CN106599923A - Detecting method and detecting device for stamped anti-counterfeiting characteristic - Google Patents
Detecting method and detecting device for stamped anti-counterfeiting characteristic Download PDFInfo
- Publication number
- CN106599923A CN106599923A CN201611168869.2A CN201611168869A CN106599923A CN 106599923 A CN106599923 A CN 106599923A CN 201611168869 A CN201611168869 A CN 201611168869A CN 106599923 A CN106599923 A CN 106599923A
- Authority
- CN
- China
- Prior art keywords
- image
- counterfeiting characteristic
- detection
- counterfeiting
- characteristic image
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000009466 transformation Effects 0.000 claims abstract description 19
- 238000001514 detection method Methods 0.000 claims description 135
- 230000004927 fusion Effects 0.000 claims description 46
- 238000000605 extraction Methods 0.000 claims description 18
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 239000000284 extract Substances 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 238000007689 inspection Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 10
- 230000005540 biological transmission Effects 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 9
- 230000011218 segmentation Effects 0.000 description 9
- 238000010606 normalization Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 235000001968 nicotinic acid Nutrition 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000012925 reference material Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
The invention discloses a detecting method and a detecting device for a stamped anti-counterfeiting characteristic. The detecting method comprises the steps of extracting anti-counterfeiting characteristic information of a first detecting image and generating a first anti-counterfeiting characteristic image through acquiring the first detecting image and a second detecting image of a to-be-detected object; extracting anti-counterfeiting characteristic information of the second detecting image, performing mirror image transformation and generating a second anti-counterfeiting characteristic image; fusing the first anti-counterfeiting characteristic image and the second anti-counterfeiting characteristic image and generating a fused anti-counterfeiting characteristic image; performing matching on the fused anti-counterfeiting characteristic image and a standard anti-counterfeiting characteristic image in a preset template, and determining the to-be-detected object is true or false according to the matching result. According to the detecting method and the detecting device, acquisition of visible light reflection images on a front surface and a back surface is required, and acquisition of a visible light transmission image is not required. On the condition that high stamped anti-counterfeiting characteristic detecting performance is ensured, cost equipment is effectively reduced, and furthermore a complicated algorithm in image splicing technology is not required. Furthermore a performance requirement to a digital signal processor is reduced.
Description
Technical field
The present invention relates to anti-counterfeiting detection technical field, more particularly to a kind of detection method and dress to printing anti-counterfeiting characteristic
Put.
Background technology
Mainly a complete security pattern is divided into into some sub-regions, part subregion print to printing anti-counterfeiting technology
In the front of banknote, part subregion is printed on the reverse side of banknote to brush, and front reverse side all subregion junction is neither ruptured and is left white
Do not misplace again overlapping, all subregion combines to form complete security pattern.
Multi national river possess to print anti-counterfeiting characteristic, such as galloping horse pattern of 10 yuan of plastics coin of Hong-Kong government, Euro
Denomination numeral to being patterned, 99 editions, 05 edition yin yang complementarity ancient money of RMB to being patterned, the space of a whole page volume digital pattern of RMB 15
Deng.The type anti-counterfeiting characteristic belongs to public's anti-counterfeiting characteristic, is by human eye without professional equipment instrument in general
False proof judgement can be carried out, inspection method is met light and observes integrity to being patterned for human eye, check that image has dislocation-free overlapping etc..
It is existing to printing detection method typically using visible transmission imageing sensor and visible from bionics angle
Light reflected image sensor carries out image acquisition, and using technologies such as image mosaics visible reflectance image mosaic is completed, it will be seen that
Light reflection is matched with visible transmission to watermark image to watermark image, realizes the detection of the anti-counterfeiting characteristic.This anti-counterfeiting detection
In scheme, extra setting visible transmission sensor is needed, and visible transmission sensor is not dashed forward for remaining anti-counterfeiting characteristic
The anti-counterfeit capability for going out, and the image mosaic technology in the program is often using complicated algorithms such as check and punctuate detections, at device data
Reason Capability Requirement is higher.
The content of the invention
It is an object of the invention to provide a kind of detection method and device to printing anti-counterfeiting characteristic, without the need for arranging visible transmission
Sensor is capable of achieving to printing anti-counterfeiting characteristic detection, equipment cost is reduced, while reducing the property to digital signal processor
Can require.
To solve above-mentioned technical problem, the present invention provides a kind of detection method to printing anti-counterfeiting characteristic, including:
Obtain first detection image and the second detection image of examined object, first detection image and described
Second detection image is positive and negative image corresponding with to printing false proof region respectively;
The anti-counterfeiting characteristic information of first detection image is extracted, the first anti-counterfeiting characteristic image is generated;
Extract the anti-counterfeiting characteristic information of second detection image and carry out mirror transformation, generate the second anti-counterfeiting characteristic
Picture;
First anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image are merged, the false proof spy of fusion is generated
Levy image;
The fusion anti-counterfeiting characteristic image is matched with the standard anti-counterfeiting characteristic image prestored in template, according to matching
As a result the true and false of the examined object is judged.
Alternatively, the anti-counterfeiting characteristic information for extracting first detection image, generates the first anti-counterfeiting characteristic image bag
Include:
The version information of the examined object is obtained, it is right in first detection image to determine according to the version information
Print the first position information in false proof region;
According to the first position information, first detection image is carried out using projection and sliding window way of search
Search, determines that first pair prints false proof region;
Printing false proof region to described first pair carries out feature extraction, generates the first anti-counterfeiting characteristic image.
Alternatively, the anti-counterfeiting characteristic information for extracting second detection image and mirror transformation is carried out, generates second
Anti-counterfeiting characteristic image includes:
According to the first position information, carry out determining after coordinate transform in second detection image to printing false proof region
Second position information;
Printing false proof region to the second couple in second detection image carries out feature extraction and carries out mirror transformation, generates
Second anti-counterfeiting characteristic image.
Alternatively, it is described to be merged first anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image, it is raw
Include into fusion anti-counterfeiting characteristic image:
First anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image are carried out into binary conversion treatment;
The pixel value of the pixel of the image same position after process is carried out taking big computing respectively, fusion is generated false proof
Characteristic image.
Alternatively, it is described first anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image to be carried out at binaryzation
Reason includes:
The two-value of first anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image is determined using thresholding method
Change threshold value;
The pixel value that will be above the pixel of the binary-state threshold is set to 0, and the pixel value of rest of pixels point retains initial value.
Alternatively, the fusion anti-counterfeiting characteristic image is carried out with the standard anti-counterfeiting characteristic image prestored in template described
Matching, also includes before the true and false that the examined object is judged according to matching result:
The pixel value of each pixel in the fusion anti-counterfeiting characteristic image is normalized.
Alternatively, it is described to carry out the fusion anti-counterfeiting characteristic image and the standard anti-counterfeiting characteristic image prestored in template
Match somebody with somebody, judge that the true and false of the examined object includes according to matching result:
Calculate the correlation coefficient of the fusion anti-counterfeiting characteristic image and the standard anti-counterfeiting characteristic image;
The correlation coefficient and predetermined threshold value are compared, when the correlation coefficient is more than or equal to the predetermined threshold value
When, judge the examined object as true;When the correlation coefficient is less than the predetermined threshold value, the examined object is judged
It is false.
Alternatively, also include after the first detection image and the second detection image that obtain examined object:
By first detection image, the size of second detection image and the reference material prestored in template
The size of body is contrasted, and determines the drawing coefficient of image;
Corresponding coordinate in each image is corrected according to the drawing coefficient.
Present invention also offers a kind of detection means to printing anti-counterfeiting characteristic, including:
Image collection module, for obtaining first detection image and the second detection image of examined object, described
One detection image and second detection image are positive and negative image corresponding with to printing false proof region respectively;
First extraction module, for extracting the anti-counterfeiting characteristic information of first detection image, generates the first anti-counterfeiting characteristic
Image;
Second extraction module, it is raw for extracting the anti-counterfeiting characteristic information of second detection image and carrying out mirror transformation
Into the second anti-counterfeiting characteristic image;
Fusion Module, for first anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image to be merged,
Generate fusion anti-counterfeiting characteristic image;
Detection module, for the fusion anti-counterfeiting characteristic image to be carried out with the standard anti-counterfeiting characteristic image prestored in template
Matching, according to matching result the true and false of the examined object is judged.
Detection method and device to printing anti-counterfeiting characteristic provided by the present invention, by the first inspection for obtaining examined object
Altimetric image and the second detection image, extract the anti-counterfeiting characteristic information of the first detection image, generate the first anti-counterfeiting characteristic image;Carry
Take the anti-counterfeiting characteristic information of the second detection image and carry out mirror transformation, generate the second anti-counterfeiting characteristic image;By the first false proof spy
Levy image and the second anti-counterfeiting characteristic image is merged, generate fusion anti-counterfeiting characteristic image;Will fusion anti-counterfeiting characteristic image with
The standard anti-counterfeiting characteristic image prestored in template is matched, and according to matching result the true and false of examined object is judged.The application
The collection of positive and negative visible reflectance image need to be only carried out, the collection without the need for carrying out visible transmission image is being ensured to print inspection
In the case of surveying anti-counterfeiting performance, the cost of equipment is effectively reduced, and the complicated algorithm in image mosaic technology need not be adopted,
Reduce the performance requirement to digital signal processor.
Description of the drawings
For the clearer explanation embodiment of the present invention or the technical scheme of prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for technology description is briefly described, it should be apparent that, drawings in the following description are only this
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with root
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the flow chart to printing a kind of specific embodiment of the detection method of anti-counterfeiting characteristic provided by the present invention;
Fig. 2 is the flow chart of the anti-counterfeiting characteristic information that the first detection image is extracted in the embodiment of the present invention;
Fig. 3 is a kind of specific embodiment stream of the anti-counterfeiting characteristic information that the second detection image is extracted in the embodiment of the present invention
Cheng Tu;
Fig. 4 is another kind of specific embodiment flow chart to printing the detection method of anti-counterfeiting characteristic provided by the present invention;
Fig. 5 is another specific embodiment schematic diagram to printing the detection method of anti-counterfeiting characteristic provided by the present invention;
Fig. 6 is just in the face of print regional location schematic diagram in the detection method to printing anti-counterfeiting characteristic provided by the present invention;
Fig. 7 is that genuine notes reverse side is illustrated to printing regional location in the detection method to printing anti-counterfeiting characteristic provided by the present invention
Figure;
Fig. 8 is that counterfeit money reverse side is illustrated to printing regional location in the detection method to printing anti-counterfeiting characteristic provided by the present invention
Figure;
Fig. 9 is that genuine notes are just facing print region with reverse side to print in the detection method to printing anti-counterfeiting characteristic provided by the present invention
The fusion schematic diagram in region;
Figure 10 is that counterfeit money is just facing print region and reverse side pair in the detection method to printing anti-counterfeiting characteristic provided by the present invention
The fusion schematic diagram in print region;
Figure 11 is the structured flowchart to printing the detection means of anti-counterfeiting characteristic provided in an embodiment of the present invention.
Specific embodiment
In order that those skilled in the art more fully understand the present invention program, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.Obviously, described embodiment is only a part of embodiment of the invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, belongs to the scope of protection of the invention.
Flow chart such as Fig. 1 institutes to printing a kind of specific embodiment of the detection method of anti-counterfeiting characteristic provided by the present invention
Show, the method includes:
Step S101:Obtain first detection image and the second detection image of examined object, the first detection figure
Picture and second detection image are positive and negative image corresponding with to printing false proof region respectively;
Can specifically adopt CIS sensors visible with the front to printing anti-counterfeiting mark pattern, reverse side to examined object
Light reflected image is acquired, and generates the first detection image and the second detection image.
Step S102:The anti-counterfeiting characteristic information of first detection image is extracted, the first anti-counterfeiting characteristic image is generated;
As a kind of specific embodiment, as shown in Fig. 2 extracting the anti-counterfeiting characteristic letter of the first detection image in the present embodiment
The process of breath can be specifically included:
Step S1021:The version information of the examined object is obtained, first inspection is determined according to the version information
To the first position information in the false proof region of print in altimetric image;
Step S1022:According to the first position information, examined to described first using projection and sliding window way of search
Altimetric image is scanned for, and determines that first pair prints false proof region;
Step S1023:Printing false proof region to described first pair carries out feature extraction, generates the first anti-counterfeiting characteristic image.
According to the version information of examined object in the present embodiment, the Template Information for prestoring is searched in data base,
Determine in the first detection image to the first position information in the false proof region of print.In the first detection image, using projection and cunning
Dynamic window way of search is scanned for, the false proof region of first pair of print of labelling, and to the region feature extraction is carried out, and obtains the first false proof spy
Levy image.
Step S103:Extract the anti-counterfeiting characteristic information of second detection image and carry out mirror transformation, generate second and prevent
Pseudo-characteristic image;
A kind of specific embodiment of the anti-counterfeiting characteristic image of generation second that the present embodiment is provided is as shown in figure 3, its tool
Body includes:
Step S1131:According to the first position information, it is right in second detection image to carry out determining after coordinate transform
Print the second position information in false proof region;
Step S1132:Printing false proof region to the second couple in second detection image carries out feature extraction and carries out mirror
As conversion, the second anti-counterfeiting characteristic image is generated.
First position information is carried out after coordinate transform, you can obtain second pair of print corresponding with first position information false proof
The positional information in region, printing false proof region to second pair according to the positional information carries out feature extraction, and carries out after mirror transformation
Generate the second anti-counterfeiting characteristic image.Step S103 need to get first position after step S102 is performed in this kind of embodiment
Carry out on the basis of information.
Step S104:First anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image are merged, is generated
Fusion anti-counterfeiting characteristic image;
The process of fusion can be specially:First anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image are entered
Row binary conversion treatment;The pixel value of the pixel of the image same position after process is carried out taking big computing respectively, generation is melted
Close anti-counterfeiting characteristic image.
Step S105:The fusion anti-counterfeiting characteristic image and the standard anti-counterfeiting characteristic image prestored in template are carried out
Match somebody with somebody, the true and false of the examined object is judged according to matching result.
The process of judgement is specially:
Calculate the correlation coefficient of the fusion anti-counterfeiting characteristic image and the standard anti-counterfeiting characteristic image;By the phase relation
Number is compared with predetermined threshold value, when the correlation coefficient is more than or equal to the predetermined threshold value, judges the thing to be detected
Body is true;When the correlation coefficient is less than the predetermined threshold value, the examined object is judged as false.
Detection method to printing anti-counterfeiting characteristic provided by the present invention, by the first detection image for obtaining examined object
And second detection image, the anti-counterfeiting characteristic information of the first detection image is extracted, generate the first anti-counterfeiting characteristic image;Extract second
The anti-counterfeiting characteristic information of detection image simultaneously carries out mirror transformation, generates the second anti-counterfeiting characteristic image;By the first anti-counterfeiting characteristic image
And second anti-counterfeiting characteristic image merged, generate fusion anti-counterfeiting characteristic image;By fusion anti-counterfeiting characteristic image and the mould that prestores
Standard anti-counterfeiting characteristic image in plate is matched, and according to matching result the true and false of examined object is judged.The application only need to enter
The collection of row positive and negative visible reflectance image, the collection without the need for carrying out visible transmission image is ensureing false proof to print detection
In the case of performance, the cost of equipment is effectively reduced, and the complicated algorithm in image mosaic technology need not be adopted, reduced
Performance requirement to digital signal processor.
Detection method to printing anti-counterfeiting characteristic provided by the present invention, examined object can be specially banknote, such as 100 yuan
RMB.First detection image, the second detection image correspond to respectively front, the reverse side of banknote.With the first detection in the present embodiment
As a example by image is for the direct picture of banknote.Banknote is further elaborated on to the detection process for printing anti-counterfeiting characteristic.
Another kind of specific embodiment flow chart such as Fig. 4 institutes to printing the detection method of anti-counterfeiting characteristic provided by the present invention
Show, specifically include:
Step S201:Image acquisition is carried out to banknote front, reverse side, front detection image and reverse side detection figure is generated
Picture.
Front, reverse side visible reflectance image acquisition are completed using CIS sensors, direct picture I is collectedAAnd reverse side
Image IB, I (i, j) is the pixel value of pixel (i, j).
Step S202:Obtain comprising banknote denominations towards version information, transferred according to version information and be pre-stored in data base
In just in the face of watermark image positional information;
Using vectorRepresent that certain version direct picture is to printing the position of region of search, wherein x
The abscissa of region of search, y is the vertical coordinate of region of search, and Δ x is the width of region of search, and Δ y is the height of region of search;
Step S203:Align and complete just to face impression in the face of the application projection of watermark image region of search and sliding window way of search
As search, realize positioning watermark image, labelling direct picture positional information, and carried out just facing watermark image according to the positional information
Extract;
To regionThe floor projection of image pixel is carried out,
Lengthwise position positioning, window size Δ y are completed using sliding window searching method1It is the elevation information to watermark image,
Prestore in a storage module, when i meets following condition
Record y1=i is the vertical coordinate to watermark image summit;
To regionThe upright projection of image pixel is carried out,
Lateral attitude positioning, window size Δ x are completed using sliding window searching method1It is the width information to watermark image,
Prestore in a storage module when i meets following condition
Record x1=i is the abscissa to watermark image summit;Thus, complete front surface region to determine the region of watermark image,
Front surface region is to watermark image regionExtract and just face watermark image IA1,
IA1(i, j)=I (i+x1,j+y1), i=0 ..., Δ x1, j=0 ..., Δ y1
Step S204:According to the positional information for just facing watermark image, coordinate transform is carried out, obtain and just face watermark image position
Confidence ceases corresponding reverse side to printing zone position information, carries out reverse side according to the positional information and extracts and carry out to printing area image
Mirror transformation;
First according to just in the face of the position of watermark imageCarry out following coordinate transform obtain with
Just in the face of the corresponding opposed region positional information of print positional information
Reverse side is extracted to watermark image IB1(i, j),
IB1(i, j)=IB(i+w-x1-Δx1,y1), i=0 ..., Δ x1, j=0 ..., Δ y1
In above formula, w is the width information of banknote, and to the region horizontal direction mirror transformation is carried out, and obtains reverse side to printing area
Domain mirror image:
IC1(i, j)=IB1(Δx1- i, j), i=0 ..., Δ x1, j=0 ..., Δ y1
Step S205:Watermark image binary conversion treatment will be just faced, the image pixel that will be above binary-state threshold sets to 0, remaining
Pixel retains, and non-zero pixel is normalized, and reverse side takes same treatment to printing region;
Process just in the face of print area image I using binarization method firstA1, obtain binary-state threshold TA1,
Align and enter row threshold division in the face of print area image, obtain just in the face of the segmentation figure picture in print region
Segmentation figure picture is normalized
In above formula, [g0,g0+g1] for image stretch range of stretch;
Using binarization method reverse side is processed to printing area image IC1, obtain binary-state threshold TC1,
Row threshold division is entered to printing region mirror image to reverse side, reverse side is obtained to printing the segmentation figure picture in region
Segmentation figure picture is normalized
Step S206:By Threshold segmentation and the pixel of normalized two width image same position carries out maximizing operation, formed
Fusion image;
IAC3(i, j)=max (IA3(i,j),IC3(i, j)), i=0 ..., Δ x1, j=0 ..., Δ y1
Step S207:Normalized fusion image is matched with the masterplate that prestores, matching output result reaches default threshold
Judge that the banknote is true during value.
Transverse projection stencil matching correlation coefficient is calculated, and transverse projection data are obtained first
Transverse projection data are normalized,
In above formula, [f0,f0+f1] for data for projection stretching range of stretch;
Transfer the transverse projection masterplate f for prestoring in a storage moduleVAC3, carry out stencil matching correlation coefficient calculating
Longitudinal projection's stencil matching correlation coefficient is calculated, and longitudinal projection's data are obtained first
Longitudinal projection is normalized,
Transfer the transverse projection masterplate f for prestoring in a storage moduleHAC3, carry out stencil matching correlation coefficient calculating
When correlation coefficient meets following condition, judge that the banknote is true
It is pointed out that the mode of the masterplate generation that prestores is similar with step S201-S206, adopted for standard bill
Collection, prestores in a storage module.
For laterally entering paper money or longitudinal paper money intake device, because image-sampling frequency is consistent, walk paper money speed it is inconsistent when, there is figure
As situation about stretching compared with true resolution size or shorten, i.e. banknote actual size may banknote size corresponding with the masterplate that prestores
Inconsistent problem.In consideration of it, the banknote dimension information of the masterplate that prestores can be prestored to data base, according to the size of input banknote
With the size that prestores, to region of search and to the sliding window size that watermark image rope is searched line translation is entered, when stencil matching step is carried out,
Fusion image feature and the length information of the masterplate that prestores are entered into row interpolation normalization, then completes matching, such as Fig. 5 is provided by the present invention
Another specific embodiment schematic diagram shown in, its Detailed operating procedures is as follows;
The template information that prestores banknote dimension information corresponding with the template information, note prestores banknote picture traverse for W, banknote
Height H, front region of searchTo watermark image dimension width Δ m1, to watermark image dimensional height Δ m1;
Front, reverse side visible reflectance image acquisition are completed using CIS sensors, direct picture I is obtainedAAnd verso images
IB, I (i, j) is the pixel value of pixel (i, j).
Banknote denominations are obtained towards version information and dimension information, is determined just according to face amount Information version dimension information
In the face of watermark image region of search;
It is picture traverse W to calculate actual banknote dimension information1, banknote height H1, obtain conversion width conversion coefficient ηW=
W1/ W, altitude conversion coefficient ηH=H1/ H, then just in the face of the position of print region of search
Wherein ηWM for region of search abscissa, ηHN for region of search vertical coordinate, ηWΔ m for region of search width, ηHΔ n is
The height of region of search;It is presented below for convenience, remembers x=ηWM, y=ηHN, Δ x=ηWΔ m, Δ y=ηHΔn;
Complete just to search in the face of watermark image with reference to sliding window way of search using projective iteration, realize positioning watermark image,
Labelling direct picture positional information, and carried out just extracting in the face of watermark image according to the positional information;
By taking erect image as an example, first to regionThe floor projection of image pixel is carried out,
Determine that the search just in the face of print region is highly η using altitude conversion coefficientHΔn1, make Δ y1=ηHΔn1, application
Sliding window searching method completes lengthwise position positioning, when i meets following condition
Record y1=i is the vertical coordinate to watermark image summit;
To regionThe upright projection of image pixel is carried out,
Determine that the search just in the face of print region is highly η using altitude conversion coefficientWΔm1, make Δ y1=ηWΔm1, application
Sliding window searching method completes lateral attitude positioning, when i meets following condition
Record x1=i is the abscissa to watermark image summit;Thus, complete front surface region to determine the region of watermark image,Intercepting image is IA1,
IA1(i, j)=I (i+x1,j+y1), i=0 ..., Δ x1, j=0 ..., Δ y1
According to the positional information for just facing watermark image, coordinate transform is carried out, obtain and just face watermark image positional information pair
The opposed region positional information answered, and according to the positional information carry out reverse side to print area image extract and carry out mirror transformation;
First according to just in the face of the position of watermark imageCarry out following coordinate transform
Opposed region positional information corresponding with print positional information is just faced is obtained,
IB1(i, j)=IB(i+w-x1-Δx1,j+y1), i=0 ..., Δ x1, j=0 ..., Δ y1
And horizontal direction mirror transformation is carried out to the region, reverse side is obtained to printing area image.
IC1(i, j)=IB1(Δx1- i, j), i=0 ..., Δ x1, j=0 ..., Δ y1
Watermark image binary conversion treatment will be just faced, the image pixel that will be above binary-state threshold sets to 0, rest of pixels retains,
Non-zero pixel is normalized, reverse side takes same treatment to printing region;
Process just in the face of print area image I using binarization method firstA1, obtain binary-state threshold TA1,
Align and enter row threshold division in the face of print area image, obtain just in the face of the segmentation figure picture in print region
Segmentation figure picture is normalized
Using binarization method reverse side is processed to printing region mirror image IC1, obtain binary-state threshold TC1,
Row threshold division is entered to printing region mirror image to reverse side, reverse side is obtained to printing the segmentation figure picture in region
Segmentation figure picture is normalized
The pixel of two width image same positions is carried out to take big, formation fusion image, and completes the normalization of image size;
IAC3(i, j)=max (IA3(i,j),IC3(i, j)), i=0 ..., Δ x1, j=0 ..., Δ y1
Normalized fusion image is matched with the masterplate that prestores, it is to judge to be somebody's turn to do that matching output result reaches predetermined threshold value
It is true to open banknote.
Transverse projection stencil matching correlation coefficient is calculated, and transverse projection data are obtained first
Transverse projection is normalized,
Masterplate length normalization method, transverse projection data E to fusion imageVAC3Enter row interpolation, be by data length interpolation
With transverse projection data masterplate fVAC3Length is consistent, remembers that the data for projection after interpolation is FVAC3,
Longitudinal projection's stencil matching correlation coefficient is calculated, and longitudinal projection's data are obtained first
Longitudinal projection is normalized,
Masterplate length normalization method, longitudinal projection's data E to fusion imageHAC3Enter row interpolation, be by data length interpolation
With longitudinal projection data masterplate fHAC3Length is consistent, remembers that the data for projection after interpolation is FHAC3,
When correlation coefficient meets following condition, judge that the banknote is true:
Recognition result is completed in embedded systems in the application, and control machinery motion module is realized paper money by embedded system
The true and false differentiation of ticket.By being corrected to coordinate, can avoid due to caused by the stretching in image acquisition procedures or compression
The inaccurate problem of matching result, improves testing result accuracy.
Fig. 6 shows in the detection method to printing anti-counterfeiting characteristic provided by the present invention and just illustrates in the face of print regional location
Figure, Fig. 7 shows that genuine notes reverse side is to printing regional location schematic diagram in the detection method to printing anti-counterfeiting characteristic provided by the present invention,
Fig. 8 shows that counterfeit money reverse side is to printing regional location schematic diagram in the detection method to printing anti-counterfeiting characteristic provided by the present invention, and
Fig. 9 shows that genuine notes are just in the face of printing region with reverse side to printing region in the detection method to printing anti-counterfeiting characteristic provided by the present invention
Fusion schematic diagram, Figure 10 show it is provided by the present invention to print anti-counterfeiting characteristic detection method in counterfeit money just in the face of print region
With fusion schematic diagram of the reverse side to print region.It can be seen that, the application need not be using visible light projection sensor and image mosaic skill
Art, you can realize the identification to authenticity of banknotes.
The detection means to printing anti-counterfeiting characteristic provided in an embodiment of the present invention is introduced below, it is described below to print
The detection means of anti-counterfeiting characteristic can be mutually to should refer to the above-described detection method to printing anti-counterfeiting characteristic.
Figure 11 is the structured flowchart to printing the detection means of anti-counterfeiting characteristic provided in an embodiment of the present invention, with reference to Figure 11 to print
The detection means of anti-counterfeiting characteristic can include:
Image collection module 100, it is described for obtaining first detection image and the second detection image of examined object
First detection image and second detection image are positive and negative image corresponding with to printing false proof region respectively;
First extraction module 200, for extracting the anti-counterfeiting characteristic information of first detection image, generates the first false proof spy
Levy image;
Second extraction module 300, for extracting the anti-counterfeiting characteristic information of second detection image and carrying out mirror transformation,
Generate the second anti-counterfeiting characteristic image;
Fusion Module 400, for first anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image to be melted
Close, generate fusion anti-counterfeiting characteristic image;
Detection module 500, for merging anti-counterfeiting characteristic image and the standard anti-counterfeiting characteristic image prestored in template by described
Matched, the true and false of the examined object is judged according to matching result.
The present embodiment to print anti-counterfeiting characteristic detection means be used for realize it is aforesaid to print anti-counterfeiting characteristic detection method,
Therefore the reality of the detection method to printing anti-counterfeiting characteristic hereinbefore visible to the specific embodiment in the detection for printing anti-counterfeiting characteristic
A part is applied, for example, image collection module 100, the first extraction module 200, the second extraction module 300, Fusion Module 400, inspection
Survey module 500, be respectively used to realize step S101 in the above-mentioned detection method to printing anti-counterfeiting characteristic, S102, S103, S104 and
S105, so, its specific embodiment is referred to the description of corresponding various pieces embodiment, will not be described here.
Detection means to printing anti-counterfeiting characteristic provided by the present invention, by the first detection image for obtaining examined object
And second detection image, the anti-counterfeiting characteristic information of the first detection image is extracted, generate the first anti-counterfeiting characteristic image;Extract second
The anti-counterfeiting characteristic information of detection image simultaneously carries out mirror transformation, generates the second anti-counterfeiting characteristic image;By the first anti-counterfeiting characteristic image
And second anti-counterfeiting characteristic image merged, generate fusion anti-counterfeiting characteristic image;By fusion anti-counterfeiting characteristic image and the mould that prestores
Standard anti-counterfeiting characteristic image in plate is matched, and according to matching result the true and false of examined object is judged.The application only need to enter
The collection of row positive and negative visible reflectance image, the collection without the need for carrying out visible transmission image is ensureing false proof to print detection
In the case of performance, the cost of equipment is effectively reduced, and the complicated algorithm in image mosaic technology need not be adopted, reduced
Performance requirement to digital signal processor.
Each embodiment is described by the way of progressive in this specification, and what each embodiment was stressed is and other
The difference of embodiment, between each embodiment same or similar part mutually referring to.For dress disclosed in embodiment
For putting, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part is referring to method part
Illustrate.
Professional further appreciates that, with reference to the unit of each example of the embodiments described herein description
And algorithm steps, can with electronic hardware, computer software or the two be implemented in combination in, in order to clearly demonstrate hardware and
The interchangeability of software, according to function has generally described the composition and step of each example in the above description.These
Function is performed with hardware or software mode actually, depending on the application-specific and design constraint of technical scheme.Specialty
Technical staff can use different methods to realize described function to each specific application, but this realization should not
Think beyond the scope of this invention.
The step of method described with reference to the embodiments described herein or algorithm, directly can be held with hardware, processor
Capable software module, or the combination of the two is implementing.Software module can be placed in random access memory (RAM), internal memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, depositor, hard disk, moveable magnetic disc, CD-ROM or technology
In field in known any other form of storage medium.
The detection method and device to printing anti-counterfeiting characteristic provided by the present invention is described in detail above.Herein
In apply specific case the principle and embodiment of the present invention be set forth, the explanation of above example is only intended to side
Assistant solves the method for the present invention and its core concept.It should be pointed out that for those skilled in the art, not
On the premise of departing from the principle of the invention, some improvement and modification can also be carried out to the present invention, these are improved and modification also falls into
In the protection domain of the claims in the present invention.
Claims (9)
1. it is a kind of to print anti-counterfeiting characteristic detection method, it is characterised in that include:
Obtain first detection image and the second detection image of examined object, first detection image and described second
Detection image is positive and negative image corresponding with to printing false proof region respectively;
The anti-counterfeiting characteristic information of first detection image is extracted, the first anti-counterfeiting characteristic image is generated;
Extract the anti-counterfeiting characteristic information of second detection image and carry out mirror transformation, generate the second anti-counterfeiting characteristic image;
First anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image are merged, fusion anti-counterfeiting characteristic is generated
Picture;
The fusion anti-counterfeiting characteristic image is matched with the standard anti-counterfeiting characteristic image prestored in template, according to matching result
Judge the true and false of the examined object.
2. as claimed in claim 1 to the detection method of print anti-counterfeiting characteristic, it is characterised in that the extraction described first is detected
The anti-counterfeiting characteristic information of image, generating the first anti-counterfeiting characteristic image includes:
The version information of the examined object is obtained, is determined according to the version information anti-to print in first detection image
The first position information in pseudo- region;
According to the first position information, first detection image is searched using projection and sliding window way of search
Rope, determines that first pair prints false proof region;
Printing false proof region to described first pair carries out feature extraction, generates the first anti-counterfeiting characteristic image.
3. as claimed in claim 2 to the detection method of print anti-counterfeiting characteristic, it is characterised in that the extraction described second is detected
The anti-counterfeiting characteristic information of image simultaneously carries out mirror transformation, and generating the second anti-counterfeiting characteristic image includes:
According to the first position information, carry out determining after coordinate transform in second detection image to printing the of false proof region
Two positional informationes;
Printing false proof region to the second couple in second detection image carries out feature extraction and carries out mirror transformation, generates second
Anti-counterfeiting characteristic image.
4. as described in any one of claims 1 to 3 to print anti-counterfeiting characteristic detection method, it is characterised in that it is described will be described
First anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image are merged, and generating fusion anti-counterfeiting characteristic image includes:
First anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image are carried out into binary conversion treatment;
The pixel value of the pixel of the image same position after process is carried out taking big computing respectively, fusion anti-counterfeiting characteristic is generated
Image.
5. as claimed in claim 4 to the detection method of print anti-counterfeiting characteristic, it is characterised in that described by the described first false proof spy
Levying image and second anti-counterfeiting characteristic image carries out binary conversion treatment and includes:
The binaryzation threshold of first anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image is determined using thresholding method
Value;
The pixel value that will be above the pixel of the binary-state threshold is set to 0, and the pixel value of rest of pixels point retains initial value.
6. as claimed in claim 1 to the detection method of print anti-counterfeiting characteristic, it is characterised in that described that the fusion is false proof
Characteristic image is matched with the standard anti-counterfeiting characteristic image prestored in template, and according to matching result the examined object is judged
The true and false before also include:
The pixel value of each pixel in the fusion anti-counterfeiting characteristic image is normalized.
7. as claimed in claim 6 to the detection method of print anti-counterfeiting characteristic, it is characterised in that described by the false proof spy of the fusion
Levy image and matched with the standard anti-counterfeiting characteristic image prestored in template, the examined object is judged according to matching result
The true and false includes:
Calculate the correlation coefficient of the fusion anti-counterfeiting characteristic image and the standard anti-counterfeiting characteristic image;
The correlation coefficient and predetermined threshold value are compared, when the correlation coefficient is more than or equal to the predetermined threshold value,
Judge the examined object as true;When the correlation coefficient be less than the predetermined threshold value when, judge the examined object as
It is false.
8. as described in any one of claims 1 to 3 to print anti-counterfeiting characteristic detection method, it is characterised in that obtain it is to be checked
Also include after the first detection image and the second detection image of surveying object:
By first detection image, the size of second detection image and the standard item prestored in template
Size is contrasted, and determines the drawing coefficient of image;
Corresponding coordinate in each image is corrected according to the drawing coefficient.
9. it is a kind of to print anti-counterfeiting characteristic detection means, it is characterised in that include:
Image collection module, for obtaining first detection image and the second detection image of examined object, first inspection
Altimetric image and second detection image are positive and negative image corresponding with to printing false proof region respectively;
First extraction module, for extracting the anti-counterfeiting characteristic information of first detection image, generates the first anti-counterfeiting characteristic image;
Second extraction module, for extracting the anti-counterfeiting characteristic information of second detection image and carrying out mirror transformation, generates the
Two anti-counterfeiting characteristic images;
Fusion Module, for first anti-counterfeiting characteristic image and second anti-counterfeiting characteristic image to be merged, generates
Fusion anti-counterfeiting characteristic image;
A detection module, for the fusion anti-counterfeiting characteristic image and the standard anti-counterfeiting characteristic image prestored in template to be carried out
Match somebody with somebody, the true and false of the examined object is judged according to matching result.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611168869.2A CN106599923B (en) | 2016-12-16 | 2016-12-16 | Method and device for detecting seal anti-counterfeiting features |
PCT/CN2017/073054 WO2018107574A1 (en) | 2016-12-16 | 2017-02-07 | Method and device for detecting see-through register anti-counterfeiting characteristics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611168869.2A CN106599923B (en) | 2016-12-16 | 2016-12-16 | Method and device for detecting seal anti-counterfeiting features |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106599923A true CN106599923A (en) | 2017-04-26 |
CN106599923B CN106599923B (en) | 2020-01-24 |
Family
ID=58599586
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611168869.2A Active CN106599923B (en) | 2016-12-16 | 2016-12-16 | Method and device for detecting seal anti-counterfeiting features |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106599923B (en) |
WO (1) | WO2018107574A1 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109389153A (en) * | 2018-08-31 | 2019-02-26 | 众安信息技术服务有限公司 | A kind of holographic false proof code check method and device |
CN110309859A (en) * | 2019-06-06 | 2019-10-08 | 阿里巴巴集团控股有限公司 | A kind of image true-false detection method, device and electronic equipment |
CN112749690A (en) * | 2020-03-27 | 2021-05-04 | 腾讯科技(深圳)有限公司 | Text detection method and device, electronic equipment and storage medium |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115223018B (en) * | 2022-06-08 | 2023-07-04 | 东北石油大学 | Camouflage object collaborative detection method and device, electronic equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1312051A1 (en) * | 2000-07-20 | 2003-05-21 | Currency Systems International, Inc. | Note-specific currency processing |
CN104574638A (en) * | 2014-09-30 | 2015-04-29 | 上海层峰金融设备有限公司 | Method for identifying RMB |
CN105184957A (en) * | 2015-09-28 | 2015-12-23 | 深圳怡化电脑股份有限公司 | Paper currency discrimination method and system |
CN205750988U (en) * | 2016-05-17 | 2016-11-30 | 北京新岸线数字图像技术有限公司 | A kind of paper money discrimination device |
CN106920320A (en) * | 2015-12-28 | 2017-07-04 | 浙江维融电子科技股份有限公司 | A kind of offset printing of version RMB in 2015 is to the identification device and its discrimination method that are patterned |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100157377A1 (en) * | 2008-12-18 | 2010-06-24 | Xerox Corporation | Uv fluorescence encoded background images using adaptive halftoning into disjoint sets |
CN205451254U (en) * | 2015-12-28 | 2016-08-10 | 浙江维融电子科技股份有限公司 | 2015 year version RMB offset printing is to identification device of seal pattern |
CN105931357A (en) * | 2016-04-19 | 2016-09-07 | 北京新岸线数字图像技术有限公司 | Banknote counterfeit detection method and device |
CN205722109U (en) * | 2016-04-19 | 2016-11-23 | 北京新岸线数字图像技术有限公司 | Banknote anti-counterfeiting detection equipment |
-
2016
- 2016-12-16 CN CN201611168869.2A patent/CN106599923B/en active Active
-
2017
- 2017-02-07 WO PCT/CN2017/073054 patent/WO2018107574A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1312051A1 (en) * | 2000-07-20 | 2003-05-21 | Currency Systems International, Inc. | Note-specific currency processing |
CN104574638A (en) * | 2014-09-30 | 2015-04-29 | 上海层峰金融设备有限公司 | Method for identifying RMB |
CN105184957A (en) * | 2015-09-28 | 2015-12-23 | 深圳怡化电脑股份有限公司 | Paper currency discrimination method and system |
CN106920320A (en) * | 2015-12-28 | 2017-07-04 | 浙江维融电子科技股份有限公司 | A kind of offset printing of version RMB in 2015 is to the identification device and its discrimination method that are patterned |
CN205750988U (en) * | 2016-05-17 | 2016-11-30 | 北京新岸线数字图像技术有限公司 | A kind of paper money discrimination device |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109389153A (en) * | 2018-08-31 | 2019-02-26 | 众安信息技术服务有限公司 | A kind of holographic false proof code check method and device |
CN109389153B (en) * | 2018-08-31 | 2021-03-02 | 众安信息技术服务有限公司 | Holographic anti-counterfeiting code checking method and device |
CN110309859A (en) * | 2019-06-06 | 2019-10-08 | 阿里巴巴集团控股有限公司 | A kind of image true-false detection method, device and electronic equipment |
CN110309859B (en) * | 2019-06-06 | 2023-04-07 | 创新先进技术有限公司 | Image authenticity detection method and device and electronic equipment |
CN112749690A (en) * | 2020-03-27 | 2021-05-04 | 腾讯科技(深圳)有限公司 | Text detection method and device, electronic equipment and storage medium |
CN112749690B (en) * | 2020-03-27 | 2023-09-12 | 腾讯科技(深圳)有限公司 | Text detection method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2018107574A1 (en) | 2018-06-21 |
CN106599923B (en) | 2020-01-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110598699B (en) | Anti-counterfeiting bill authenticity distinguishing system and method based on multispectral image | |
CN107085883B (en) | A kind of method and apparatus of paper money recognition | |
CN106599923A (en) | Detecting method and detecting device for stamped anti-counterfeiting characteristic | |
CN108320373B (en) | Method and device for detecting anti-counterfeiting mark of paper money | |
CN107610322B (en) | Banknote version identification method and device, electronic equipment and storage medium | |
JP4932177B2 (en) | Coin classification device and coin classification method | |
EP1953710B1 (en) | Counterfeit Deterrence Using Dispersed Miniature Security Marks | |
AU2016360852B2 (en) | Method for authenticating and/or checking the integrity of a subject | |
CN106558143B (en) | It is a kind of 100 yuans splicing bank note recognition methods and device | |
JP5372183B2 (en) | Coin classification device and coin classification method | |
CN110378351B (en) | Seal identification method and device | |
CN106780954A (en) | A kind of method and device of paper money recognition | |
CN107437293A (en) | A kind of bill anti-counterfeit discrimination method based on bill global characteristics | |
Sharan et al. | Detection of counterfeit Indian currency note using image processing | |
CN109409158A (en) | A kind of method for anti-counterfeit based on two dimensional code edge roughness | |
Rathee et al. | Feature fusion for fake Indian currency detection | |
CN108806058A (en) | A kind of paper currency detecting method and device | |
CN105957237B (en) | A kind of version recognition methods of bank note and device | |
CN106934922A (en) | A kind of paper currency detecting method and device | |
TWI326854B (en) | Verification method for determining areas within an image corresponding to monetary banknote | |
Amirsab et al. | An automated recognition of fake or destroyed Indian currency notes | |
CN106296975A (en) | The recognition methods of a kind of dollar bill face amount and device | |
KR101080069B1 (en) | Method Judging The Forged Sealing and Recording media | |
TWI378406B (en) | Method for performing color analysis operation on image corresponding to monetary banknote | |
Berchtold et al. | Smartphone-supported integrity verification of printed documents |
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 |