CN107134048A - A kind of bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature - Google Patents
A kind of bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature Download PDFInfo
- Publication number
- CN107134048A CN107134048A CN201710337615.7A CN201710337615A CN107134048A CN 107134048 A CN107134048 A CN 107134048A CN 201710337615 A CN201710337615 A CN 201710337615A CN 107134048 A CN107134048 A CN 107134048A
- Authority
- CN
- China
- Prior art keywords
- bill
- watermark
- feature
- point
- characteristic point
- 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
Landscapes
- Inspection Of Paper Currency And Valuable Securities (AREA)
- Editing Of Facsimile Originals (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature, this method includes bill watermark feature and extracts stage, matching stage and cognitive phase, specifically includes following steps：Bill watermarking images are gathered, each pixel Hessian matrixes of component, generation graphical rule space determines characteristic point based on non-maxima suppression, and calculates characteristic point direction, obtains SURF feature point descriptions；Description of obtained bill watermark is matched with description of standard ticket watermark；The matching result of matching stage is recognized, the true and false of tested bill is judged according to matching result.The method that the present invention is provided can realize that intelligent extraction is detected bill and extracts watermark feature, and the feature of extraction is matched into contrast with standard ticket watermark feature, automatic identification can be completed, realizes that bill intelligent anti-counterfeiting differentiates.
Description
Technical field
The present invention relates to bill anti-counterfeit authentication technique field, more particularly to a kind of bill anti-counterfeit of Intelligent Recognition watermark feature
Discrimination method.
Background technology
With national economy and scientific and technological high speed development, the application of bill in daily life is increasingly extensive.But current bill
There are problems that mismanagement, the true and false differentiate still there are many criminals to be reaped staggering profits by making fictitious bill in society,
" clone's ticket ", " forgery ticket ", " adulterium ticket " contour the prevailing of imitative fictitious bill cause serious financial consequences to country.Traditional bill
Distinguishing method between true and false needs to carry out artificial judgment by the false proof point in 30 to bill many, is determined according to the experience of people is checked
Bill is true and false.Artificial treatment inefficiency, error-prone, subjective composition are big, realize the intelligent analysis of bill, automatic discriminating, are
The important trend of following bill authentication technique.
Watermark is one of important anti-false sign of bill, by extracting tested bill watermark feature, and with standard watermark feature
Match cognization can effectively realize the false proof discriminating of smart tickets.The insertion of watermarking images and extracting method (ZL201110139206.9)
Disclose and a kind of be suitable to solve the transparency in watermarking algorithm and contradict the Gray-level Watermarking image of problem with robustness to be embedded in and carry
Method is taken, but this method can not directly carry out papers discriminating；Bill anti-counterfeit based on bill watermark distribution characteristics differentiates
Method (ZL201110400177.7) realizes the binaryzation of bill images using local thresholding method；Found in bill images and connection
The same or analogous object of shuttering, joint template matches are carried out by module of coefficient correlation；Extract bill images
Watermark distribution characteristics；Characteristic matching is carried out based on watermark distribution characteristics, differentiates the true and false of bill.Patent utilization of the present invention accelerates steady
Strong feature (Speeded Up Robust Features, SURF) extracting method, it is possible to achieve intelligent extraction is detected bill and extracted
Watermark feature, will extract feature with standard ticket watermark feature and matches contrast, can complete automatic identification, realize bill intelligent anti-counterfeiting
Differentiate.
The content of the invention
In order to solve the above technical problems, it is an object of the invention to provide a kind of bill anti-counterfeit of Intelligent Recognition watermark feature mirror
Other method, the purpose of the present invention is realized by following technical scheme：
A kind of bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature, this method includes bill watermark feature and extracts rank
Section, matching stage and cognitive phase, specifically include following steps：
Step A gathers bill watermarking images, each pixel Hessian matrixes of component, generation graphical rule space, based on non-
Maximum suppresses to determine characteristic point, and calculates characteristic point direction, obtains SURF feature point descriptions；
Step B is matched description of obtained bill watermark with description of standard ticket watermark；
Step C recognizes the matching result of matching stage, and the true and false of tested bill is judged according to matching result.
Compared with prior art, one or more embodiments of the invention can have the following advantages that：
The bill watermarking images that this method includes extract stage, matching stage, cognitive phase, it is possible to achieve intelligent extraction quilt
The feature of extraction is matched contrast with standard ticket watermark feature, can complete automatic identification by ticket checking according to watermark feature is extracted, and is realized
Bill intelligent anti-counterfeiting differentiates.
Brief description of the drawings
Fig. 1 is the bill anti-counterfeit discrimination method flow chart of Intelligent Recognition watermark feature；
Fig. 2 is bill watermark feature extraction procedure flow chart；
Fig. 3 is bill watermark extracting feature point diagram.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with embodiment and accompanying drawing to this hair
It is bright to be described in further detail.
As shown in figure 1, for the bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature, this method comprises the following steps：
Step 10 gathers bill watermarking images, and each pixel Hessian matrixes of component generate graphical rule space, are based on
Non-maxima suppression determines characteristic point, and calculates characteristic point direction, obtains SURF feature point description operators；
Step 20 is matched description of obtained bill watermark with description of standard ticket watermark；
Step 30 recognizes the matching result of matching stage, and the true and false of tested bill is judged according to matching result.
As shown in Fig. 2 above-mentioned steps 10 are specifically included：
To tested bill printing opacity processing, its surface watermark is presented.Bill watermarking images are gathered, each pixel is built
Hessian matrixesTypically by image pixel point brightness value and certain Directional partial derivative convolution of Gaussian kernel,
Gaussian kernel is approximately replaced with box wave filter herein, because box wave filter only has 0, -1,1, therefore convolutional calculation can use integrogram
As optimizing, algorithm speed is effectively improved.Each pixel need to calculate Dxx、Dxy、Dyy, therefore three wave filters are needed, after filtering
(each point pixel value is for an available width response diagram)；Filter to the bill watermarking images different scale of collection
Ripple device is filtered, and obtains a series of response diagrams of the same image in different scale, that is, generates pyramid scale space.
If certain pointValue be more than itself scale layer in remaining 8 point and above and under two
9 points of scale layer totally 26 pointsThen the point is characterized a little, with this determination watermarking images characteristic point, such as Fig. 3
It is shown.
Centered on characteristic point, some numerical digit radius of feature point scale is proportional to, the interior institute of 60 ° of sectors of statistics is a little in x
The small echo response summation in (level) and y (vertical) direction, and Gauss weight coefficient is assigned to these responses, then in the range of 60 °
Response be summed to form new vector, travel through whole border circular areas, selection most long vector direction is the principal direction of this feature point.
Selected one piece of square area centered on characteristic point, is rotated and is alignd with principal direction, square is divided into 4
× 4 16 sub-regions, count the wavelet character in each region, obtain 4 coefficients, construct 4 × 4 × 4 dimensional vectors, that is, set up and retouch
State son.
Above-mentioned steps 20 are specifically included：
Some characteristic point in tested bill watermarking images is chosen, this feature point is found out Central European with standard ticket watermarking images
Two closest characteristic points of formula, if minimum distance is less than some proportion threshold value with secondary closely ratio, receive this pair
Match point.Proportion threshold value is lower, and matching points are fewer, but result can be more accurate.
Bill watermark need to can just show that watermark is easily obscured with ticket contents in image acquisition process under light transmission condition,
To exclude the key point without matching relationship that background clutter is produced, distance rates ratio is less than being considered just for some threshold value
Really matching.Because for erroneous matching, due to the higher-dimension of feature space, similar distance may have a large amount of other mistakes
Match somebody with somebody, so that its ratio values are higher.Ratio values are optimal between 0.4~0.6, less than 0.4 few match points, are more than
0.6 a large amount of error matching points of presence.
Although disclosed herein embodiment as above, described content is only to facilitate understanding the present invention and adopting
Embodiment, is not limited to the present invention.Any those skilled in the art to which this invention pertains, are not departing from this
On the premise of the disclosed spirit and scope of invention, any modification and change can be made in the implementing form and in details,
But the scope of patent protection of the present invention, still should be subject to the scope of the claims as defined in the appended claims.
Claims (3)
1. a kind of bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature, it is characterised in that methods described includes bill watermark
Feature extraction phases, matching stage and cognitive phase, specifically include following steps：
Step A gathers bill watermarking images, each pixel Hessian matrixes of component, generation graphical rule space, based on non-very big
Value suppresses to determine characteristic point, and calculates characteristic point direction, obtains SURF feature point descriptions；
Step B is matched description of obtained bill watermark with description of standard ticket watermark；
Step C recognizes the matching result of matching stage, and the true and false of tested bill is judged according to matching result.
2. the bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature as claimed in claim 1, it is characterised in that the step
A is specifically included：
To tested bill printing opacity processing, make bill surface that watermark is presented；
Bill watermarking images are gathered, each pixel Hessian matrixes are builtTo the bill watermark figure of collection
As being filtered with the wave filter of different scale, a series of response diagrams of the same image in different scale, generation image gold are obtained
Word tower metric space；
There is certain point in the pyramid scale space generated according to bill watermarking images has maximum pixel compared with consecutive points around it
Value, characteristic point is primarily determined that using based on non-maxima suppression, if certain pointValue is more than its in itself scale layer
Remaining eight points and on itself and under two scale layers, nine points totally 26 pointsThen the point is spy
Levy a little；
Characteristic point principal direction is calculated, 16 sub-regions are chosen altogether along principal direction horizontal direction x, vertical direction y, each region is counted
Interior wavelet character, obtains four coefficients, constructs 4 × 4 × 4 dimensional vectors, that is, describes son.
3. the bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature as claimed in claim 1, it is characterised in that the step
B is specifically included：
Choose some characteristic point in tested bill watermarking images, find out this feature point with standard ticket watermarking images it is European away from
From two nearest characteristic points, if minimum distance is less than some proportion threshold value with secondary closely ratio, receive this pair of matchings
Point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710337615.7A CN107134048A (en) | 2017-05-15 | 2017-05-15 | A kind of bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710337615.7A CN107134048A (en) | 2017-05-15 | 2017-05-15 | A kind of bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107134048A true CN107134048A (en) | 2017-09-05 |
Family
ID=59733054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710337615.7A Pending CN107134048A (en) | 2017-05-15 | 2017-05-15 | A kind of bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107134048A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537945A (en) * | 2018-03-09 | 2018-09-14 | 深圳怡化电脑股份有限公司 | Bill method of detecting watermarks, system and self-service device |
| CN108921209A (en) * | 2018-06-21 | 2018-11-30 | 杭州骑轻尘信息技术有限公司 | Image identification method, device and electronic equipment |
| CN109448219A (en) * | 2018-10-25 | 2019-03-08 | 深圳怡化电脑股份有限公司 | Image matching method, device, bill identifier and computer readable storage medium |
| CN111612966A (en) * | 2020-05-21 | 2020-09-01 | 广东乐佳印刷有限公司 | Bill certificate anti-counterfeiting detection method and device based on image recognition |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129704A (en) * | 2011-02-23 | 2011-07-20 | 山东大学 | SURF operand-based microscope image splicing method |
| CN102542660A (en) * | 2011-12-05 | 2012-07-04 | 中钞实业有限公司 | Bill anti-counterfeiting identification method based on bill watermark distribution characteristics |
| CN104008379A (en) * | 2014-06-16 | 2014-08-27 | 河南科技大学 | Object recognition method based on surf |
| CN104933434A (en) * | 2015-06-16 | 2015-09-23 | 同济大学 | Image matching method combining length between perpendiculars (LBP) feature extraction method and surf feature extraction method |
| CN105608671A (en) * | 2015-12-30 | 2016-05-25 | 哈尔滨工业大学 | Image connection method based on SURF algorithm |
| KR20160064931A (en) * | 2014-11-28 | 2016-06-08 | 숭실대학교산학협력단 | Apparatus and Method for detecting intelligent high-speed multi-object |
-
2017
- 2017-05-15 CN CN201710337615.7A patent/CN107134048A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129704A (en) * | 2011-02-23 | 2011-07-20 | 山东大学 | SURF operand-based microscope image splicing method |
| CN102542660A (en) * | 2011-12-05 | 2012-07-04 | 中钞实业有限公司 | Bill anti-counterfeiting identification method based on bill watermark distribution characteristics |
| CN104008379A (en) * | 2014-06-16 | 2014-08-27 | 河南科技大学 | Object recognition method based on surf |
| KR20160064931A (en) * | 2014-11-28 | 2016-06-08 | 숭실대학교산학협력단 | Apparatus and Method for detecting intelligent high-speed multi-object |
| CN104933434A (en) * | 2015-06-16 | 2015-09-23 | 同济大学 | Image matching method combining length between perpendiculars (LBP) feature extraction method and surf feature extraction method |
| CN105608671A (en) * | 2015-12-30 | 2016-05-25 | 哈尔滨工业大学 | Image connection method based on SURF algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 何东健: "《数字图像处理》", 28 February 2015 * |
| 敖祖锐: "《星载SAR影像模拟与正射校正》", 31 January 2017 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537945A (en) * | 2018-03-09 | 2018-09-14 | 深圳怡化电脑股份有限公司 | Bill method of detecting watermarks, system and self-service device |
| CN108537945B (en) * | 2018-03-09 | 2020-09-15 | 深圳怡化电脑股份有限公司 | Bill watermark detection method and system and self-service equipment |
| CN108921209A (en) * | 2018-06-21 | 2018-11-30 | 杭州骑轻尘信息技术有限公司 | Image identification method, device and electronic equipment |
| CN109448219A (en) * | 2018-10-25 | 2019-03-08 | 深圳怡化电脑股份有限公司 | Image matching method, device, bill identifier and computer readable storage medium |
| CN111612966A (en) * | 2020-05-21 | 2020-09-01 | 广东乐佳印刷有限公司 | Bill certificate anti-counterfeiting detection method and device based on image recognition |
| CN111612966B (en) * | 2020-05-21 | 2021-05-07 | 广东乐佳印刷有限公司 | Bill certificate anti-counterfeiting detection method and device based on image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102222384B (en) | Analysis method of multispectral image of note | |
| Zhang et al. | Contact lens detection based on weighted LBP | |
| CN107221070A (en) | A kind of bill anti-counterfeit discrimination method recognized based on master pattern fluorescent characteristics | |
| CN104298989B (en) | False distinguishing method and its system based on zebra stripes Infrared Image Features | |
| CN107134048A (en) | A kind of bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature | |
| CN102542660B (en) | Bill anti-counterfeiting identification method based on bill watermark distribution characteristics | |
| CN108694393A (en) | A kind of certificate image text area extraction method based on depth convolution | |
| CN104658097B (en) | A kind of rmb paper currency denomination identifying method of Histogram Matching based on image | |
| CN105894655B (en) | Paper currency detection and recognition methods under complex environment based on RGB-D cameras | |
| CN110210608A (en) | The enhancement method of low-illumination image merged based on attention mechanism and multi-level features | |
| CN110443128A (en) | One kind being based on SURF characteristic point accurately matched finger vein identification method | |
| CN106557740B (en) | The recognition methods of oil depot target in a kind of remote sensing images | |
| Pham et al. | Deep learning-based fake-banknote detection for the visually impaired people using visible-light images captured by smartphone cameras | |
| CN108509870B (en) | A kind of Eriocheir sinensis uniqueness recognition methods based on images match | |
| CN108921831B (en) | Stained coin identification method based on image processing technology | |
| Tessfaw et al. | Ethiopian banknote recognition and fake detection using support vector machine | |
| Alshayeji et al. | Detection method for counterfeit currency based on bit-plane slicing technique | |
| CN105809173B (en) | A kind of image RSTN invariable attribute feature extraction and recognition methods based on bionical object visual transform | |
| CN108647695A (en) | Soft image conspicuousness detection method based on covariance convolutional neural networks | |
| WO2016123903A1 (en) | Folded bill identification method and device | |
| CN103886309A (en) | Method for identifying dollar denominations through facial recognition | |
| Dixit et al. | Image texture analysis-survey | |
| Jadhav et al. | Currency identification and forged banknote detection using deep learning | |
| CN106599891B (en) | A kind of remote sensing images region of interest rapid extracting method based on scale phase spectrum conspicuousness | |
| Sharan et al. | Detection of counterfeit Indian currency note using image processing |
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: 20170905 |