CN105184955B - A kind of recognition methods of bank note and device - Google Patents
A kind of recognition methods of bank note and device Download PDFInfo
- Publication number
- CN105184955B CN105184955B CN201510506975.6A CN201510506975A CN105184955B CN 105184955 B CN105184955 B CN 105184955B CN 201510506975 A CN201510506975 A CN 201510506975A CN 105184955 B CN105184955 B CN 105184955B
- Authority
- CN
- China
- Prior art keywords
- light
- hollow out
- line position
- bank note
- projection value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of recognition methods of bank note and device, becomes the safe line position of hollow out by the light for obtaining bank note, becomes the safe line position of hollow out to the light and carries out binaryzation;The row projection value that the light after binaryzation becomes the safe line position of hollow out is calculated, row projection value curve is obtained according to the row projection value;Use row projection value curve described in dynamic time warping algorithmic match;According to matching result, differentiate that light becomes the true and false of hollow out safety line.The present invention becomes the safe line position progress binaryzation of hollow out to light and obtains the row projection value of the light change safe line position of hollow out and obtain row projection value curve, the row projection value curve for being become hollow out safety line to light using dynamic time warping algorithm is matched, the progress false distinguishing identification of hollow out safety line effectively can be become to the light of bank note, be advantageous to the true and false prevention that light becomes hollow out safety line.
Description
Technical field
The present invention relates to recognition methods and the device in paper money recognition field, more particularly to a kind of bank note.
Background technology
2015 millboard coin light more than existing version bank note becomes hollow out safety line, and this light becomes among hollow out safety line
Word can be clearly apparent in infrared transmission image.By judging that light becomes the feature of hollow out safety line, it can be determined that go out bank note
Version whether belong to 2015 editions, while differentiate light become the hollow out safety line true and false.
The content of the invention
The invention provides recognition methods and the device that bank note light becomes hollow out safety line, this method and device are on bank note
The detection that light becomes hollow out safety line is adaptable, it can be determined that whether the version for going out bank note is that there is light to become hollow out safety line
Version, while differentiate that light becomes the true and false of hollow out safety line.
To realize above-mentioned design, the present invention uses following technical scheme:
On the one hand a kind of recognition methods of bank note is employed, including:
The light for obtaining bank note becomes the safe line position of hollow out, becomes the safe line position of hollow out to the light and carries out binaryzation;
The row projection value that the light after binaryzation becomes the safe line position of hollow out is calculated, row projection is obtained according to the row projection value
It is worth curve;
Use row projection value curve described in dynamic time warping algorithmic match;
According to matching result, differentiate that light becomes the true and false of hollow out safety line.
Wherein, the acquisition light becomes the safe line position of hollow out, becomes the safe line position of hollow out to the light and carries out binaryzation, bag
Include:
The infrared transmission image of bank note is obtained, choosing light according to the infrared transmission image becomes the safe line position of hollow out, cuts
Cut the region subgraph that the light becomes the safe line position of hollow out;
The row projection value of the region subgraph is calculated, the row of the light change safe line position of hollow out are extracted according to the row projection value
Project value tag;
Value tag, which is projected, according to the row is accurately positioned the light change safe line position of hollow out;
Become the safe line position of hollow out to the light using Adaptive Thresholding and carry out binaryzation.
Wherein, the row projection value for calculating the region subgraph, light is extracted according to the row projection value and becomes hollow out safety
After the row projection value tag of line position, it is described according to arrange the projection value tag be accurately positioned light become hollow out safe line position it
Before, in addition to:
It is to become hollow out safety with light to go out bank note according to the row projection value feature recognition of the light change safe line position of hollow out
The bank note of line version.
Wherein, the light for obtaining bank note becomes the safe line position of hollow out, becomes the safe line position of hollow out to the light and carries out two
Before value, in addition to:
The Information of bank note is identified, the Information is divided into:Positive positive, positive reverse, reverse side forward direction and reverse side
Reversely;
The light for obtaining bank note becomes the safe line position of hollow out, becomes the safe line position of hollow out to the light and carries out binaryzation,
Specially:
When the Information for identifying bank note is reverse for positive positive or reverse side, the light of bank note is obtained on the right side of bank note
Become the safe line position of hollow out, become the safe line position of hollow out to the light and carry out binaryzation;
When the Information for identifying bank note is reverse front or reverse side forward direction, the light of bank note is obtained on the left of bank note
Become the safe line position of hollow out, become the safe line position of hollow out to the light and carry out binaryzation.
Wherein, it is described using row projection value curve described in dynamic time warping algorithmic match, be specially:
Find an optimal Time alignment function so that the row projection value curve is bent closest to standard row projection value
Line, obtain the minimum range summation of match point time.
Wherein, it is described according to matching result, differentiate that light becomes the true and false of hollow out safety line, be specially:
If the minimum range summation of the match point time in the range of preset distance, the light become hollow out safety line into
Very, otherwise it is false.
On the other hand a kind of identification device of bank note is used, including:
Acquiring unit, the light for obtaining bank note become the safe line position of hollow out, and becoming the safe line position of hollow out to the light enters
Row binaryzation;
Row projecting cell, become the row projection value of the safe line position of hollow out for calculating the light after binaryzation, according to the row
Projection value obtains row projection value curve;
Matching unit, for using row projection value curve described in dynamic time warping algorithmic match;
False distinguishing unit, for according to matching result, differentiating that light becomes the true and false of hollow out safety line.
Wherein, in addition to:
Towards recognition unit, for identifying the Information of bank note, the Information is divided into:Positive positive, front is instead
It is positive and reverse side is reverse to, reverse side.
Wherein, in addition to:
Version recognition unit, the row projection value feature recognition for becoming the safe line position of hollow out according to the light, which goes out bank note, is
Become the bank note of hollow out safety line version with light.
Wherein, the acquiring unit includes:
Cutter unit, for obtaining the infrared transmission image of bank note, light is chosen according to the infrared transmission image and becomes hollow out
Safe line position, cut the region subgraph that the light becomes the safe line position of hollow out;
Row projecting cell, for calculating the row projection value of the region subgraph, light change is extracted according to the row projection value and engraved
The row projection value tag of empty safe line position;
Positioning unit, the light change safe line position of hollow out is accurately positioned for projecting value tag according to the row;
Binarization unit, binaryzation is carried out for becoming the safe line position of hollow out to the light using Adaptive Thresholding.
Beneficial effects of the present invention are:The present invention becomes the safe line position of hollow out by obtaining the light of bank note, and the light is become
The safe line position of hollow out carries out binaryzation;The row projection value that the light after binaryzation becomes the safe line position of hollow out is calculated, according to described
Row projection value obtains row projection value curve;Use row projection value curve described in dynamic time warping algorithmic match;Tied according to matching
Fruit, differentiate that light becomes the true and false of hollow out safety line.The present invention becomes the safe line position progress binaryzation of hollow out to light and obtains light change hollow out
The row projection value of safe line position simultaneously obtains row projection value curve, becomes hollow out safety line to light using dynamic time warping algorithm
Row projection value curve is matched, and effectively can be become the progress false distinguishing identification of hollow out safety line to the light of bank note, is advantageous to light change and engrave
The true and false prevention of empty safety line.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, institute in being described below to the embodiment of the present invention
The accompanying drawing needed to use is briefly described, it should be apparent that, drawings in the following description are only some implementations of the present invention
Example, for those of ordinary skill in the art, on the premise of not paying creative work, it can also be implemented according to the present invention
The content of example and these accompanying drawings obtain other accompanying drawings.
Fig. 1 is a kind of method stream of the first embodiment of the recognition methods of the bank note provided in the specific embodiment of the invention
Cheng Tu.
Fig. 2 is a kind of method stream of the second embodiment of the recognition methods of the bank note provided in the specific embodiment of the invention
Cheng Tu.
Fig. 3 is the bank note schematic diagram of the miscellaneous editions provided in the specific embodiment of the invention.
Fig. 4 is that the light of the bank note of miscellaneous editions in Fig. 3 becomes the region subgraph row projection value curve map of the safe line position of hollow out.
Fig. 5 is that the light of bank note in Fig. 3-c becomes the binary image of the safe line position of hollow out.
Fig. 6 is the row projection value curve after Fig. 5 binaryzations.
Fig. 7 is a kind of structure side of the first embodiment of the identification device of the bank note provided in the specific embodiment of the invention
Block diagram.
Fig. 8 is a kind of structure side of the second embodiment of the identification device of the bank note provided in the specific embodiment of the invention
Block diagram.
Embodiment
For make present invention solves the technical problem that, the technical scheme that uses and the technique effect that reaches it is clearer, below
The technical scheme of the embodiment of the present invention will be described in further detail with reference to accompanying drawing, it is clear that described embodiment is only
It is part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those skilled in the art exist
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Fig. 1 is refer to, it is a kind of the first implementation of the recognition methods of the bank note provided in the specific embodiment of the invention
The method flow diagram of example.As illustrated, the recognition methods, including:
Step S101, the light for obtaining bank note become the safe line position of hollow out, become the safe line position of hollow out to the light and carry out two
Value.
Specifically, the word among light change hollow out safety line can be clearly indicated by infrared transmission image, according to text
Word becomes the safe line position of hollow out to light using Adaptive Thresholding in the distribution that light becomes in hollow out safety line and carries out binaryzation.Its
In, Adaptive Thresholding is that the whole region that light is become to the safe line position of hollow out is divided into three parts by word:The left side, centre, the right side
Side, middle part are the region of word, try to achieve the average value of the left side and the right gray scale as gray threshold.Binarization
In, when gray value is more than or equal to gray threshold to be black, when gray value less than gray threshold be it is white, it is safe so as to complete light change hollow out
The binaryzation of line position, denoising effectively can be carried out to background, greatly simplify the complexity of calculating.
Step S102, the row projection value that the light after binaryzation becomes the safe line position of hollow out is calculated, according to the row projection value
Obtain row projection value curve.
Wherein, bank note infrared view width is 200DPI resolution ratio, is highly 150DPI resolution ratio, and light becomes hollow out safety
Gray value sum on line per a line forms a row projection value, and the row projection value that whole light becomes the safe line position of hollow out forms row
Projection value curve, projection value can be larger when running into font for safety line row projection value curve after binaryzation, is thrown in no font
Shadow value can be smaller, projection value curve be whether there is with font and the change of font and change, be illustrated in figure 5 2015 editions 100 yuan
The image that the bank note light of face amount becomes after hollow out safety line binaryzation, such as the row drop shadow curve that Fig. 6 is corresponding.
Step S103, use row projection value curve described in dynamic time warping algorithmic match.
Wherein, the thought of dynamic time warping algorithm (Dynamic Time Warping, DTW) is:Due to voice signal
It is a kind of signal with quite big randomness, even if identical speaker, to identical word, the result pronounced each time is all not
With, it is also not possible to there is identical time span.Therefore with storage model matches when, the time of unknown words
Axle unevenly will be distorted or bent, so that its feature aligns with template characteristic.DTW is for waveform shape on the whole very phase
Seemingly, but it is the waveform not lined up on a timeline, there is good robustness.DTW by time series carry out extension and
Shorten, to calculate the similitude between two time serieses.DTW is retouched with the Time alignment function W (n) for meeting certain condition
The corresponding time relationship of test template and reference template is stated, regular letter when solving two template matches corresponding to cumulative distance minimum
Number.
Specifically, find an optimal Time alignment function so that the row projection value curve is thrown closest to standard row
Shadow value curve, obtain the minimum range summation of match point time.In the present embodiment, the characteristic time sequence of a reference template is set
It is classified as A={ a1,a2,…,ai, input security features time series B={ b to be identified1,b2,…,bi, wherein i ≠ j, if
Time alignment function is C={ c (1), c (2) ..., c (N) }, and wherein N is path length, and c (n)=(i (n), j (n)) represents n-th
Individual matching double points are made up of the individual characteristic vector of jth (n) of i-th (n) of reference template individual characteristic vector and template to be identified
Matching double points, distance (or distortion value) d (a therebetweeni(n),bi(n)) it is referred to as local matching distance, the minimum of match point time
It is apart from summation
Step S104, according to matching result, differentiate that light becomes the true and false of hollow out safety line.
In the present embodiment, threshold range when preset light becomes hollow out safety line to be genuine, 0.5-0.8 is arranged to, if D ∈
[0.5,0.8], then light change hollow out safety line is true;If D > 0.8 or D < 0.5, light becomes hollow out safety line as vacation.This area
Technical staff should be known that when can cause light change hollow out safety line according to the difference of image scanning instrument scanning accuracy to be genuine
Threshold range produce corresponding change, thus different threshold ranges is had using different scanning accuracies, it is no longer superfluous herein
State.
In summary, in the present embodiment, the recognition methods of bank note includes becoming the light of bank note the progress false distinguishing of hollow out safety line.
The safe line position of hollow out is become by the light for obtaining bank note, becomes the safe line position of hollow out to the light and carries out binaryzation;Calculate two-value
Light after change becomes the row projection value of the safe line position of hollow out, and row projection value curve is obtained according to the row projection value;Use dynamic
Time wrapping algorithm matches the row projection value curve;According to matching result, differentiate that light becomes the true and false of hollow out safety line.The present invention
Become the safe line position progress binaryzation of hollow out to light to obtain the row projection value of the light change safe line position of hollow out and obtain row projection value
Curve, become hollow out safety line characteristic information using dynamic time warping algorithmic match light, hollow out effectively can be become to the light of bank note
Safety line carries out false distinguishing identification, is advantageous to the true and false prevention that light becomes hollow out safety line.
Fig. 2 is refer to, it is a kind of the second implementation of the recognition methods of the bank note provided in the specific embodiment of the invention
The method flow diagram of example.As illustrated, the recognition methods, including:
Step S201, identifies the Information of bank note, and the Information is divided into:Positive positive, positive reverse, reverse side is just
To reverse with reverse side.
Specifically, can according to the crown word number magnetic image of bank note to bank note towards being identified, if crown word number magnetic chart
Picture is front forward direction in the lower left corner of bank note, then bank note, if crown word number magnetic image, in the upper right corner of bank note, bank note is positive
Reversely, if crown word number magnetic image is in the lower right corner inferior horn of bank note, bank note is that reverse side is positive, if crown word number magnetic image is in paper
The upper left corner of coin, then bank note is that reverse side is reverse.
Step S202, the infrared transmission image of bank note is obtained, choosing light according to the infrared transmission image becomes hollow out safety
Line position, cut the region subgraph that the light becomes the safe line position of hollow out.
Specifically, when the Information for identifying bank note is reverse for positive positive or reverse side, light becomes hollow out safety line position
Put on the right side of bank note, close to the right border 3-5cm position, cut the light and become the region subgraph of the safe line position of hollow out i.e.
The image of cutting the right border 3-5cm position;When the Information for identifying bank note is reverse front or reverse side forward direction, light
Become the safe line position of hollow out in the left side of bank note, close to left boundary 3-5cm position, cut the light and become hollow out safety line position
The region subgraph put cuts the image of left boundary 3-5cm position.
Step S203, the row projection value of the region subgraph is calculated, extracting light according to the row projection value becomes hollow out safety
The row projection value tag of line position.
In the present embodiment, Fig. 3 is the bank note schematic diagram of the miscellaneous editions provided in the specific embodiment of the invention, wherein a
For 1999 millboard coin, b is 2005 millboard coin, and c is 2015 millboard coin, and Fig. 4 is that the light of the bank note of miscellaneous editions in Fig. 3 becomes hollow out peace
The region subgraph row projection value curve map of full line position, wherein a are 1999 editions row projection value curves, and b is 2005 editions row projection values
Curve, c are 2015 editions row projection value curves, and view field is the projection value of the region subgraph of cutting herein, i.e., light becomes hollow out peace
The projection value in all fronts region, the abscissa of row projection value represent the width coordinate of bank note, and ordinate represents the sum of projection value.2015
Light be present and become hollow out safety line, its row projection value image and 1999 editions, the row projection value curve difference of 2005 editions in 100 yuan notes of version
It is very big.2015 editions 100 yuan notes become hollow out safety line due to light be present, and light becomes in hollow out safety line the word word for having 100
Sample, thus row projection value curve has approximate U curve shape feature.
Step S204, it is with light change to go out bank note according to the row projection value feature recognition of the light change safe line position of hollow out
The bank note of hollow out safety line version.
Specifically, become the row of bank note of the bank note of hollow out safety line version with becoming hollow out safety line version without light with light
The difference of projection value curve is very big, by extracting whether corresponding row projection value curvilinear characteristic easily can identify bank note
It is the bank note that there is light to become hollow out safety line version.In the present embodiment, 100 yuan note row projection value curves of various versions are as schemed
Shown in 4, in only c there is light and become hollow out safety line in 2015 editions 100 yuan notes, there is approximate U's in its row projection value curve
Curve shape feature, it may determine that light becomes hollow out safety line and whether there is with the presence or absence of this feature according in row projection value curve,
And the 100 yuan of printed words become according to light in hollow out safety line are accurately positioned light and become the safe line position of hollow out, are so as to identify bank note
It is no to belong to 2015 editions 100 yuan notes.In addition, bank note, in crosses paper money, same column data is by cmos image sensor (CIS)
Same position, so row projected image gray scale relative different is smaller.Version is identified because being directed to row projection properties, is calculated
Method robustness is stronger.It should be known to those skilled in the art that the word difference or position that light becomes in hollow out safety line are different
Safe alignment projection value curve can be caused to show different characteristic, similarly may determine that light becomes hollow out safety according to corresponding feature
Line whether there is.
Step S205, project value tag according to the row and be accurately positioned the light change safe line position of hollow out.
Specifically, become the row of bank note of the bank note of hollow out safety line version with becoming hollow out safety line version without light with light
The difference of projection value curve is very big, can be accurately positioned light change hollow out safety by extracting corresponding row projection value curvilinear characteristic
Line position.In the present embodiment, as shown in c in Fig. 4,2015 editions 100 yuan notes become hollow out safety line due to light be present, and light change is engraved
100 word printed words in empty safety line be present, thus row projection value curve has approximate U curve shape feature, according to this
Individual curvilinear characteristic can be accurately positioned light and become the safe line position of hollow out.Those skilled in the art should be known that light becomes hollow out safety line
On word it is different or position difference can cause safe alignment projection value curve to show different characteristic, similarly according to corresponding
Feature accurate judgement light becomes the position of hollow out safety line.
Step S206, become the safe line position of hollow out to the light using Adaptive Thresholding and carry out binaryzation.
Specifically, Adaptive Thresholding is the whole region that light is become to the safe line position of hollow out is divided into three parts by word:
The left side, centre, the right, middle part are the region of word, try to achieve the average value of the left side and the right gray scale as gray scale threshold
Value, when gray scale is more than or equal to gray threshold to be black, when gray scale less than gray threshold is white, so as to complete light change hollow out safety line position
The binaryzation put, denoising effectively can be carried out to background, greatly simplify the complexity of calculating.In the present embodiment, to 2015
Image after the safe line position progress binaryzation of light change hollow out of 100 yuan notes of version is as shown in Figure 5.
Step S207, the row projection value that the light after binaryzation becomes the safe line position of hollow out is calculated, according to the row projection value
Obtain row projection value curve.
Specifically, bank note infrared view width is 200DPI resolution ratio, it is highly 150DPI resolution ratio, light becomes hollow out peace
Gray value sum on all fronts per a line forms a row projection value, and the row projection value that whole light becomes the safe line position of hollow out is formed
Row projection value curve, projection value can be larger when running into font for safety line row projection value curve after binaryzation, when not having font
Row projection value can be smaller, row projection value curve be whether there is with font and the change of font and change.In the present embodiment, to 2015
Image after the safe line position progress binaryzation of light change hollow out of 100 yuan notes of version calculates its row projection value, obtained projection value
Curve is as shown in Figure 6.
Step S208, use row projection value curve described in dynamic time warping algorithmic match.
Step S209, according to matching result, differentiate that light becomes the true and false of hollow out safety line.
In summary, in the present embodiment, the recognition methods of bank note also includes identification and becomes hollow out safety line version with light
Bank note.The present embodiment utilizes magnetic stripe transmittancy, and in infrared transmission image, light change hollow out safety line transmittancy is weaker, and
Light becomes the feature that word transmittancy is stronger in hollow out safety line, and the row projection value curve for becoming hollow out safety line region according to light is special
Sign can accurately identify whether bank note is the bank note version that light becomes hollow out safety line be present;Safety line is used only in the present embodiment
Provincial characteristics identifies bank note version, reduces algorithm amount of calculation, improves algorithm recognition speed;Use dynamic time warping algorithm
Safety line characteristic information is extracted, false distinguishing identification is carried out to new edition bank note safety line, is advantageous to the prevention of the safety line true and false.
It is a kind of embodiment of the identification device of bank note of this programme below, a kind of embodiment of the identification device of bank note is based on
A kind of embodiment of recognition methods of bank note realizes that not most description, please join in a kind of embodiment of the identification device of bank note
Examine a kind of embodiment of the recognition methods of bank note.
Fig. 7 is refer to, it is a kind of the first implementation of the identification device of the bank note provided in the specific embodiment of the invention
The block diagram of example.As illustrated, the identification device, including:
Acquiring unit 710, the light for obtaining bank note become the safe line position of hollow out, become the safe line position of hollow out to the light
Carry out binaryzation.
Specifically, the word among light change hollow out safety line can be clearly indicated by infrared transmission image, according to text
Word becomes the safe line position of hollow out to light using Adaptive Thresholding in the distribution that light becomes in hollow out safety line and carries out binaryzation.Its
In, Adaptive Thresholding is that the whole region that light is become to the safe line position of hollow out is divided into three parts by word:The left side, centre, the right side
Side, middle part are the region of word, the average value of the left side and the right gray scale are tried to achieve as gray threshold, when gray scale is more than
Equal to gray threshold to be black, when gray scale less than gray threshold is white, so as to complete the binaryzation of the light change safe line position of hollow out, energy
Denoising effectively is carried out to background, greatly simplify the complexity of calculating.
Row projecting cell 720, become the row projection value of the safe line position of hollow out for calculating the light after binaryzation, according to described
Row projection value obtains row projection value curve.
Wherein, bank note infrared view width is 200DPI resolution ratio, is highly 150DPI resolution ratio, and light becomes hollow out safety
Gray value sum on line per a line forms a row projection value, and the row projection value that whole light becomes the safe line position of hollow out forms row
Projection value curve, projection value can be larger when running into font for safety line row projection value curve after binaryzation, is thrown in no font
Shadow value can be smaller, projection value curve be whether there is with font and the change of font and change.
Matching unit 730, for using row projection value curve described in dynamic time warping algorithmic match.
Wherein, the thought of dynamic time warping algorithm (Dynamic Time Warping, DTW) is:Due to voice signal
It is a kind of signal with quite big randomness, even if identical speaker, to identical word, the result pronounced each time is all not
With, it is also not possible to there is identical time span.Therefore with storage model matches when, the time of unknown words
Axle unevenly will be distorted or bent, so that its feature aligns with template characteristic.DTW is for waveform shape on the whole very phase
Seemingly, but it is the waveform not lined up on a timeline, there is good robustness.DTW by time series carry out extension and
Shorten, to calculate the similitude between two time serieses.DTW is retouched with the Time alignment function W (n) for meeting certain condition
The corresponding time relationship of test template and reference template is stated, regular letter when solving two template matches corresponding to cumulative distance minimum
Number.
Specifically, find an optimal Time alignment function so that the row projection value curve is thrown closest to standard row
Shadow value curve, obtain the minimum range summation of match point time.In the present embodiment, the characteristic time sequence of a reference template is set
It is classified as A={ a1,a2,…,ai, input security features time series B={ b to be identified1,b2,…,bj, wherein i ≠ j, if
Time alignment function is C={ c (1), c (2) ..., c (N) }, and wherein N is path length, and c (n)=(i (n), j (n)) represents n-th
Individual matching double points are made up of the individual characteristic vector of jth (n) of i-th (n) of reference template individual characteristic vector and template to be identified
Matching double points, distance (or distortion value) d (a therebetweeni(n),bi(n)) it is referred to as local matching distance, the minimum of match point time
It is apart from summation
False distinguishing unit 740, for according to matching result, differentiating that light becomes the true and false of hollow out safety line.
In the present embodiment, threshold range when preset word safety line is genuine, 0.5-0.8 is arranged to, if D ∈
[0.5,0.8], then word safety line is true;If D > 0.8 or D < 0.5, word safety line is false.Those skilled in the art
It should be known that threshold value model when can cause light change hollow out safety line according to the difference of image scanning instrument scanning accuracy to be genuine
The corresponding change of generation is enclosed, thus is likely to occur different threshold ranges, is not repeated here.
In summary, above-mentioned each unit cooperates, and becomes the safe line position of hollow out by the light for obtaining bank note, to the light
Become the safe line position of hollow out and carry out binaryzation;The row projection value that the light after binaryzation becomes the safe line position of hollow out is calculated, according to institute
State row projection value and obtain row projection value curve;Use row projection value curve described in dynamic time warping algorithmic match;According to matching
As a result, differentiate that light becomes the true and false of hollow out safety line.The present invention obtains light change to the safe line position progress binaryzation of light change hollow out and engraved
The row projection value of empty safe line position simultaneously obtains row projection value curve, becomes hollow out safety using dynamic time warping algorithmic match light
Line characteristic information, the progress false distinguishing identification of hollow out safety line effectively can be become to the light of bank note, be advantageous to light and become hollow out safety line
The true and false is prevented.
Fig. 8 is refer to, it is a kind of the second implementation of the identification device of the bank note provided in the specific embodiment of the invention
The block diagram of example.As illustrated, the identification device, including:
Acquiring unit 710, the light for obtaining bank note become the safe line position of hollow out, become the safe line position of hollow out to the light
Carry out binaryzation.
Cutter unit 711, for obtaining the infrared transmission image of bank note, light change is chosen according to the infrared transmission image and engraved
Empty safe line position, cut the region subgraph that the light becomes the safe line position of hollow out.
Specifically, when the Information for identifying bank note is reverse for positive positive or reverse side, light becomes hollow out safety line position
Put on the right side of bank note, close to the right border 3-5cm position, cut the light and become the region subgraph of the safe line position of hollow out i.e.
The image of cutting the right border 3-5cm position;When the Information for identifying bank note is reverse front or reverse side forward direction, light
Become the safe line position of hollow out in the left side of bank note, close to left boundary 3-5cm position, cut the light and become hollow out safety line position
The region subgraph put cuts the image of left boundary 3-5cm position.
Row projecting cell 712, for calculating the row projection value of the region subgraph, light is extracted according to the row projection value and become
The row projection value tag of the safe line position of hollow out.
In the present embodiment, Fig. 3 is the bank note schematic diagram of the miscellaneous editions provided in the specific embodiment of the invention, wherein a
For 1999 millboard coin, b is 2005 millboard coin, and c is 2015 millboard coin, and Fig. 4 is that the light of the bank note of miscellaneous editions in Fig. 3 becomes hollow out peace
The region subgraph row projection value curve map of full line position, wherein a are 1999 editions row projection value curves, and b is 2005 editions row projection values
Curve, c are 2015 editions row projection value curves, and view field is the projection value of the region subgraph of cutting herein, i.e., light becomes hollow out peace
The projection value in all fronts region, the abscissa of row projection value represent the width coordinate of bank note, ordinate represent projection value row and.It is aobvious
Light be present and become hollow out safety line, its row projection value image and 1999 editions, the row projection value song of 2005 editions in right 2015 editions 100 yuan notes
Line is widely different.Wherein, 2015 editions 100 yuan notes become hollow out safety line due to light be present, and exist in light change hollow out safety line
100 word printed words, thus row projection value curve has an approximate U curve shapes feature.
Positioning unit 713, the light change safe line position of hollow out is accurately positioned for projecting value tag according to the row.
Specifically, arranging projection value tag according to whether existing, judge that light becomes hollow out safety line and whether there is, be accurately positioned light
Become the safe line position of hollow out, so as to easily distinguish whether bank note belongs to the bank note that light be present and become hollow out safety line version.In addition,
For bank note in crosses paper money, same column data is by cmos image sensor (CIS) same position, so row projected image gray scale
Relative different is smaller.Version identifies that because being directed to row projection properties algorithm robustness is stronger.
In the present embodiment, be present light and become hollow out safety line in 2015 editions 100 yuan notes, and exist in light change hollow out safety line
100 word printed words, its row projection value curve have approximate U curve shape feature, according to this curve shape feature come
It is accurately positioned light and becomes the safe line position of hollow out.
Binarization unit 714, binaryzation is carried out for becoming the safe line position of hollow out to the light using Adaptive Thresholding.
Specifically, Adaptive Thresholding is the whole region that light is become to the safe line position of hollow out is divided into three parts by word:
The left side, centre, the right, middle part are the region of word, try to achieve the average value of the left side and the right gray scale as gray scale threshold
Value, when gray scale is more than or equal to gray threshold to be black, when gray scale less than gray threshold is white, so as to complete light change hollow out safety line position
The binaryzation put, denoising effectively can be carried out to background, greatly simplify the complexity of calculating.
Row projecting cell 720, become the row projection value of the safe line position of hollow out for calculating the light after binaryzation, according to described
Row projection value obtains row projection value curve.
Matching unit 730, for using row projection value curve described in dynamic time warping algorithmic match.
False distinguishing unit 740, for according to matching result, differentiating that light becomes the true and false of hollow out safety line.
Towards recognition unit 750, for identifying the Information of bank note, the Information is divided into:Positive positive, front
Reversely, reverse side is positive and reverse side is reverse.
Specifically, can according to the crown word number magnetic image of bank note to bank note towards being identified, if crown word number magnetic chart
Picture is front forward direction in the lower left corner of bank note, then bank note, if crown word number magnetic image, in the upper right corner of bank note, bank note is positive
Reversely, if crown word number magnetic image is in the lower right corner inferior horn of bank note, bank note is that reverse side is positive, if crown word number magnetic image is in paper
The upper left corner of coin, then bank note is that reverse side is reverse.
Version recognition unit 760, for becoming the row projection value feature recognition paper delivery of the safe line position of hollow out according to the light
Coin is the bank note that there is light to become hollow out safety line version.
In summary, the present embodiment utilizes magnetic stripe transmittancy, in infrared transmission image, safety line transmittancy compared with
It is weak, and the stronger feature of word transmittancy in safety line, accurately identify whether bank note is to have light to become hollow out safety line
Bank note version;Safety line provincial characteristics identification bank note version is used only in the present embodiment, reduces algorithm amount of calculation, improves calculation
Method recognition speed;The present embodiment is entered using dynamic time warping algorithm extraction safety line characteristic information to new edition bank note safety line
Row false distinguishing identifies, is advantageous to the prevention of the safety line true and false.
With respect to the training and identification in neural network BP training algorithm, the algorithm in the embodiment of the present invention only has recognizer,
Algorithmic code is easier to safeguard;Bank note version is identified using only safety line provincial characteristics, reduces algorithm amount of calculation, improves calculation
Method recognition speed;Independent of the brightness of CIS sensors collection image, the influence that variation of image grayscale identifies to version is weakened,
Using magnetic stripe transmittancy, in infrared transmission image, safety line transmittancy is weaker, and in safety line word transmittancy compared with
Whether strong feature, cog region separation coin are that light becomes hollow out safety line version bank note, improve version discrimination;In addition using dynamic
Time wrapping algorithm matches safety line characteristic information and carries out false distinguishing identification to 2015 editions bank note safety lines, is advantageous to the safety line true and false
Prevention.
The technical principle of the present invention is described above in association with specific embodiment.These descriptions are intended merely to explain the present invention's
Principle, and limiting the scope of the invention can not be construed in any way.Based on explanation herein, the technology of this area
Personnel would not require any inventive effort the other embodiments that can associate the present invention, and these modes are fallen within
Within protection scope of the present invention.
Claims (9)
- A kind of 1. recognition methods of bank note, it is characterised in that including:The light for obtaining bank note becomes the safe line position of hollow out, becomes the safe line position of hollow out to the light and carries out binaryzation;The row projection value that the light after binaryzation becomes the safe line position of hollow out is calculated, it is bent to obtain row projection value according to the row projection value Line;Use row projection value curve described in dynamic time warping algorithmic match;According to matching result, differentiate that light becomes the true and false of hollow out safety line;The acquisition light becomes the safe line position of hollow out, becomes the safe line position of hollow out to the light and carries out binaryzation, including:The infrared transmission image of bank note is obtained, choosing light according to the infrared transmission image becomes the safe line position of hollow out, cuts institute State the region subgraph that light becomes the safe line position of hollow out;The row projection value of the region subgraph is calculated, the row that the light change safe line position of hollow out is extracted according to the row projection value project Value tag;Value tag, which is projected, according to the row is accurately positioned the light change safe line position of hollow out;Become the safe line position of hollow out to the light using Adaptive Thresholding and carry out binaryzation.
- 2. method according to claim 1, it is characterised in that the row projection value for calculating the region subgraph, according to institute Row projection value extraction light is stated to become after the row projection value tag of the safe line position of hollow out, it is described accurate according to the row projection value tag It is determined that position light becomes before the safe line position of hollow out, in addition to:It is to become hollow out safety line version with light to go out bank note according to the row projection value feature recognition of the light change safe line position of hollow out This bank note.
- 3. method according to claim 1, it is characterised in that the light for obtaining bank note becomes the safe line position of hollow out, to institute Light is stated to become before the safe line position progress binaryzation of hollow out, in addition to:The Information of bank note is identified, the Information is divided into:Positive positive, front is reversely, reverse side is positive and reverse side is reverse;The light for obtaining bank note becomes the safe line position of hollow out, becomes the safe line position of hollow out to the light and carries out binaryzation, specifically For:When the Information for identifying bank note is reverse for positive positive or reverse side, the light change that bank note is obtained on the right side of bank note is engraved Empty safe line position, become the safe line position of hollow out to the light and carry out binaryzation;When the Information for identifying bank note is reverse front or reverse side forward direction, the light change that bank note is obtained on the left of bank note is engraved Empty safe line position, become the safe line position of hollow out to the light and carry out binaryzation.
- 4. method according to claim 1, it is characterised in that described to use row projection described in dynamic time warping algorithmic match It is worth curve, is specially:Find an optimal Time alignment function so that the row projection value curve obtains closest to standard row projection value curve Obtain the minimum range summation of match point time.
- 5. method according to claim 4, it is characterised in that it is described according to matching result, differentiate that light becomes hollow out safety line The true and false, it is specially:If the minimum range summation of the match point time, in the range of preset distance, the light becomes hollow out safety line to be true, Otherwise it is false.
- A kind of 6. identification device of bank note, it is characterised in that including:Acquiring unit, the light for obtaining bank note become the safe line position of hollow out, become the safe line position of hollow out to the light and carry out two Value;Row projecting cell, become the row projection value of the safe line position of hollow out for calculating the light after binaryzation, projected according to the row Value obtains row projection value curve;Matching unit, for using row projection value curve described in dynamic time warping algorithmic match;False distinguishing unit, for according to matching result, differentiating that light becomes the true and false of hollow out safety line;The acquiring unit, is specifically used for:The infrared transmission image of bank note is obtained, choosing light according to the infrared transmission image becomes the safe line position of hollow out, cuts institute State the region subgraph that light becomes the safe line position of hollow out;The row projection value of the region subgraph is calculated, the row that the light change safe line position of hollow out is extracted according to the row projection value project Value tag;Value tag, which is projected, according to the row is accurately positioned the light change safe line position of hollow out;Become the safe line position of hollow out to the light using Adaptive Thresholding and carry out binaryzation.
- 7. device according to claim 6, it is characterised in that also include:Towards recognition unit, for identifying the Information of bank note, the Information is divided into:Positive positive, front is reversely, instead Face is positive and reverse side is reverse.
- 8. device according to claim 6, it is characterised in that also include:Version recognition unit, it is to have that the row projection value feature recognition for becoming the safe line position of hollow out according to the light, which goes out bank note, Light becomes the bank note of hollow out safety line version.
- 9. device according to claim 6, it is characterised in that the acquiring unit includes:Cutter unit, for obtaining the infrared transmission image of bank note, light is chosen according to the infrared transmission image and becomes hollow out safety Line position, cut the region subgraph that the light becomes the safe line position of hollow out;Row projecting cell, for calculating the row projection value of the region subgraph, light is extracted according to the row projection value and becomes hollow out peace The row projection value tag of full line position;Positioning unit, the light change safe line position of hollow out is accurately positioned for projecting value tag according to the row;Binarization unit, binaryzation is carried out for becoming the safe line position of hollow out to the light using Adaptive Thresholding.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510506975.6A CN105184955B (en) | 2015-08-18 | 2015-08-18 | A kind of recognition methods of bank note and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510506975.6A CN105184955B (en) | 2015-08-18 | 2015-08-18 | A kind of recognition methods of bank note and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105184955A CN105184955A (en) | 2015-12-23 |
CN105184955B true CN105184955B (en) | 2018-03-02 |
Family
ID=54907003
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510506975.6A Expired - Fee Related CN105184955B (en) | 2015-08-18 | 2015-08-18 | A kind of recognition methods of bank note and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105184955B (en) |
Families Citing this family (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105719386A (en) * | 2016-01-18 | 2016-06-29 | 新达通科技股份有限公司 | Paper currency identification method and device based on optically-variable hollowed windowing security line |
CN106251467B (en) * | 2016-08-05 | 2019-03-12 | 深圳怡化电脑股份有限公司 | A kind of detection method and device of safety line magnetic feature |
CN106373256B (en) * | 2016-08-23 | 2019-04-26 | 深圳怡化电脑股份有限公司 | The method and system of RMB version identification |
CN106408746B (en) * | 2016-08-25 | 2019-03-12 | 深圳怡化电脑股份有限公司 | A kind of safety line recognition methods and device |
CN106447910B (en) * | 2016-09-08 | 2019-07-05 | 深圳怡化电脑股份有限公司 | A kind of method and device of paper money recognition |
CN106504406B (en) * | 2016-11-01 | 2019-11-15 | 深圳怡化电脑股份有限公司 | A kind of method and device identifying bank note |
CN106652166B (en) * | 2016-11-01 | 2019-06-07 | 深圳怡化电脑股份有限公司 | A kind of detection method and system of stuck banknotes |
CN108022363A (en) * | 2016-11-02 | 2018-05-11 | 深圳怡化电脑股份有限公司 | A kind of bank note towards recognition methods and device |
CN108074323B (en) * | 2016-11-15 | 2021-01-01 | 深圳怡化电脑股份有限公司 | Paper money facing identification method and device thereof |
CN108074322B (en) * | 2016-11-17 | 2020-09-15 | 深圳怡化电脑股份有限公司 | Image identification method and device |
CN107195070B (en) * | 2017-05-18 | 2019-09-20 | 深圳怡化电脑股份有限公司 | A kind of secret note identification method and device |
CN107274543B (en) * | 2017-06-23 | 2019-07-09 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note, device, terminal device and computer storage medium |
CN107369243B (en) * | 2017-06-23 | 2019-08-27 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note, device, terminal device and computer storage medium |
CN107610318B (en) * | 2017-08-23 | 2019-12-06 | 成都术有科技有限公司 | Method for discriminating 2015 edition RMB by utilizing metal wire backlight imaging |
CN107610320A (en) * | 2017-09-06 | 2018-01-19 | 深圳怡化电脑股份有限公司 | A kind of bank slip recognition method and apparatus |
CN109697443B (en) * | 2017-10-23 | 2022-10-11 | 深圳怡化电脑股份有限公司 | Paper money serial number segmentation method and device |
CN109300220B (en) * | 2018-08-29 | 2021-12-10 | 广州广电运通金融电子股份有限公司 | Paper authentication method, device and equipment based on safety line and readable storage medium |
CN110956737B (en) * | 2020-01-07 | 2021-10-12 | 武汉卓目科技有限公司 | Safety line identification method and device |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5184157B2 (en) * | 2008-03-14 | 2013-04-17 | 株式会社ユニバーサルエンターテインメント | Paper sheet identification device and paper sheet identification method |
CN101908241B (en) * | 2010-08-03 | 2012-05-16 | 广州广电运通金融电子股份有限公司 | Method and system for identifying valued documents |
CN102096962A (en) * | 2010-12-23 | 2011-06-15 | 北京新岸线软件科技有限公司 | Paper currency detecting method and device |
CN102737435A (en) * | 2011-04-11 | 2012-10-17 | 北京新岸线数字图像技术有限公司 | Paper money discrimination method and device |
CN104091388B (en) * | 2014-07-22 | 2016-06-22 | 新达通科技股份有限公司 | A kind of paper money discrimination method based on magnetic image and device |
CN104298989B (en) * | 2014-08-20 | 2017-08-04 | 深圳大学 | False distinguishing method and its system based on zebra stripes Infrared Image Features |
-
2015
- 2015-08-18 CN CN201510506975.6A patent/CN105184955B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN105184955A (en) | 2015-12-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105184955B (en) | A kind of recognition methods of bank note and device | |
CN101350063B (en) | Method and apparatus for locating human face characteristic point | |
CN102324132B (en) | Bank-note detecting method by identifying ultraviolet-light image and system | |
Abburu et al. | Currency recognition system using image processing | |
CN105069900B (en) | A kind of method and device for handling bank note information | |
TW201039248A (en) | Method and system for identifying image and outputting identification result | |
CN107067533A (en) | The method and device that a kind of bank note differentiates | |
CN105046807B (en) | A kind of counterfeit money recognition methods and system based on smart mobile phone | |
CN104318257A (en) | Paper currency recognition method and system | |
CN105243729B (en) | A kind of method and system for identifying bank note version | |
CN103778409A (en) | Human face identification method based on human face characteristic data mining and device | |
CN106803091B (en) | Method and system for identifying currency value of paper money | |
CN105447956A (en) | Spliced banknote detection method | |
CN105788064B (en) | Bill identification method and device | |
CN107393115A (en) | Banknote serial number identification and counterfeit identification method | |
WO2017024779A1 (en) | Material anti-counterfeiting method and material anti-counterfeiting system | |
CN105957237B (en) | A kind of version recognition methods of bank note and device | |
CN108806058A (en) | A kind of paper currency detecting method and device | |
CN106447897A (en) | Method and apparatus for detecting magnetic characteristics of paper note | |
CN107527423B (en) | Paper money anti-counterfeiting identification method and paper money identification device | |
CN106780953B (en) | Paper money counterfeit distinguishing method and system based on double-crown-word number | |
CN108269349A (en) | A kind of bill handling method, apparatus, equipment and storage medium | |
CN103903329A (en) | Financial instrument authenticity identification device with front CIS | |
Kennard et al. | Offline signature verification and forgery detection using a 2-D geometric warping approach | |
CN106934914B (en) | Method and device for anti-counterfeiting detection of paper money |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180302 Termination date: 20210818 |
|
CF01 | Termination of patent right due to non-payment of annual fee |