CN107170108B - A kind of splicing paper money detection method and system - Google Patents
A kind of splicing paper money detection method and system Download PDFInfo
- Publication number
- CN107170108B CN107170108B CN201710248567.4A CN201710248567A CN107170108B CN 107170108 B CN107170108 B CN 107170108B CN 201710248567 A CN201710248567 A CN 201710248567A CN 107170108 B CN107170108 B CN 107170108B
- Authority
- CN
- China
- Prior art keywords
- pixel
- image
- counterfeiting
- characteristic value
- image feature
- 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
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
- G07D7/2016—Testing patterns thereon using feature extraction, e.g. segmentation, edge detection or Hough-transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- 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
- G07D7/2041—Matching statistical distributions, e.g. of particle sizes orientations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
The present invention is suitable for financial technology field, provides a kind of splicing paper money detection method and system.The present invention obtains residual pixel by the object pixel in anti-counterfeiting image feature region in removal banknote image, and the characteristic value in other regions of at least one of the characteristic value of residual pixel and banknote image is compared, can accurately judge whether true bank note corresponding to banknote image is splicing paper money, and deterministic process is simple and is easily achieved.
Description
Technical field
The invention belongs to financial technology field more particularly to a kind of splicing paper money detection methods and system.
Background technique
Splicing paper money is artificial by multiple bank note, is connected by technical treatment into one banknote.Splice paper money according to true and false coin
Connecting method is divided into three classes: counterfeit money spells counterfeit money, counterfeit money spells genuine notes, genuine notes spell genuine notes.Criminal is made by illegal means and is spelled
Paper money is connect to extract complete genuine notes, brings serious negative effect to money flow.
However, the paper money identification equipments such as existing cash inspecting machine, are typically only capable to the true and false of identification bank note, without that can accurately know
Not Pin Jie paper money, how quickly and effectively to identify splicing paper money, prevent criminal and with splicing paper money malice exchange genuine notes and become urgently to solve
Certainly the problem of.
Summary of the invention
The embodiment of the invention provides a kind of splicing paper money detection method and systems, it is intended to solve the bank note such as existing cash inspecting machine
It identifies equipment, is typically only capable to the true and false of identification bank note, without that can accurately identify the problem of splicing paper money.
The first aspect of the embodiment of the present invention provides a kind of splicing paper money detection method, comprising:
Position of the positioning anti-fake characteristics of image in banknote image;
Algorithm is removed according to the position and presetted pixel, removes the target picture in anti-counterfeiting image feature region
Element obtains the residual pixel in anti-counterfeiting image feature region;
The characteristic value and the pixel at least one predeterminable area in the banknote image for comparing the residual pixel
Whether characteristic value matches, at least one described predeterminable area does not include anti-counterfeiting image feature region;
If mismatching, true bank note corresponding to the banknote image is determined to splice paper money;Otherwise, it is determined that the bank note
True bank note corresponding to image is not splicing paper money.
The second aspect of the embodiment of the present invention provides a kind of splicing paper money detection system, comprising:
Locating module, for position of the positioning anti-fake characteristics of image in banknote image;
Processes pixel module removes the anti-counterfeiting image feature for removing algorithm according to the position and presetted pixel
Object pixel in region obtains the residual pixel in anti-counterfeiting image feature region;
Matching detection module, the characteristic value and at least one of the banknote image for the residual pixel are pre-
If whether the characteristic value of the pixel in region matches, at least one described predeterminable area does not include the anti-counterfeiting image feature place
Region;
Result judgement module, if determining true bank note corresponding to the banknote image for mismatching to splice paper money;
Otherwise, it is determined that true bank note corresponding to the banknote image is not splicing paper money.
Existing beneficial effect is the embodiment of the present invention compared with prior art: passing through anti-counterfeiting image in removal banknote image
Object pixel in feature region obtains residual pixel, and by least one in the characteristic value and banknote image of residual pixel
The characteristic value in other a regions is compared, and can accurately judge whether true bank note corresponding to banknote image is splicing
Paper money, deterministic process is simple and is easily achieved.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is a kind of implementation flow chart for splicing paper money detection method that one embodiment of the present of invention provides;
Fig. 2 is the implementation flow chart of step S102 in Fig. 1 of one embodiment of the present of invention offer;
Fig. 3 is the implementation flow chart of step S103 in Fig. 1 of one embodiment of the present of invention offer;
Fig. 4 is a kind of structural block diagram for splicing paper money detection system that one embodiment of the present of invention provides;
Fig. 5 is the structural block diagram of processes pixel module in Fig. 4 of one embodiment of the present of invention offer;
Fig. 6 is the structural block diagram of matching detection module in Fig. 4 of one embodiment of the present of invention offer.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
As shown in Figure 1, a kind of splicing paper money detection method provided for one embodiment of the present of invention comprising:
Step S101, position of the positioning anti-fake characteristics of image in banknote image.
Specifically, anti-counterfeiting image feature includes at least one of following characteristics: serial number, photochromatic printing ink character, watermark,
Offset printing microfilm of characters, holographic magnetic opened window safety line, offset printing to be patterned, hand engraving head portrait, stealthy denomination number or engraving
Intaglio printing.
Specifically, the present embodiment further include:
(1) region that is likely to occur of the anti-counterfeiting image feature in banknote image, as Probability Area are obtained, interception may
Region, and binary conversion treatment is carried out to the gray level image of Probability Area.Such as the rmb paper currency for being 100 yuan for face amount, if
Determining the region where photochromatic printing ink " 100 " printed words is Probability Area, in the gray level image after binary conversion treatment in the region
The gray value of " 100 " printed words is 0, and the gray value of remaining area is 1.
(2) it on the bianry image of Probability Area, moves a moving window in order line by line, obtains moving window
The pixel accumulated value of region after each movement, moving window is throughout all positions of Probability Area, according to pixel accumulated value
Variation determine position of the anti-counterfeiting image feature in banknote image.
In one embodiment, further comprising the steps of before step S101:
A. the banknote image of bank note to be detected is obtained;
B. the boundary of the anti-counterfeiting image feature is obtained according to the texture of banknote image and gray value;
C. anti-counterfeiting image feature is obtained according to boundary.
Specifically, step a can be realized by shooting or scanning mode, with infrared light or ultraviolet light shooting function or
The terminal of person's white light or multispectral shooting function shoots or scans bank note to be measured, obtains banknote image.For example, can be by having
White light or multispectral image shooting function or camera with ultraviolet light, single irradiation shooting function of infrared light are realized;It is more
Spectrograph refers to while being mixed into a kind of mixing light source using the light source of multiple Single wavelengths, and several that target can be obtained do not share the same light
The photo of irradiation is composed, wherein spectral region is visible light, ultraviolet light and infrared light.
It should be noted that in stepb, texture is a kind of visual signature for reflecting homogeneity phenomenon in image, it is embodied
Body surface has slowly varying or periodically variable surface textural alignment attribute.Specifically, can use
A variety of methods extract the textural characteristics of banknote image, such as statistical method, geometric method, modelling or signal processing method.Gray value
Acquisition is to obtain gray value according to the red, green, blue color component of banknote image.
Further, since the characteristic value of both characteristic values of anti-counterfeiting image feature and its periphery background image has difference
Not, therefore using the boundary of the available anti-counterfeiting image feature of picture edge characteristic extraction algorithm.Picture edge characteristic extraction algorithm
Specifically includes the following steps:
(1) it filters, banknote image is filtered;
(2) enhance, highlight target area and other regions Zhong Te by corresponding to gradient magnitude in enhancing image
The significant changes of value indicative;
(3) it detects, by judging that threshold size obtains edge detection in gradient magnitude;
(4) it positions, the accurate position for determining edge.
Specifically, the image of border inner is anti-counterfeiting image feature in step c.
Step S102 removes algorithm according to the position and presetted pixel, removes in anti-counterfeiting image feature region
Object pixel obtains the residual pixel in anti-counterfeiting image feature region.
In the present embodiment, it is that specific single or multiple pictures are removed according to the different characteristic of each pixel that pixel, which removes algorithm,
Vegetarian refreshments.Object pixel refers to all pixels of anti-counterfeiting image feature itself.Residual pixel is removal anti-counterfeiting image feature location
Residual pixel after object pixel in domain, in region.
Such as be 100 yuan of rmb paper currency for face amount, set photochromatic printing ink " 100 " character as anti-counterfeiting image feature,
A fixed area on bank note where " 100 " printed words is anti-counterfeiting image feature region, the shape of the fixed area,
Long or wide equidimension is in advance preset.Then object pixel is the included all pixels of " 100 " character itself, residual pixel
For the pixel for removing the residual image after " 100 " character in the fixed area.
It should be noted that anti-counterfeiting image feature, such as serial number, photochromatic printing ink character etc., frequently include font or
Decorative pattern, due to its special printing technology, so that its optical signature is very special, it is difficult to obtain stable characteristic value and be carried out to it
Detection.Therefore, the object pixel removed in the present embodiment in anti-counterfeiting image feature region obtains residual pixel, avoids anti-
Influence of the unstability of pseudo- characteristics of image to feature extraction in subsequent step itself, improves accuracy in detection.
Specifically, it is adaptive threshold Binarization methods that presetted pixel, which removes algorithm, as a preferred embodiment.
Adaptive threshold is the binaryzation threshold determined on the location of pixels according to the pixel Distribution value of the neighborhood block of pixel
Value.This have the advantage that the binarization threshold of each pixel position is not fixed and invariable, but by its surrounding neighbors
Pixel is distributed to determine.The binarization threshold of the higher image-region of brightness would generally be higher, and the lower image of brightness
The binarization threshold in region then can adaptably become smaller.Different brightness, contrast, texture local image region will possess phase
Corresponding local binarization threshold value.Common adaptive threshold has: 1) mean value of local neighborhood block, 2) Gauss of local neighborhood block
Weighted sum.
The problems such as there are new and old and abrasions due to bank note, has interference to its gray level image, passes through adaptive threshold two-value
Change algorithm, binary conversion treatment is carried out to the gray level image of the intercepted Probability Area, compared to passing through fixed threshold algorithm
It is more accurate to handle obtained bianry image.
Step S103 compares the pixel at least one predeterminable area in the characteristic value and banknote image of residual pixel
Whether characteristic value matches, at least one described predeterminable area does not include anti-counterfeiting image feature region.
In one embodiment, before step S103, further includes: according to default feature extraction algorithm, obtain residual pixel
Characteristic value and banknote image at least one predeterminable area in pixel characteristic value.
Specifically, the default feature extraction algorithm is gray feature extracting method or texture characteristic extracting method.
At least one of characteristic value and banknote image of the residual pixel obtained using gray feature extracting method are preset
The characteristic value of pixel in region is gray value of image.
At least one of characteristic value and banknote image of the residual pixel obtained using texture characteristic extracting method are preset
The characteristic value of pixel in region is texture eigenvalue.Specifically, texture eigenvalue includes k rank moment of the orign, such as second moment, three
Rank square etc..
The feature of residual pixel is obtained using the object pixel in removal anti-counterfeiting image feature region in the present embodiment
Value, the unstability for avoiding anti-counterfeiting image feature itself make the result inaccuracy of feature extraction, result in a feature that value
Inaccuracy with result, using the spy of the pixel at least one predeterminable area in the characteristic value and banknote image of residual pixel
Value indicative is compared, it is ensured that the stability that characteristic value obtains improves characteristic matching accuracy.
Step S104 determines true bank note corresponding to the banknote image if mismatching to splice paper money;Otherwise, sentence
True bank note corresponding to the fixed banknote image is not splicing paper money.
Specifically, step S104 further include:
By statistic algorithm, the range of the characteristic value of the pixel at least one predeterminable area in banknote image is obtained;
Judge the characteristic value of residual pixel whether in the range;
If being judged to mismatching not in the range;If being judged to matching in the range.
In a particular application, determine that bank note refers to that bank note is spliced for genuine notes and counterfeit money for splicing paper money.When judgement bank note
It is not splicing paper money, it is also necessary to verify whether this bank note is inspection that counterfeit money could complete forge or true or paper money using forge or true or paper money detection method
It surveys.
As shown in Fig. 2, in one embodiment of the invention, the step S102 in embodiment corresponding to Fig. 1 is specifically wrapped
It includes:
Step S201, according to the position, by having including the anti-counterfeiting image feature in the banknote image
The predeterminable area of default fixed shape is as anti-counterfeiting image feature region.
Step S202 carries out image binaryzation processing to anti-counterfeiting image feature region.
Step S203, according to image binaryzation processing as a result, removing the target picture in anti-counterfeiting image feature region
Element obtains the residual pixel in anti-counterfeiting image feature region.
In a particular application, in step S201, there is the predeterminable area of default fixed shape to refer to the shape and ruler in region
Very little size is preset fixed value.For example, predeterminable area is rectangle, width and height are fixed value, then anti-counterfeiting image feature
Region can determine.Predeterminable area can also be other shapes, such as circle, triangle etc..
Specifically, step S202 includes: to be carried out according to predeterminable area of the adaptive threshold Binarization methods to banknote image
Image binaryzation processing.
The object pixel removed in anti-counterfeiting image feature region in the present embodiment obtains residual pixel, avoids anti-fake
Influence of the unstability of characteristics of image to feature extraction in subsequent step itself, improves accuracy in detection.
As shown in figure 3, in one embodiment of the invention, the step S103 in embodiment corresponding to Fig. 1 is specifically wrapped
It includes:
Step S301 obtains the residual pixel in anti-counterfeiting image feature region according to default feature extraction algorithm
Characteristic value.
Step S302 obtains the picture at least one predeterminable area in banknote image according to default feature extraction algorithm
The characteristic value of element;
Step S303 removes the extreme value in the characteristic value of the pixel at least one predeterminable area in banknote image;
Step S304, by the characteristic value of residual pixel with remove at least one predeterminable area in the banknote image after extreme value
In the characteristic value of pixel be compared.
Specifically, the default feature extraction algorithm is gray feature extracting method or texture characteristic extracting method.
Specifically, in step S303, remove extreme value using gymnastics point-score, removes highest N number of value and minimum N number of
Value.Due to inevitably there is dirty or fold on bank note, changes acutely on the gray level image of various wave bands, affect the spy of extraction
Value indicative.And most of dirty or fold will not be throughout entire bank note, and often only some is locally present, and results in a feature that value
In have maximum value or minimum value presence.In the characteristic value for removing the pixel at least one predeterminable area in banknote image
Extreme value can exclude most dirty or fold influences.
The embodiment of the present invention is remained by the object pixel in anti-counterfeiting image feature region in removal banknote image
Afterimage element, and the characteristic value in other regions of at least one of the characteristic value of residual pixel and banknote image is compared, it can
Accurately to judge whether true bank note corresponding to banknote image is splicing paper money, deterministic process is simple and is easily achieved.
As shown in figure 4, for a kind of splicing paper money detection system 100 that one embodiment of the present of invention provides, for executing Fig. 1
Method and step in corresponding embodiment comprising:
Locating module 101, for position of the positioning anti-fake characteristics of image in banknote image;
It is special to remove the anti-counterfeiting image for removing algorithm according to the position and presetted pixel for processes pixel module 102
The object pixel in region is levied, the residual pixel in anti-counterfeiting image feature region is obtained;
Matching detection module 103, at least one in the characteristic value and the banknote image of the residual pixel
Whether the characteristic value of the pixel in a predeterminable area matches, at least one described predeterminable area does not include the anti-counterfeiting image feature
Region;
Result judgement module 104, if determining true bank note corresponding to the banknote image for splicing for mismatching
Paper money;Otherwise, it is determined that true bank note corresponding to the banknote image is not splicing paper money.
In a particular application, splicing above-mentioned each module included by paper money detection system 100 can be in picture processing chip
Software program module, user can according to actual needs be adjusted the function of these program modules.
As shown in figure 5, in one embodiment of the invention, the processes pixel module 102 in Fig. 4 includes for executing figure
The structure of method and step in embodiment corresponding to 2 comprising:
Region setup unit 201, for will include the anti-counterfeiting image feature in the banknote image according to the position
Having inside presets the predeterminable area for fixing shape as anti-counterfeiting image feature region;
Binary conversion treatment unit 202, for carrying out image binaryzation processing to anti-counterfeiting image feature region;
Pixel removal unit 203, for according to described image binary conversion treatment as a result, removing the anti-counterfeiting image feature
Object pixel in region obtains the residual pixel in anti-counterfeiting image feature region.
As shown in fig. 6, in one embodiment of the invention, the matching detection module 103 in Fig. 4 includes for executing figure
The structure of method and step in embodiment corresponding to 3 comprising:
Fisrt feature extraction unit 301, for according to feature extraction algorithm is preset, obtaining the anti-counterfeiting image feature place
The characteristic value of residual pixel in region;
Second feature extraction unit 302, for obtaining in the banknote image at least according to feature extraction algorithm is preset
The characteristic value of pixel in one predeterminable area;
Extreme value processing unit 303, for removing the spy of the pixel at least one predeterminable area in the banknote image
Extreme value in value indicative;
Feature comparing unit 304, for by the characteristic value of the residual pixel with remove the banknote image after extreme value
In at least one predeterminable area in the characteristic value of pixel be compared.
The feature of residual pixel is obtained using the object pixel in removal anti-counterfeiting image feature region in the present embodiment
Value, the unstability for avoiding anti-counterfeiting image feature itself make the result inaccuracy of feature extraction, result in a feature that value
Inaccuracy with result, using the spy of the pixel at least one predeterminable area in the characteristic value and banknote image of residual pixel
Value indicative is compared, it is ensured that the stability that characteristic value obtains improves characteristic matching accuracy.
In one embodiment, splice paper money detection system 100 further include:
Image collection module, for obtaining the banknote image of bank note to be measured;
Boundary obtains module, obtains the anti-counterfeiting image feature for the texture and gray value according to the banknote image
Boundary;
Anti-counterfeiting image obtains module, for obtaining the anti-counterfeiting image feature according to the boundary.
Specifically, the anti-counterfeiting image feature includes at least one of following characteristics: serial number, photochromatic printing ink character,
Watermark, offset printing microfilm of characters, holographic magnetic opened window safety line, offset printing to be patterned, hand engraving head portrait, stealthy denomination number or
Intaglio ink.
Module or unit in all embodiments of the invention can pass through universal integrated circuit, such as CPU (Central
Processing Unit, central processing unit), or pass through ASIC (Application Specific Integrated
Circuit, specific integrated circuit) Lai Shixian.
The steps in the embodiment of the present invention can be sequentially adjusted, merged and deleted according to actual needs.
Module or unit in system of the embodiment of the present invention can be combined, divided and deleted according to actual needs.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
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 (8)
1. a kind of splicing paper money detection method characterized by comprising
Position of the positioning anti-fake characteristics of image in banknote image;
Algorithm is removed according to the position and presetted pixel, removes the object pixel in anti-counterfeiting image feature region,
Obtain the residual pixel in anti-counterfeiting image feature region;Wherein, the presetted pixel removal algorithm is adaptive thresholding
It is worth Binarization methods, adaptive threshold is on the position for determine the pixel according to the pixel Distribution value of the contiguous block of pixel
Binarization threshold;Wherein, the object pixel refers to all pixels of anti-counterfeiting image feature itself;
Compare the feature of the characteristic value of the residual pixel and the pixel at least one predeterminable area in the banknote image
Whether value matches, at least one described predeterminable area does not include anti-counterfeiting image feature region;It specifically includes: according to pre-
If feature extraction algorithm, the characteristic value of the residual pixel in anti-counterfeiting image feature region is obtained;According to default feature
Extraction algorithm obtains the characteristic value of the pixel at least one predeterminable area in the banknote image;Remove the bank note figure
Extreme value in the characteristic value of the pixel at least one predeterminable area as in;By the characteristic value of the residual pixel and remove pole
The characteristic value of the pixel at least one predeterminable area in the banknote image after value is compared;
If mismatching, true bank note corresponding to the banknote image is determined to splice paper money;Otherwise, it is determined that the banknote image
Corresponding true bank note is not splicing paper money;
If described mismatch, true bank note corresponding to the banknote image is determined to splice paper money;Otherwise, it is determined that the bank note
True bank note corresponding to image is not splicing paper money further include:
By statistic algorithm, the range of the characteristic value of the pixel at least one predeterminable area in banknote image is obtained;
Judge the characteristic value of the residual pixel whether in the range;
If being judged as mismatch not in the range;If being judged to matching in the range.
2. a kind of splicing paper money detection method as described in claim 1, which is characterized in that described according to the position and default picture
Element removal algorithm, removes the object pixel in anti-counterfeiting image feature region, obtains the anti-counterfeiting image feature place
Residual pixel in region, specifically includes:
According to the position, having including the anti-counterfeiting image feature in the banknote image is preset into fixed shape
Predeterminable area is as anti-counterfeiting image feature region;
Image binaryzation processing is carried out to anti-counterfeiting image feature region;
According to described image binary conversion treatment as a result, remove the object pixel in anti-counterfeiting image feature region, obtain
To the residual pixel in anti-counterfeiting image feature region.
3. a kind of splicing paper money detection method as described in claim 1, which is characterized in that the positioning anti-fake characteristics of image is in paper
Before position on coin image, comprising:
Obtain the banknote image of bank note to be measured;
The boundary of the anti-counterfeiting image feature is obtained according to the texture of the banknote image and gray value;
The anti-counterfeiting image feature is obtained according to the boundary.
4. a kind of splicing paper money detection method as described in any one of claims 1 to 3, which is characterized in that the anti-counterfeiting image is special
Sign includes at least one of following characteristics: serial number, photochromatic printing ink character, watermark, offset printing microfilm of characters, holographic magnetic windowing
Safety line, offset printing to be patterned, hand engraving head portrait, stealthy denomination number or intaglio ink.
5. a kind of splicing paper money detection system characterized by comprising
Locating module, for position of the positioning anti-fake characteristics of image in banknote image;
Processes pixel module removes the anti-counterfeiting image feature place for removing algorithm according to the position and presetted pixel
Object pixel in region obtains the residual pixel in anti-counterfeiting image feature region;Wherein, the default removal is calculated
Method is adaptive threshold Binarization methods, and adaptive threshold is that the picture is determined according to the pixel Distribution value of the contiguous block of pixel
Binarization threshold on the position of element;Wherein, the object pixel refers to all pixels of anti-counterfeiting image feature itself;
Matching detection module, at least one preset areas in the characteristic value and the banknote image of the residual pixel
Whether the characteristic value of the pixel in domain matches, at least one described predeterminable area does not include anti-counterfeiting image feature location
Domain;
Result judgement module, if determining true bank note corresponding to the banknote image for mismatching to splice paper money;It is no
Then, determining true bank note corresponding to the banknote image not is splicing paper money, comprising: by statistic algorithm, obtains banknote image
In at least one predeterminable area in pixel characteristic value range;Judge the characteristic value of the residual pixel whether described
In range;If being judged as mismatch not in the range;If being judged to matching in the range;
The matching detection module includes:
Fisrt feature extraction unit, for obtaining in anti-counterfeiting image feature region according to feature extraction algorithm is preset
Residual pixel characteristic value;
Second feature extraction unit, for it is pre- to obtain at least one of described banknote image according to feature extraction algorithm is preset
If the characteristic value of the pixel in region;
Extreme value processing unit, in the characteristic value for removing the pixel at least one predeterminable area in the banknote image
Extreme value;
Feature comparing unit, for by the characteristic value of the residual pixel with remove in the banknote image after extreme value at least
The characteristic value of pixel in one predeterminable area is compared.
6. a kind of splicing paper money detection system as claimed in claim 5, which is characterized in that the processes pixel module includes:
Region setup unit, for according to the position, by the banknote image including the anti-counterfeiting image feature
Predeterminable area with default fixed shape is as anti-counterfeiting image feature region;
Binary conversion treatment unit, for carrying out image binaryzation processing to anti-counterfeiting image feature region;
Pixel removal unit, for according to described image binary conversion treatment as a result, removing anti-counterfeiting image feature location
Object pixel in domain obtains the residual pixel in anti-counterfeiting image feature region.
7. a kind of splicing paper money detection system as claimed in claim 5, which is characterized in that further include:
Image collection module, for obtaining the banknote image of bank note to be measured;
Boundary obtains module, obtains the side of the anti-counterfeiting image feature for the texture and gray value according to the banknote image
Boundary;
Anti-counterfeiting image obtains module, for obtaining the anti-counterfeiting image feature according to the boundary.
8. such as a kind of described in any item splicing paper money detection systems of claim 5 to 7, which is characterized in that the anti-counterfeiting image is special
Sign includes at least one of following characteristics: serial number, photochromatic printing ink character, watermark, offset printing microfilm of characters, holographic magnetic windowing
Safety line, offset printing to be patterned, hand engraving head portrait, stealthy denomination number or intaglio ink.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710248567.4A CN107170108B (en) | 2017-04-17 | 2017-04-17 | A kind of splicing paper money detection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710248567.4A CN107170108B (en) | 2017-04-17 | 2017-04-17 | A kind of splicing paper money detection method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107170108A CN107170108A (en) | 2017-09-15 |
CN107170108B true CN107170108B (en) | 2019-08-23 |
Family
ID=59849228
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710248567.4A Active CN107170108B (en) | 2017-04-17 | 2017-04-17 | A kind of splicing paper money detection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107170108B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108062820B (en) * | 2017-11-29 | 2019-10-15 | 深圳怡化电脑股份有限公司 | A kind of paper currency detecting method, note detection device and electronic equipment |
CN111341006B (en) * | 2020-02-28 | 2022-01-25 | 深圳怡化电脑股份有限公司 | Hidden magnetic stripe paper money identification method, system, server and storage medium |
CN111815848B (en) * | 2020-03-09 | 2021-08-24 | 广州康艺电子有限公司 | Big data type printing plate type identification method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102890840A (en) * | 2012-08-22 | 2013-01-23 | 山东新北洋信息技术股份有限公司 | Method and device for identifying paper money |
CN104361674A (en) * | 2014-09-30 | 2015-02-18 | 浙江维融电子科技股份有限公司 | Paper money recognition method and device |
CN104809800A (en) * | 2015-04-14 | 2015-07-29 | 深圳怡化电脑股份有限公司 | Preprocessing method for extracting banknote splicing mark, spliced banknote recognition method and device |
CN104851184A (en) * | 2015-05-27 | 2015-08-19 | 深圳怡化电脑股份有限公司 | Recognition method of transversely spliced banknote and device thereof |
CN105447956A (en) * | 2015-11-06 | 2016-03-30 | 东方通信股份有限公司 | Spliced banknote detection method |
CN205670338U (en) * | 2016-06-17 | 2016-11-02 | 光荣电子工业(苏州)有限公司 | There is the cleaning-sorting machine of the splicing pseudo-function of coin inspection |
-
2017
- 2017-04-17 CN CN201710248567.4A patent/CN107170108B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102890840A (en) * | 2012-08-22 | 2013-01-23 | 山东新北洋信息技术股份有限公司 | Method and device for identifying paper money |
CN104361674A (en) * | 2014-09-30 | 2015-02-18 | 浙江维融电子科技股份有限公司 | Paper money recognition method and device |
CN104809800A (en) * | 2015-04-14 | 2015-07-29 | 深圳怡化电脑股份有限公司 | Preprocessing method for extracting banknote splicing mark, spliced banknote recognition method and device |
CN104851184A (en) * | 2015-05-27 | 2015-08-19 | 深圳怡化电脑股份有限公司 | Recognition method of transversely spliced banknote and device thereof |
CN105447956A (en) * | 2015-11-06 | 2016-03-30 | 东方通信股份有限公司 | Spliced banknote detection method |
CN205670338U (en) * | 2016-06-17 | 2016-11-02 | 光荣电子工业(苏州)有限公司 | There is the cleaning-sorting machine of the splicing pseudo-function of coin inspection |
Also Published As
Publication number | Publication date |
---|---|
CN107170108A (en) | 2017-09-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Guo et al. | A reliable method for paper currency recognition based on LBP | |
CN107085883B (en) | A kind of method and apparatus of paper money recognition | |
KR101883425B1 (en) | Method for differentiation forgery by portable terminal device | |
CN104616392B (en) | A kind of paper money discrimination method based on local binary patterns | |
CN107170108B (en) | A kind of splicing paper money detection method and system | |
CN107103683B (en) | Paper money identification method and device, electronic equipment and storage medium | |
Wang et al. | Image forgery forensics based on manual blurred edge detection | |
CN103886309A (en) | Method for identifying dollar denominations through facial recognition | |
CN107437293A (en) | A kind of bill anti-counterfeit discrimination method based on bill global characteristics | |
CN106845469B (en) | Paper money identification method and device | |
Sharan et al. | Detection of counterfeit Indian currency note using image processing | |
CN108780506A (en) | Use the counterfeit detection scheme of paper surface and mobile camera | |
WO2007105890A1 (en) | Recognizing the denomination of a note using wavelet transform | |
CN108830275A (en) | Dot character, the recognition methods of dot matrix digit and device | |
Guarnera et al. | A new study on wood fibers textures: documents authentication through LBP fingerprint | |
CN106599923B (en) | Method and device for detecting seal anti-counterfeiting features | |
CN112990166B (en) | Face authenticity identification method and device and electronic equipment | |
CN107527423B (en) | Paper money anti-counterfeiting identification method and paper money identification device | |
Ponishjino et al. | Bogus currency authorization using HSV techniques | |
Amirsab et al. | An automated recognition of fake or destroyed Indian currency notes | |
Ansari et al. | A robust method for identification of paper currency using otsu’s thresholding | |
JP6860151B2 (en) | Printed matter reading inspection method and its equipment, and printed matter reading inspection software | |
Colaco et al. | Efficient Image Processing Technique for Authentication of Indian Paper Currency | |
CN108537945B (en) | Bill watermark detection method and system and self-service equipment | |
CN108171865B (en) | Paper money detection method, paper money detection device and electronic equipment |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |