Two row samplings work and have often enough provided correct result, and calculated amount is little, reduces the computation burden of system.
In step 6), candidate region image is amplified to 2 times.And by the character string numerical value of OCR character recognition program identification prefix code area image.
Technical conceive of the present invention is: be positive placement or reverse side placement because system cannot be distinguished the bank note of placement, be inverted or just putting, therefore capture four regions of banknote image, four regions are position corresponding to prefix code region when four kinds of modes of emplacements of corresponding bank note respectively.Calculate respectively the pixel value in four regions, to determine the position at prefix code place, finally by crossing OCR character recognition program, the character string of prefix code is identified.
The present invention can identify prefix code region accurately, and reliability is high, and can ensure to complete the prefix code identification of individual bank note in 100ms, is applicable to extensive commercial application.
Content described in this instructions embodiment is only enumerating of way of realization to inventive concept; protection scope of the present invention should not be regarded as only limiting to the concrete form that embodiment states, protection scope of the present invention also and conceive the equivalent technologies means that can expect according to the present invention in those skilled in the art.
Claims (3)
1. the localization method of bank note hat font size image-region, comprises the following steps:
1), obtain individual banknote image of horizontal positioned, banknote image and bank note in perspective;
2), obtain first area, second area, the 3rd region and the four-range area image of current banknote image, when just putting, corresponding bank note front, first area is preced with the band of position of font size, when positive inversion of the corresponding bank note of second area, be preced with the band of position of font size, when the corresponding bank note reverse side in the 3rd region is just being put, be preced with the band of position of font size, when the corresponding bank note reverse side in the 4th region is inverted, be preced with the band of position of font size;
3), in each region, at least select respectively two row data as sampling row, obtain respectively the pixel value of each sampling row, pixel value refers to the brightness value of the pixel of composition row data, calculating pixel value is less than the quantity of the pixel of upper limit threshold F, and the ratio that the pixel quantity that pixel value is less than to upper limit threshold F accounts for pixel total quantity is designated as V
1;
4), the pixel of the every a line to each region is carried out the Sobel gradient calculation of [1,0,1] respectively, obtain quantity that gradient calculation value is greater than the pixel of lower threshold G and account for the ratio of pixel total quantity, this ratio is designated as V
2; After Sobel calculates, each location of pixels can obtain a gradient calculation value, and gradient calculation value is larger, and the possibility of this corresponding location of pixels in picture material edge is just larger;
5) all sampling row, to four regions, calculate respectively this sampling row V to each sampling row
1+ V
2value, find V
1+ V
2maximal value, using the region at this maximal value place as prefix code region;
6), prefix code area image is amplified, and the image after amplifying is done and longitudinal stretching is proofreaied and correct, reject the white space of prefix code area image, preserve image, identify the character of prefix code area image.
2. the localization method of bank note hat font size image-region as claimed in claim 1, is characterized in that: in step 6, candidate region image is amplified to 2 times.
3. the localization method of bank note hat font size image-region as claimed in claim 2, is characterized in that: by the character string numerical value of OCR character recognition program identification prefix code area image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210202477.9A CN102750773B (en) | 2012-06-15 | 2012-06-15 | Method for positioning paper money number image region |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210202477.9A CN102750773B (en) | 2012-06-15 | 2012-06-15 | Method for positioning paper money number image region |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102750773A CN102750773A (en) | 2012-10-24 |
| CN102750773B true CN102750773B (en) | 2014-07-30 |
Family
ID=47030921
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210202477.9A Active CN102750773B (en) | 2012-06-15 | 2012-06-15 | Method for positioning paper money number image region |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102750773B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107085882A (en) * | 2017-06-02 | 2017-08-22 | 深圳怡化电脑股份有限公司 | A kind of method and device for determining counterfeit money |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046252B (en) * | 2014-11-21 | 2018-09-07 | 华中科技大学 | A kind of RMB prefix code recognition methods |
| CN106355743A (en) * | 2015-07-14 | 2017-01-25 | 深圳怡化电脑股份有限公司 | Banknote version identification method and device |
| CN108074323B (en) * | 2016-11-15 | 2021-01-01 | 深圳怡化电脑股份有限公司 | Paper money facing identification method and device thereof |
| CN106600812B (en) * | 2016-12-14 | 2019-12-06 | 深圳怡化电脑股份有限公司 | Paper money identification method and device |
| CN108831004B (en) * | 2017-05-02 | 2021-01-01 | 深圳怡化电脑股份有限公司 | Method and device for determining paper currency crown word number area and automatic deposit and withdrawal equipment |
| CN108961531B (en) * | 2017-05-17 | 2020-10-20 | 深圳怡化电脑股份有限公司 | Method, device and equipment for identifying serial number of paper currency and storage medium |
| CN112990150A (en) * | 2021-05-10 | 2021-06-18 | 恒银金融科技股份有限公司 | Method for measuring upper and lower boundaries of crown word number based on projection bidirectional accumulation sum |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010122894A (en) * | 2008-11-19 | 2010-06-03 | Oki Electric Ind Co Ltd | Medium discrimination device |
| CN101923741A (en) * | 2010-08-11 | 2010-12-22 | 西安理工大学 | Paper currency number identification method based on currency detector |
| CN102005078A (en) * | 2010-12-23 | 2011-04-06 | 北京新岸线软件科技有限公司 | Method and device for recognizing paper currencies and tickets |
-
2012
- 2012-06-15 CN CN201210202477.9A patent/CN102750773B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010122894A (en) * | 2008-11-19 | 2010-06-03 | Oki Electric Ind Co Ltd | Medium discrimination device |
| CN101923741A (en) * | 2010-08-11 | 2010-12-22 | 西安理工大学 | Paper currency number identification method based on currency detector |
| CN102005078A (en) * | 2010-12-23 | 2011-04-06 | 北京新岸线软件科技有限公司 | Method and device for recognizing paper currencies and tickets |
Non-Patent Citations (5)
| Title |
|---|
| 人民币纸币序列号、面额号定位与分割;艾朝霞;《科学技术与工程》;20111216;第11卷(第19期);全文 * |
| 刘承香 阮双琛 胡学娟 黄贵明.纸币号码识别技术研究.《激光与红外》.2008,第38卷(第8期),全文. |
| 刘炜.人民币冠字号码识别与图像鉴伪技术研究及应用.《中国优秀硕士学位论文全文数据库（电子期刊）》.中国学术期刊（光盘版）电子杂志出版社,2011,(第12期),全文. * |
| 纸币号码识别技术研究;刘承香 阮双琛 胡学娟 黄贵明;《激光与红外》;20080820;第38卷(第8期);全文 * |
| 艾朝霞.人民币纸币序列号、面额号定位与分割.《科学技术与工程》.2011,第11卷(第19期),全文. |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107085882A (en) * | 2017-06-02 | 2017-08-22 | 深圳怡化电脑股份有限公司 | A kind of method and device for determining counterfeit money |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102750773A (en) | 2012-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102750773B (en) | Method for positioning paper money number image region | |
| CN103824066B (en) | A kind of licence plate recognition method based on video flowing | |
| US9946941B2 (en) | Lane detection | |
| US8184859B2 (en) | Road marking recognition apparatus and method | |
| US9311533B2 (en) | Device and method for detecting the presence of a logo in a picture | |
| CN104298982B (en) | A kind of character recognition method and device | |
| CN102750540B (en) | Morphological filtering enhancement-based maximally stable extremal region (MSER) video text detection method | |
| CN103606220B (en) | A kind of check printing digit recognizing method based on White-light image and infrared image | |
| CN103034848A (en) | Identification method of form type | |
| CN101515325A (en) | Character extracting method in digital video based on character segmentation and color cluster | |
| CN105184208B (en) | A kind of Quick Response Code Primary Location method and system | |
| CN106384113A (en) | Odd-and-even-line license plate character dividing method based on projection and template matching | |
| CN105005969B (en) | A kind of bill images alter detection method and system | |
| CN105160756A (en) | Paper money facing direction recognition method and device | |
| CN109308456B (en) | Target object information determination method, device, equipment and storage medium | |
| CN104966348B (en) | A kind of bill images key element integrality detection method and system | |
| EP2813973A1 (en) | Method and system for processing video image | |
| CN106951896B (en) | License plate image tilt correction method | |
| CN112446262A (en) | Text analysis method, text analysis device, text analysis terminal and computer-readable storage medium | |
| CN106203397A (en) | Differentiate and localization method based on the form of tabular analysis technology in image | |
| CN101639893A (en) | Method and device for identifying road direction | |
| CN112016566B (en) | Segmentation method for handwritten Chinese characters at financial bill upper-case money amount | |
| CN107392206A (en) | Rail pressed characters dividing method under a kind of working condition | |
| KR102094234B1 (en) | Serial number recognition Apparatus and method for paper money | |
| CN110059695B (en) | Character segmentation method based on vertical projection and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |