CN106710062B - Detect the method and device of bank note safety line - Google Patents
Detect the method and device of bank note safety line Download PDFInfo
- Publication number
- CN106710062B CN106710062B CN201611141187.2A CN201611141187A CN106710062B CN 106710062 B CN106710062 B CN 106710062B CN 201611141187 A CN201611141187 A CN 201611141187A CN 106710062 B CN106710062 B CN 106710062B
- Authority
- CN
- China
- Prior art keywords
- pixel
- safety line
- region
- value
- bank note
- 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.)
- Expired - Fee Related
Links
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
Abstract
The present invention is suitable for paper money recognition technical field, proposes the method and device of detection bank note safety line, comprising: obtains the image-region comprising safety line;Calculate the sum of the pixel value of each column in described image region;Image-region where the minimum continuous preset quantity column of the sum of the pixel value is determined as the safety line region;At least one of characteristic parameter based on safety line region pixel: in mean value, variance and pixel number, forge or true or paper money is detected.In the present invention, calculate the sum of the pixel value of each column in the image-region of safety line, image-region where the minimum continuous preset quantity column of the sum of the pixel value is determined as safety line region, the influence of safety line bright spot is eliminated according to the pixel value mean value in the region outside safety line, the detection method of mean value, variance, pixel number is comprehensively considered in safety line region, so that the accuracy rate of detection forge or true or paper money improves.
Description
Technical field
The invention belongs to paper money recognition technical fields, more particularly to the method and device of detection bank note safety line.
Background technique
Safety line is the important anti-counterfeiting characteristic of RMB.The 5th set of 100 yuan note of RMB of version in 2015 increases second
Safety line: light becomes hollow out opened window safety line, and light becomes 4 millimeters of hollow out opened window safety line line width, and photomodification can be to light source requirements
Not high, color change is obvious, integrates hollow out character features, is more conducive to public's identification.But not simply by eye recognition
Such as more acurrate using plant identification, the bank note that criminal forges in order to prevent comes into the market, and it is high-precision to be badly in need of exploitation
Plant.
Summary of the invention
The embodiment of the present invention is designed to provide a kind of method and device for detecting bank note safety line, it is intended to solve current
The not high problem of eye recognition bank note safety line accuracy.
The embodiments of the present invention are implemented as follows, a method of detection bank note safety line, comprising:
Obtain the image-region comprising safety line;
Calculate the sum of the pixel value of each column in described image region;
Image-region where the minimum continuous preset quantity column of the sum of the pixel value is determined as where the safety line
Region;
Characteristic parameter based on safety line region pixel: at least one in mean value, variance and pixel number
, forge or true or paper money is detected.
The another object of the embodiment of the present invention is to provide a kind of device for detecting bank note safety line, comprising:
Acquiring unit, for obtaining the image-region comprising safety line;
First computing unit, for calculating the sum of the pixel value of each column in described image region;
Positioning unit, for image-region where the minimum continuous preset quantity column of the sum of the pixel value to be determined as institute
State safety line region;
Detection unit, for the characteristic parameter based on safety line region pixel: mean value, variance and pixel
At least one of in number, forge or true or paper money is detected.
In embodiments of the present invention, the sum of the pixel value for calculating each column in the image-region of safety line, by the pixel
Image-region where the minimum continuous preset quantity column of the sum of value is determined as safety line region, comprehensively considers in safety line region
Mean value, variance, the detection method of pixel number, so that the accuracy rate of detection forge or true or paper money improves.
Detailed description of the invention
Fig. 1 is the method flow diagram of detection bank note safety line provided in an embodiment of the present invention;
Fig. 2 is spy of the 5th set of 100 yuan note Article 2 safety line provided in an embodiment of the present invention under infrared transmission figure
Sign figure;
Fig. 3 is the flow chart provided in an embodiment of the present invention detected based on mean value to forge or true or paper money;
Fig. 4 is the schematic diagram after the 5th set of 100 yuan note Article 2 safety line binaryzation provided in an embodiment of the present invention;
Fig. 5 is the flow chart provided in an embodiment of the present invention detected based on variance to forge or true or paper money;
Fig. 6 is the flow chart provided in an embodiment of the present invention detected based on pixel number to forge or true or paper money;
Fig. 7 is the structural block diagram of the device of detection bank note safety line provided in an embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is used only for explaining the present invention, and
It is not used in the restriction present invention.
Fig. 1 is the method flow diagram of detection bank note safety line provided in an embodiment of the present invention.
In S101, the image-region comprising safety line is obtained;
Preferably, the image-region of the acquisition comprising safety line is cut from the infrared transmission figure where the safety line
It obtains.
The image-region comprising safety line not only includes safety line region, further includes safety line exterior domain.
Fig. 2 shows the 5th set of 100 yuan note Article 2 safety lines provided in an embodiment of the present invention under infrared transmission figure
Characteristic pattern.Intermediate dark gray section is the safety line region, and two sides bright gray parts are the safety line outskirt
Domain.
In S102, the sum of the pixel value of each column in described image region is calculated.
Specifically, using two-dimensional Cartesian coordinate system, I (x, y) indicates the pixel value in point P (x, y), wherein x indicates point P
It being expert at, y indicates point P column, then:
Mean that the sum of the pixel value of y column calculation formula.
Consider each column pixel value column and, than consider single-row pixel value column and, the interference of noise can be excluded, so that inspection
Accuracy rate is surveyed to improve.
In S103, image-region where the minimum continuous preset quantity column of the sum of the pixel value is determined as the peace
All fronts region.
Preferably, the preset quantity column are 15 column.
The width of Article 2 safety line is between 15-16 column, even if inside has, hollow out 100 is digital, the pixel of each column
The sum of value is also more much smaller than the sum of each column pixel value of non-security line.Therefore where minimum continuous 15 column of the sum of pixel value
Image-region, as safety line region.
In S104, the characteristic parameter based on safety line region pixel: in mean value, variance and pixel number
At least one of, forge or true or paper money is detected.
Situation one:
Fig. 3 is the flow chart provided in an embodiment of the present invention detected based on mean value to forge or true or paper money.
S301 calculates the pixel value mean value of the safety line exterior domain;
S302, in the safety line region, extraction pixel value is less than the pixel value mean value of the safety line exterior domain
Pixel;
S303 calculates the mean value of the pixel extracted;
S304 exports paper if the mean value of the pixel extracted is less than the pixel value mean value of the safety line exterior domain
Coin is the testing result of genuine note;
S305 is exported if the mean value of the pixel extracted is not less than the pixel value mean value of the safety line exterior domain
Bank note is the testing result of counterfeit money.
Article 2 safety line region is not all the low value of pixel value, the pixel value of 100 printed words wherein included just compared with
It is high.The influence of these bright spots is excluded when calculating the mean value of safety line region.
Safety line region is had determined that in S103, then the pixel value that can calculate safety line exterior domain is equal
Value.Pixel value in safety line region is greater than the point of the pixel value mean value of safety line exterior domain, that is, is regarded as safety line
The point of 100 printed words in region will exclude 100 printed words when calculating the pixel value mean value of safety line region
Point.
Fig. 4 is the schematic diagram after the 5th set of 100 yuan note Article 2 safety line binaryzation provided in an embodiment of the present invention,
Middle Fig. 4 (a) is overall diagram, and it is that the gray value of the pixel on image is arranged that Fig. 4 (b), which is binaryzation described in partial enlarged view,
It is 0 or 255, that is, whole image is showed and significantly there was only black and white visual effect.In Fig. 3, white portion is
For 100 printed words.When calculating the mean value of pixel value of safety line region, the point of these 100 printed words is excluded.
Specifically, the pixel value mean value of the safety line region and the pixel value mean value of the safety line exterior domain
Difference is greater than third threshold value.
Preferably, the third threshold value is between 30-40.
In the embodiment of the present invention, processing to 100 printed words eliminates its interference to detection method, therefore inspection can be improved
The accuracy of survey.
Situation two:
Further, on the basis of situation one, Fig. 5 shows provided in an embodiment of the present invention true to bank note based on variance
The flow chart that puppet is detected.
S501 calculates the variance of the pixel extracted;
S502 exports the testing result that bank note is genuine note if the variance of the pixel extracted is less than first threshold;
S503 exports the testing result that bank note is counterfeit money if the variance of the pixel extracted is not less than first threshold.
Specifically,
The formula of the variance for calculating the pixel extracted are as follows:
Wherein, u indicates the pixel value mean value of safety line exterior domain, and m indicates to exclude picture in Article 2 safety line region
The mean value of pixel of the element value greater than u.
The first threshold is the variance of point of the Article 2 safety line region less than pixel value u, this variance yields is smaller,
Can be obtained based on the statistical value of a large amount of test samples, for example, take standard deviation be 15, indicate the area pixel value generally within
In positive and negative 15 range of mean value, corresponding variance is the pixel number * 15^2 extracted.
Variance is further verified on the basis of mean value, more improves the accuracy rate of detection.
Situation three:
Fig. 6 is the flow chart provided in an embodiment of the present invention detected based on pixel number to forge or true or paper money.
S601 counts the pixel number that safety line region pixel value is lower than second threshold;
S602 exports the testing result that bank note is genuine note if the pixel number is within a preset range;
S603, if the pixel number not within a preset range, exports the testing result that bank note is counterfeit money.
The second threshold is the number of point of the Article 2 safety line region less than pixel value u, because safety line accounts for
There are certain width and height, it is preferable that the second threshold is 2500.
Since the height of safety line is probably in 300 rows or so, width is in 15 column left and right, it is therefore preferred that the default model
It is trapped among between 2000~5000.
Further, if comprehensively considering situation one, situation two and situation three comprehensively consider the safety line region
Three mean value of pixel, variance and pixel number characteristic parameters, verifying while three parameters is so that detection forge or true or paper money
Accuracy rate is higher.
A kind of method of detection bank note safety line feature corresponding to the inventive embodiments, Fig. 7 show implementation of the present invention
A kind of structural block diagram of the device for detection bank note safety line that example provides illustrates only and the present embodiment phase for ease of description
The part of pass.
As shown in fig. 7, the device includes:
Single 71 are obtained, for obtaining the image-region comprising safety line;
First computing unit 72, for calculating the sum of the pixel value of each column in described image region;
Positioning unit 73, for image-region where the minimum continuous preset quantity column of the sum of the pixel value to be determined as
The safety line region;
Detection unit 74, for the characteristic parameter based on safety line region pixel: mean value, variance and pixel
At least one of in number, forge or true or paper money is detected.
The detection unit 74 includes:
Second computing unit, for calculating the pixel value mean value of the safety line exterior domain;
Extraction unit, for extracting the pixel that pixel value is less than the safety line exterior domain in the safety line region
It is worth the pixel of mean value;
Third computing unit, for calculating the mean value of the pixel extracted;
If the mean value of the pixel extracted is less than the pixel value mean value of the safety line exterior domain, it is true for exporting bank note
The testing result of coin;
If the mean value of the pixel extracted is not less than the pixel value mean value of the safety line exterior domain, exporting bank note is
The testing result of counterfeit money.
The detection unit 74 includes:
4th computing unit, for calculating the variance of the pixel extracted;
If the variance of the pixel extracted is less than first threshold, the testing result that bank note is genuine note is exported;
If the variance of the pixel extracted is not less than first threshold, the testing result that bank note is counterfeit money is exported.
The detection unit 74 includes:
5th computing unit, the pixel number for being lower than second threshold for counting safety line region pixel value;
If the pixel number is within a preset range, the testing result that bank note is genuine note is exported;
If the pixel number within a preset range, does not export the testing result that bank note is counterfeit money.
The acquiring unit 71 includes:
The image-region of the acquisition comprising safety line is to intercept to obtain from the infrared transmission figure where the safety line.
In embodiments of the present invention, the sum of the pixel value for calculating each column in the image-region of safety line, by the pixel
Image-region where the minimum continuous preset quantity column of the sum of value is determined as safety line region, according to the picture in the region outside safety line
Plain value mean value eliminates the influence of 100 printed words bright spot of safety line, and mean value, variance, pixel are comprehensively considered in safety line region
The detection method of number, so that the accuracy rate of detection forge or true or paper money improves.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (10)
1. a kind of method for detecting bank note safety line characterized by comprising
Obtain the image-region comprising safety line;
Calculate the sum of the pixel value of each column in described image region;
Image-region where the minimum continuous preset quantity column of the sum of the pixel value is determined as the safety line region;
At least one of characteristic parameter based on safety line region pixel: in mean value, variance and pixel number, it is right
Forge or true or paper money is detected.
2. the method as described in claim 1, which is characterized in that described to be detected to forge or true or paper money, comprising:
Calculate the pixel value mean value of the safety line exterior domain;
The pixel that pixel value is less than the pixel value mean value of the safety line exterior domain is extracted in the safety line region;
Calculate the mean value of the pixel extracted;
If the difference of the mean value of the pixel extracted and the pixel value mean value of the safety line exterior domain is greater than third threshold value,
Output bank note is the testing result of genuine note;
If the difference of the mean value of the pixel extracted and the pixel value mean value of the safety line exterior domain is not more than third threshold value,
Then export the testing result that bank note is counterfeit money.
3. method according to claim 2, which is characterized in that described to be detected to forge or true or paper money, comprising:
Calculate the variance of the pixel extracted;
If the variance of the pixel extracted is less than first threshold, the testing result that bank note is genuine note is exported;
If the variance of the pixel extracted is not less than first threshold, the testing result that bank note is counterfeit money is exported.
4. the method as described in claim 1, which is characterized in that described to be detected to forge or true or paper money, comprising:
Count the pixel number that safety line region pixel value is lower than second threshold;
If the pixel number is within a preset range, the testing result that bank note is genuine note is exported;
If the pixel number within a preset range, does not export the testing result that bank note is counterfeit money.
5. the method as described in claim 1, which is characterized in that the image-region of the acquisition comprising safety line is from the peace
It intercepts and obtains in infrared transmission figure where completely.
6. a kind of device for detecting bank note safety line characterized by comprising
Acquiring unit, for obtaining the image-region comprising safety line;
First computing unit, for calculating the sum of the pixel value of each column in described image region;
Positioning unit, for image-region where the minimum continuous preset quantity column of the sum of the pixel value to be determined as the peace
All fronts region;
Detection unit, for the characteristic parameter based on safety line region pixel: in mean value, variance and pixel number
At least one of, forge or true or paper money is detected.
7. device as claimed in claim 6, which is characterized in that the detection unit includes:
Second computing unit, for calculating the pixel value mean value of the safety line exterior domain;
Extraction unit, it is equal less than the pixel value of the safety line exterior domain for extracting pixel value in the safety line region
The pixel of value;
Third computing unit, for calculating the mean value of the pixel extracted;
If the difference of the mean value of the pixel extracted and the pixel value mean value of the safety line exterior domain is greater than third threshold value,
Output bank note is the testing result of genuine note;
If the difference of the mean value of the pixel extracted and the pixel value mean value of the safety line exterior domain is not more than third threshold value,
Then export the testing result that bank note is counterfeit money.
8. device as claimed in claim 7, which is characterized in that the detection unit includes:
4th computing unit, for calculating the variance of the pixel extracted;
If the variance of the pixel extracted is less than first threshold, the testing result that bank note is genuine note is exported;
If the variance of the pixel extracted is not less than first threshold, the testing result that bank note is counterfeit money is exported.
9. device as claimed in claim 6, which is characterized in that the detection unit includes:
5th computing unit, the pixel number for being lower than second threshold for counting safety line region pixel value;
If the pixel number is within a preset range, the testing result that bank note is genuine note is exported;
If the pixel number within a preset range, does not export the testing result that bank note is counterfeit money.
10. device as claimed in claim 6, which is characterized in that the image-region of the acquisition comprising safety line is from described
It intercepts and obtains in infrared transmission figure where safety line.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611141187.2A CN106710062B (en) | 2016-12-12 | 2016-12-12 | Detect the method and device of bank note safety line |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611141187.2A CN106710062B (en) | 2016-12-12 | 2016-12-12 | Detect the method and device of bank note safety line |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106710062A CN106710062A (en) | 2017-05-24 |
CN106710062B true CN106710062B (en) | 2019-04-26 |
Family
ID=58936880
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611141187.2A Expired - Fee Related CN106710062B (en) | 2016-12-12 | 2016-12-12 | Detect the method and device of bank note safety line |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106710062B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107610318B (en) * | 2017-08-23 | 2019-12-06 | 成都术有科技有限公司 | Method for discriminating 2015 edition RMB by utilizing metal wire backlight imaging |
CN108091033B (en) * | 2017-12-26 | 2020-10-20 | 深圳怡化电脑股份有限公司 | Paper money identification method and device, terminal equipment and storage medium |
CN108198322B (en) * | 2018-02-07 | 2020-03-27 | 深圳怡化电脑股份有限公司 | Magnetic stripe positioning method and device |
CN110956737B (en) * | 2020-01-07 | 2021-10-12 | 武汉卓目科技有限公司 | Safety line identification method and device |
CN111627145B (en) * | 2020-05-19 | 2022-06-21 | 武汉卓目科技有限公司 | Method and device for identifying fine hollow image-text of image |
CN111915792B (en) * | 2020-05-19 | 2022-06-07 | 武汉卓目科技有限公司 | Method and device for identifying zebra crossing image-text |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2230647A1 (en) * | 2006-09-29 | 2010-09-22 | Aruze Corp. | Sheet identifying device |
CN104778778A (en) * | 2015-03-23 | 2015-07-15 | 深圳怡化电脑股份有限公司 | Money checking method and system |
EP2899698A1 (en) * | 2014-01-27 | 2015-07-29 | Glory Ltd. | Banknote processing apparatus and banknote processing method |
CN105303677A (en) * | 2015-10-29 | 2016-02-03 | 深圳怡化电脑股份有限公司 | Method and apparatus for obtaining boundary of banknote security thread |
CN106127930A (en) * | 2016-06-17 | 2016-11-16 | 深圳怡化电脑股份有限公司 | A kind of method and system detecting banknote security line integrity |
-
2016
- 2016-12-12 CN CN201611141187.2A patent/CN106710062B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2230647A1 (en) * | 2006-09-29 | 2010-09-22 | Aruze Corp. | Sheet identifying device |
EP2899698A1 (en) * | 2014-01-27 | 2015-07-29 | Glory Ltd. | Banknote processing apparatus and banknote processing method |
CN104778778A (en) * | 2015-03-23 | 2015-07-15 | 深圳怡化电脑股份有限公司 | Money checking method and system |
CN105303677A (en) * | 2015-10-29 | 2016-02-03 | 深圳怡化电脑股份有限公司 | Method and apparatus for obtaining boundary of banknote security thread |
CN106127930A (en) * | 2016-06-17 | 2016-11-16 | 深圳怡化电脑股份有限公司 | A kind of method and system detecting banknote security line integrity |
Also Published As
Publication number | Publication date |
---|---|
CN106710062A (en) | 2017-05-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106710062B (en) | Detect the method and device of bank note safety line | |
CN107085883B (en) | A kind of method and apparatus of paper money recognition | |
CN104091388B (en) | A kind of paper money discrimination method based on magnetic image and device | |
CN105787929B (en) | Skin rash point extracting method based on spot detection | |
CN104992496A (en) | Paper money face identification method and apparatus | |
CN102005078A (en) | Method and device for recognizing paper currencies and tickets | |
CN102324132A (en) | Bank-note detecting method by identifying ultraviolet-light image and system | |
CN106355744B (en) | A kind of recognition methods of Indonesian Rupiah value of money and device | |
CN104680145B (en) | The on off state change detecting method and device of a kind of | |
CN103886309A (en) | Method for identifying dollar denominations through facial recognition | |
Sharan et al. | Detection of counterfeit Indian currency note using image processing | |
CN106780954A (en) | A kind of method and device of paper money recognition | |
CN106780965B (en) | A kind of Paper Currency Identification and device | |
CN106683261B (en) | A kind of false distinguishing method and apparatus of bank note | |
CN106485828B (en) | A kind of Paper Currency Identification and device | |
CN106600812B (en) | Paper money identification method and device | |
CN108806058A (en) | A kind of paper currency detecting method and device | |
CN106447910B (en) | A kind of method and device of paper money recognition | |
CN107742357A (en) | A kind of recognition methods of paper money number and device | |
CN106934922A (en) | A kind of paper currency detecting method and device | |
CN106447897A (en) | Method and apparatus for detecting magnetic characteristics of paper note | |
CN107527423B (en) | Paper money anti-counterfeiting identification method and paper money identification device | |
CN103489255A (en) | Device and method for detecting defect of bank note | |
CN108711213A (en) | A kind of recognition methods of bank note zebra stripes black and white block and device | |
CN106447908A (en) | Paper money authentic identification method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190426 Termination date: 20211212 |