CN106846609A - It is a kind of based on perceiving the bank note face amount of Hash towards recognition methods - Google Patents
It is a kind of based on perceiving the bank note face amount of Hash towards recognition methods Download PDFInfo
- Publication number
- CN106846609A CN106846609A CN201611163899.4A CN201611163899A CN106846609A CN 106846609 A CN106846609 A CN 106846609A CN 201611163899 A CN201611163899 A CN 201611163899A CN 106846609 A CN106846609 A CN 106846609A
- Authority
- CN
- China
- Prior art keywords
- image
- bank note
- banknote
- hash
- face amount
- 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 22
- 230000008447 perception Effects 0.000 claims abstract description 24
- 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 description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D7/20—Testing patterns thereon
- G07D7/202—Testing patterns thereon using pattern matching
- G07D7/2033—Matching unique patterns, i.e. patterns that are unique to each individual paper
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D11/00—Devices accepting coins; Devices accepting, dispensing, sorting or counting valuable papers
- G07D11/10—Mechanical details
- G07D11/16—Handling of valuable papers
Abstract
The present invention relates to a kind of based on perceiving the bank note face amount of Hash towards recognition methods, the method is by the way that by difference, towards after the image scaling of face amount standard bank note, generation graphics standard perceives Hash fingerprint；Then banknote area image is extracted in banknote image to be detected accordingly after scaling, calculates the image perception Hash fingerprint of bank note area image；The image perception Hash fingerprint of banknote area image and corresponding graphics standard are finally perceived into Hash fingerprint matching, according to matching similarity with judge the face amount of bank note towards.The present invention can greatly improve the accuracy rate of target identification, and autgmentability in the case of without the time and space expense for additionally increasing algorithm.
Description
Technical field
The invention belongs to technical field of financial equipment, and in particular to a kind of based on perceiving the bank note face amount of Hash towards identification
Method.
Background technology
In withdrawal circulator core equipment, identification module is responsible for every Detection task of bank note, including truth identification, hat
Font size is recognized and the sorting of bank note works.Typically in movement is circulated, each item of image of the bank note for entering identification module
Before detection, top priority be to determine the face amount of bank note with towards, face amount towards accuracy of judgement whether directly affect subsequent figure
As testing result.Wherein in every image-processing operations, the face amount of bank note is the basis of these Detection tasks, face towards judgement
Be worth towards accuracy of judgement whether, directly affect the accuracy rate of subsequent detection task.
Patent No. CN2015102505749 bank note towards in the patent of recognition methods and device, it is proposed that use BP
Neural network recognization bank note face amount towards, bank note is divided into some grids first, the gray value for then extracting each grid is total
With, and a characteristic vector is formed, these characteristic vectors input grader is trained.This identification based on neutral net
Method, not only needs to all kinds of face amounts towards substantial amounts of training is carried out, and its previous work amount is larger；And the selection of its feature is right
It is very sensitive in the conversion of illumination, it is easy to cause to recognize mistake.
The content of the invention
There is provided a kind of based on the bank note face amount face for perceiving Hash it is an object of the invention to solve above-mentioned technical problem
To recognition methods.
To achieve the above object, the present invention is adopted the following technical scheme that：
It is a kind of based on perceive Hash bank note face amount towards recognition methods, including：
S101, by difference towards after the image scaling of face amount standard bank note, generation graphics standard perceives Hash fingerprint；
S102, after banknote area image is accordingly scaled in extraction banknote image to be detected, calculates the figure of bank note area image
As perceiving Hash fingerprint；
S103, Hash fingerprint is perceived by the image perception Hash fingerprint of banknote area image with corresponding graphics standard
Match somebody with somebody, and according to similarity judge the face amount of bank note towards.
In step S02, before banknote area image in extracting banknote image to be detected, following step is still further comprised
Suddenly：
Calculate banknote image angle of inclination, then using the angle of inclination by affine transformation by banknote image rotate to
Horizontal level, then extracts banknote area image using threshold segmentation method.
It is some by the coboundary sampling in banknote image spaced apart when the gradient of banknote image is calculated
Discrete point, these discrete points is fitted in alignment, will calculate the angle of inclination of straight line as the angle of inclination of banknote image.
The image perception Hash fingerprint of bank note area image is calculated described in step S102, refers to calculate bank note area image
Image average, and by the pixel of banknote area image pixel-by-pixel with the average ratio of image compared with less than setting to 0 for average, greatly
255 are put in average, 0 and 255 Serial No.s for constituting are formed, all Serial No.s being made up of 0 and 255, are paper money zone
The image perception Hash fingerprint of area image.
In step S103, in banknote area, the image perception Hash fingerprint of image perceives Hash and refers to corresponding graphics standard
When line is matched, the image perception Hash fingerprint of banknote area image and graphics standard are perceived into Hash fingerprint and is compared pixel-by-pixel, shape
Into statistical counting result, then the result according to statistical counting judges similarity, and similarity highest graphics standard perceives Hash
The corresponding face amount of fingerprint towards, be identified bank note face amount towards.
The present invention by using perceive hash algorithm recognize bank note face amount towards, to each currency type, each value of money, each
Towards generating a corresponding perception Hash fingerprint respectively, breathed out towards only needing in identification process to compare corresponding perception in face amount
The similarity of uncommon fingerprint, you can quickly judge currency type, face amount and towards without the time and space expense for additionally increasing algorithm
In the case of, the accuracy rate of target identification can be greatly improved, and the scalability of algorithm is preferable.
Brief description of the drawings
Fig. 1 is flow chart of the bank note face amount based on perception Hash of the invention towards recognition methods；
Fig. 2-5 is four differences choosing of the present invention towards 100 yuans of schematic diagram；
Fig. 6-9 is four differences towards 100 yuans of perception Hash fingerprint image.
Specific embodiment
Below, substantive distinguishing features of the invention and advantage are further described with reference to example, but the present invention not office
It is limited to listed embodiment.
It is shown in Figure 1, it is a kind of based on the bank note face amount of Hash is perceived towards recognition methods, comprise the following steps：
S101, by difference towards after the image scaling of face amount standard bank note, generation as matches criteria masterplate image mark
Standard perceives Hash fingerprint；
S102, after banknote area image is accordingly scaled in extraction bank note standard picture to be detected, calculates bank note area image
Image perception Hash fingerprint；
S103, Hash fingerprint is perceived by the image perception Hash fingerprint of banknote area image with corresponding graphics standard
Match somebody with somebody, and according to similarity judge the face amount of the bank note towards.
The standard bank note can be different currency types, i.e., any that logical bank note currency type is flowed in society.
Wherein, in the present invention, in step S02, before banknote area image in extracting banknote image to be detected, also enter
One step is comprised the following steps：
Calculate banknote image angle of inclination, then using the angle of inclination by affine transformation by banknote image rotate to
Horizontal level, then extracts banknote area image, then the banknote area image scaling that will be extracted to pre- using threshold segmentation method
If size, then such as size of 50*50 calculates the image perception Hash fingerprint of bank note area image.
It is by the top in banknote image spaced apart when the gradient of banknote image is calculated in the present invention
The some discrete points of boundary's sampling, the fitting of these discrete points is in alignment, the angle of inclination of straight line is calculated as banknote image
Angle of inclination is what is realized.
When being corrected, be the center with banknote image as reference point, the angle of inclination of banknote image is rotation
Angle, affine transformation is carried out to banknote image, will be inclined banknote image and be corrected to horizontal level, as shown in Figure 2-5.
It should be noted that when banknote area is zoomed into too small size, many image details will be ignored, it is impossible to compared with
Distinguish different classes of well；And zoom to larger size, computational complexity can be caused to increase again；It is both above-mentioned by weighing,
The present invention is selected the size of image scaling to 50*50.
In the present invention, the described image perception Hash fingerprint for calculating bank note area image refers to calculate the paper after scaling
The average (i.e. the pixel average of image) of the image of coin area image, and by the pixel of banknote area image pixel-by-pixel with figure
The average ratio of picture compared with, less than setting to 0 for average, 255 are put more than average, form the Serial No.s of 0 and 255 compositions, these are by 0 He
255 Serial No.s for constituting, are the image perception Hash fingerprint of identified bank note, as Figure 6-9.
Specifically, in step s 103, the image perception Hash fingerprint of image and corresponding graphics standard in banknote area
When perceiving Hash fingerprint matching, in the matching process, it is only necessary to by the figure for judging the banknote area image of identified bank note
As the similarity for perceiving Hash fingerprint with Hash fingerprint is perceived as the graphics standard of template, by the Similarity value between them,
Can rapidly identify identified bank note towards, face amount.
Specifically in matching, using the perception Hash fingerprint of banknote area image after the scaling of identified bank note with as mould
The graphics standard of plate perceives Hash fingerprint and compares pixel-by-pixel, if respective pixel value is different, error count adds 1, final basis
The result of statistical counting judges similarity degree, and similarity highest graphics standard perceives the corresponding face amount of Hash fingerprint, be by
The face amount of the bank note of identification towards.
The present invention by using perceive hash algorithm recognize bank note face amount towards, to each currency type, each value of money, each
Hash fingerprint is perceived towards a corresponding perception Hash is generated respectively, in face amount towards only needing to compare phase in identification process
The similarity of Hash fingerprint should be perceived, you can quickly judge currency type, face amount with towards, without additionally increase algorithm time and
In the case of space expense, the accuracy rate of target identification can be greatly improved, and the scalability of algorithm is preferable.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (5)
1. a kind of based on perceiving the bank note face amount of Hash towards recognition methods, it is characterised in that including：
S101, by difference towards after the image scaling of face amount standard bank note, generation graphics standard perceives Hash fingerprint；
S102, after banknote area image is accordingly scaled in extraction banknote image to be detected, calculates the image sense of bank note area image
Know Hash fingerprint；
S103, Hash fingerprint matching is perceived by the image perception Hash fingerprint of banknote area image and corresponding graphics standard, and
According to similarity judge the face amount of bank note towards.
2. according to claim 1 based on perceiving the bank note face amount of Hash towards recognition methods, it is characterised in that in step
In S102, before banknote area image in extracting banknote image to be detected, following steps are still further comprised：
The angle of inclination of banknote image is calculated, then banknote image is rotated to level by affine transformation using the angle of inclination
Position, then extracts banknote area image using threshold segmentation method.
3. according to claim 2 based on perceiving the bank note face amount of Hash towards recognition methods, it is characterised in that in computation paper
During the gradient of coin image, sampled some discrete points by the coboundary in banknote image spaced apart, by these from
Scatterplot fitting is in alignment, will calculate the angle of inclination of straight line as the angle of inclination of banknote image.
4. according to claim 1 based on perceiving the bank note face amount of Hash towards recognition methods, it is characterised in that step S102
Described in calculate bank note area image image perception Hash fingerprint, refer to calculate bank note area image image average, and
By the pixel of banknote area image pixel-by-pixel with the average ratio of image compared with less than setting to 0 for average, 255, shape being put more than average
Into 0 and 255 Serial No.s for constituting, all Serial No.s being made up of 0 and 255 are the image perception of banknote area image
Hash fingerprint.
5. according to claim 1 based on perceiving the bank note face amount of Hash towards recognition methods, it is characterised in that step S103
In, when in banknote area, the image perception Hash fingerprint of image perceives Hash fingerprint matching with corresponding graphics standard, by bank note
The image perception Hash fingerprint of area image perceives Hash fingerprint and compares pixel-by-pixel with graphics standard, forms statistical counting result,
Then the result according to statistical counting judges similarity, and similarity highest graphics standard perceives the corresponding face amount face of Hash fingerprint
To, be identified bank note face amount towards.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611163899.4A CN106846609A (en) | 2016-12-16 | 2016-12-16 | It is a kind of based on perceiving the bank note face amount of Hash towards recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611163899.4A CN106846609A (en) | 2016-12-16 | 2016-12-16 | It is a kind of based on perceiving the bank note face amount of Hash towards recognition methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106846609A true CN106846609A (en) | 2017-06-13 |
Family
ID=59140291
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611163899.4A Pending CN106846609A (en) | 2016-12-16 | 2016-12-16 | It is a kind of based on perceiving the bank note face amount of Hash towards recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106846609A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680248A (en) * | 2017-10-13 | 2018-02-09 | 深圳怡化电脑股份有限公司 | A kind of bank note towards recognition methods, device, ATM and storage medium |
| CN110472650A (en) * | 2019-06-25 | 2019-11-19 | 福建立亚新材有限公司 | A kind of recognition methods and system of fiber appearance grade |
| CN111738079A (en) * | 2020-05-19 | 2020-10-02 | 武汉卓目科技有限公司 | Banknote denomination recognition method and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0528321A (en) * | 1991-07-19 | 1993-02-05 | Hitachi Ltd | Method and system for image recognition |
| CN101197897A (en) * | 2006-12-05 | 2008-06-11 | 佳能株式会社 | Image processing apparatus and image processing method |
| CN102096962A (en) * | 2010-12-23 | 2011-06-15 | 北京新岸线软件科技有限公司 | Paper currency detecting method and device |
| JP2013206440A (en) * | 2012-03-29 | 2013-10-07 | Glory Ltd | Bill identification device, bill identification method and bill identification program |
| CN104346858A (en) * | 2014-10-10 | 2015-02-11 | 新达通科技股份有限公司 | Paper currency face value identification method and device based on magnetic image |
| CN104809715A (en) * | 2014-01-23 | 2015-07-29 | 广州南沙资讯科技园有限公司博士后科研工作站 | Banknote image inclination correction and region extraction method |
| CN105261110A (en) * | 2015-10-26 | 2016-01-20 | 江苏国光信息产业股份有限公司 | Efficient DSP banknote serial number recognizing method |
| CN105303676A (en) * | 2015-10-27 | 2016-02-03 | 深圳怡化电脑股份有限公司 | Banknote version identification method and banknote version identification system |
| CN105654609A (en) * | 2015-12-29 | 2016-06-08 | 深圳怡化电脑股份有限公司 | Paper money processing method and paper money processing system |
-
2016
- 2016-12-16 CN CN201611163899.4A patent/CN106846609A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0528321A (en) * | 1991-07-19 | 1993-02-05 | Hitachi Ltd | Method and system for image recognition |
| CN101197897A (en) * | 2006-12-05 | 2008-06-11 | 佳能株式会社 | Image processing apparatus and image processing method |
| CN102096962A (en) * | 2010-12-23 | 2011-06-15 | 北京新岸线软件科技有限公司 | Paper currency detecting method and device |
| JP2013206440A (en) * | 2012-03-29 | 2013-10-07 | Glory Ltd | Bill identification device, bill identification method and bill identification program |
| CN104809715A (en) * | 2014-01-23 | 2015-07-29 | 广州南沙资讯科技园有限公司博士后科研工作站 | Banknote image inclination correction and region extraction method |
| CN104346858A (en) * | 2014-10-10 | 2015-02-11 | 新达通科技股份有限公司 | Paper currency face value identification method and device based on magnetic image |
| CN105261110A (en) * | 2015-10-26 | 2016-01-20 | 江苏国光信息产业股份有限公司 | Efficient DSP banknote serial number recognizing method |
| CN105303676A (en) * | 2015-10-27 | 2016-02-03 | 深圳怡化电脑股份有限公司 | Banknote version identification method and banknote version identification system |
| CN105654609A (en) * | 2015-12-29 | 2016-06-08 | 深圳怡化电脑股份有限公司 | Paper money processing method and paper money processing system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680248A (en) * | 2017-10-13 | 2018-02-09 | 深圳怡化电脑股份有限公司 | A kind of bank note towards recognition methods, device, ATM and storage medium |
| CN107680248B (en) * | 2017-10-13 | 2019-09-20 | 深圳怡化电脑股份有限公司 | A kind of bank note towards recognition methods and device |
| CN110472650A (en) * | 2019-06-25 | 2019-11-19 | 福建立亚新材有限公司 | A kind of recognition methods and system of fiber appearance grade |
| CN111738079A (en) * | 2020-05-19 | 2020-10-02 | 武汉卓目科技有限公司 | Banknote denomination recognition method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109241985B (en) | Image identification method and device | |
| Majhi et al. | Novel features for off-line signature verification | |
| US8929595B2 (en) | Dictionary creation using image similarity | |
| CN104318219B (en) | The face identification method combined based on local feature and global characteristics | |
| CN102800148B (en) | RMB sequence number identification method | |
| Abburu et al. | Currency recognition system using image processing | |
| KR20170006355A (en) | Method of motion vector and feature vector based fake face detection and apparatus for the same | |
| CN103530599A (en) | Method and system for distinguishing real face and picture face | |
| CN108108760A (en) | A kind of fast human face recognition | |
| CN104298989A (en) | Counterfeit identifying method and counterfeit identifying system based on zebra crossing infrared image characteristics | |
| CN109740572A (en) | A kind of human face in-vivo detection method based on partial color textural characteristics | |
| CN110826408B (en) | Face recognition method by regional feature extraction | |
| CN106846609A (en) | It is a kind of based on perceiving the bank note face amount of Hash towards recognition methods | |
| CN111832405A (en) | Face recognition method based on HOG and depth residual error network | |
| Sawant et al. | Currency recognition using image processing and minimum distance classifier technique | |
| CN107742357A (en) | A kind of recognition methods of paper money number and device | |
| Dhar et al. | Paper currency detection system based on combined SURF and LBP features | |
| KR20080079798A (en) | Method of face detection and recognition | |
| CN107392105A (en) | A kind of expression recognition method based on reverse collaboration marking area feature | |
| CN106803307B (en) | Banknote face value orientation identification method based on template matching | |
| CN111275070B (en) | Signature verification method and device based on local feature matching | |
| Khin et al. | License plate detection of Myanmar vehicle images captured from the dissimilar environmental conditions | |
| US20030044067A1 (en) | Apparatus and methods for pattern recognition based on transform aggregation | |
| KR20150136971A (en) | Method and apparatus for detecting face with low energy or low resolution | |
| Radványi et al. | Mobile banknote recognition: Topological models in scene understanding |
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: 20170613 |
|
| RJ01 | Rejection of invention patent application after publication |