CN105303676B - A kind of version recognition methods of bank note and system - Google Patents
A kind of version recognition methods of bank note and system Download PDFInfo
- Publication number
- CN105303676B CN105303676B CN201510705726.XA CN201510705726A CN105303676B CN 105303676 B CN105303676 B CN 105303676B CN 201510705726 A CN201510705726 A CN 201510705726A CN 105303676 B CN105303676 B CN 105303676B
- Authority
- CN
- China
- Prior art keywords
- gray level
- pixel point
- image
- level image
- bank note
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Abstract
A kind of version recognition methods the invention discloses bank note and system, this method include：The gray level image in the distinguishing characteristics region of bank note is obtained, the distinguishing characteristics region is the inconsistent region of the same position and characteristics of image of the different editions bank note of same value of money；Binary conversion treatment is carried out to the gray level image in the distinguishing characteristics region, generates binary image；Count the quantity of the black pixel point in the binary image or the quantity of white pixel point；By the quantity of the black pixel point or white pixel point quantity compared with preset threshold value, the version of bank note is identified according to comparison result.The gray level image that the present invention passes through the inconsistent region of same position characteristics of image of acquisition different editions bank note, black pixel point and white pixel point are generated after carrying out binaryzation to gray level image, the version of bank note is identified according to the quantity of black pixel point or white pixel point, recognition methods is simple, accurately.
Description
Technical field
The present invention relates to the version recognition methods of paper money recognition technical field more particularly to a kind of bank note and systems.
Background technology
With economic development, the amount of paper money in circulation is increasing, and law-breaker is to seek exorbitant profit, and manufactures the people of various versions
Coin counterfeit money, endangers financial security.But paper money in circulation has 1999 editions, 2005 editions and i.e. by hair style on the market now
2015 editions, due between the various versions with currency type bank note may size it is identical, it is background texture, rich in color, paper can not be passed through
Magnify small or color to determine its version.Traditional identification technology needs artificial setting identification point, such methods to support noise
Drag is low, and when characteristic area is slightly polluted or deviated, discriminating is easy error.
Invention content
The present invention proposes version recognition methods and the system of a kind of bank note, can accurately identify the version of bank note, and
Method is simple.
For this purpose, the present invention uses following technical scheme：
In a first aspect, a kind of version recognition methods of bank note, including：
The gray level image in the distinguishing characteristics region of bank note is obtained, the distinguishing characteristics region is the different editions of same value of money
The inconsistent region of the same position and characteristics of image of bank note；
Binary conversion treatment is carried out to the gray level image in the distinguishing characteristics region, generates binary image；
Count the quantity of the black pixel point in the binary image or the quantity of white pixel point；
By the quantity of the black pixel point or white pixel point quantity compared with preset threshold value, identified according to comparison result
Go out the version of bank note.
Wherein, the gray level image in the distinguishing characteristics region for obtaining bank note includes：
Obtain the gray level image of entire paper coin；
The gray level image in distinguishing characteristics region is intercepted from the gray level image of the entire paper coin.
Wherein, the gray level image to the distinguishing characteristics region carries out binary conversion treatment, generates binary image
Step includes：
Calculate the average gray of the gray level image in the distinguishing characteristics region；
Binaryzation is carried out to the gray level image in the distinguishing characteristics region using the average gray as binary-state threshold
Processing generates binary image.
Wherein, the preset threshold value includes the second preset threshold value；
The gray level image in distinguishing characteristics region for obtaining bank note includes：100 yuans of bank note are obtained in resolution ratio
For the gray level image of longitudinal 150DPI, transverse direction 200DPI, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in intercept
Position is X=[500：650], [380 Y=：415] the second gray level image；
The gray level image to the distinguishing characteristics region carries out binary conversion treatment, generates binary image and includes：It is right
Second gray level image carries out binary conversion treatment, generates the second binary image；
The quantity of black pixel point or the quantity of white pixel point in the statistics binary image include：Statistics
The quantity N2 of the second black pixel point in second binary image；
It is described by the black pixel point or white pixel point quantity compared with preset threshold value, identified according to comparison result
The version of bank note includes：Judge whether the quantity N2 of second black pixel point is less than the second preset threshold value, if so, identification
It is 1999 editions to go out the bank note.
Wherein, the preset threshold value further includes the first preset threshold value；
Whether the quantity N2 for judging second black pixel point is less than after the second preset threshold value, further includes：
If it is not, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=[970：1220]、Y
=[330：415] the first gray level image；
Binary conversion treatment is carried out to first gray level image, generates the first binary image；
Count the quantity N1 of the first black pixel point in first binary image；
Judge whether the quantity N1 of first black pixel point is less than the first preset threshold value；
If so, identifying that the bank note is 2015 editions；
If it is not, then identifying that the bank note is 2005 editions.
Wherein, the preset threshold value includes the first preset threshold value；
The gray level image in distinguishing characteristics region for obtaining bank note includes：100 yuans of bank note are obtained in resolution ratio
For the gray level image of longitudinal 150DPI, transverse direction 200DPI, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in intercept
Position is X=[970：1220], [330 Y=：415] the first gray level image；
The gray level image to the distinguishing characteristics region carries out binary conversion treatment, generates binary image and includes：It is right
First gray level image carries out binary conversion treatment, generates the first binary image；
The quantity of black pixel point or the quantity of white pixel point in the statistics binary image include：Statistics
The quantity N1 of the first black pixel point in first binary image；
It is described by the black pixel point or white pixel point quantity compared with preset threshold value, identified according to comparison result
The version of bank note includes：Judge whether the quantity N1 of first black pixel point is less than the first preset threshold value, if so, identification
It is 2015 editions to go out the bank note.
Wherein, the preset threshold value further includes the second preset threshold value；
Whether the quantity N1 for judging first gray level image is less than after the first preset threshold value, further includes：
If it is not, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=[500：650]、Y
=[380：415] the second gray level image；
Binary conversion treatment is carried out to second gray level image, generates the second binary image；
Count the quantity N2 of the second black pixel point in second binary image；
Judge whether the quantity N2 of second black pixel point is less than the second preset threshold value；
If so, identifying that the bank note is 1999 editions；
If it is not, then identifying that the bank note is 2005 editions.
Wherein, the preset threshold value includes the first preset threshold value and the second preset threshold value；
The gray level image in distinguishing characteristics region for obtaining bank note includes：
100 yuans of bank note are obtained in the gray level image that resolution ratio is longitudinal direction 150DPI, transverse direction 200DPI, are indulged from described
To 150DPI, transverse direction 200DPI gray level image in interception position be X=[970：1220], [330 Y=：415] the first gray scale
Image and position are X=[500：650], [380 Y=：415] the second gray level image；
The gray level image to the distinguishing characteristics region carries out binary conversion treatment, generates binary image and includes：
Binary conversion treatment is carried out to first gray level image, generates the first binary image, and to second gray scale
Image carries out binary conversion treatment, generates the second binary image；
The quantity of black pixel point or the quantity of white pixel point in the statistics binary image include：
Count the quantity N1 of the first black pixel point of the first binary image kind, and statistics second binaryzation
The quantity N2 of second black pixel point of image kind；
It is described by the black pixel point or white pixel point quantity compared with preset threshold value, identified according to comparison result
The version of bank note includes：
If the quantity N1 of the first black pixel point is less than the first preset threshold value, identify that the bank note is 2015 editions；
If the quantity N2 of the second black pixel point is less than the second preset threshold value, identify that the bank note is 1999 editions；
If the quantity N1 of the first black pixel point is more than or equal to the quantity N2 of the first preset threshold value and the second black pixel point
More than or equal to the second preset threshold value, then identify that the bank note is 2005 editions.
Second aspect, a kind of version identifying system of bank note, including：
Acquisition module, the gray level image in the distinguishing characteristics region for obtaining bank note, the distinguishing characteristics region are same
The inconsistent region of the same position and characteristics of image of the different editions bank note of value of money；
Processing module carries out binary conversion treatment for the gray level image to the distinguishing characteristics region, generates binary picture
Picture；
Statistical module, the number of quantity or white pixel point for counting the black pixel point in the binary image
Amount；
Identification module, for by the quantity of the black pixel point or white pixel point quantity compared with preset threshold value, root
The version of bank note is identified according to comparison result.
Wherein, the acquisition module includes：
Acquiring unit, the gray level image for obtaining entire paper coin；
Interception unit, the gray level image for intercepting distinguishing characteristics region from the gray level image of the entire paper coin.
A kind of version recognition methods of bank note provided by the invention and system, by the identical bits for obtaining different editions bank note
The gray level image for setting the inconsistent region of characteristics of image generates black pixel point and white picture after carrying out binaryzation to gray level image
Vegetarian refreshments identifies the version of bank note according to the quantity of black pixel point or white pixel point, and recognition methods is simple, accurately.
Description of the drawings
Fig. 1 is a kind of method flow diagram of the version recognition methods embodiment of bank note provided by the invention.
Fig. 2 a are a kind of a kind of method stream of preferred embodiment of the version recognition methods embodiment of bank note provided by the invention
Cheng Tu.
Fig. 2 b are a kind of methods of another preferred embodiment of the version recognition methods embodiment of bank note provided by the invention
Flow chart.
Fig. 3 is the schematic diagram at 100 yuans of the back side.
Fig. 4 is a kind of method stream of another preferred embodiment of the version recognition methods embodiment of bank note provided by the invention
Cheng Tu.
Fig. 5 is a kind of method stream of another preferred embodiment of the version recognition methods embodiment of bank note provided by the invention
Cheng Tu.
Fig. 6 is a kind of method stream of another preferred embodiment of the version recognition methods embodiment of bank note provided by the invention
Cheng Tu.
Fig. 7a-7c is respectively 1999 editions, 2005 editions, the gray level image in 2015 editions 100 yuans of regions 1.
Fig. 7 d-7f are respectively 1999 editions, 2005 editions, the gray level image in 2015 editions 100 yuans of regions 2.
Fig. 8 a-8c are respectively 1999 editions, 2005 editions, the gray-scale map after the binaryzation in 2015 editions 100 yuans of regions 1
Picture.
Fig. 8 d-8f are respectively 1999 editions, 2005 editions, the gray-scale map after the binaryzation in 2015 editions 100 yuans of regions 2
Picture.
Fig. 9 is a kind of structural schematic diagram of the version identifying system embodiment of bank note provided by the invention.
Figure 10 is that a kind of a kind of structure of preferred embodiment of the version identifying system embodiment of bank note provided by the invention is shown
It is intended to.
Specific implementation mode
Below in conjunction with attached drawing, the technical solution further illustrated the present invention by specific embodiment.
On the one hand, a kind of version recognition methods of bank note includes the following steps with reference to figure 1：
S101, obtain bank note distinguishing characteristics region gray level image, the distinguishing characteristics region be same value of money not
With the inconsistent region of the same position and characteristics of image of version bank note.
S102, binary conversion treatment is carried out to the gray level image in the distinguishing characteristics region, generates binary image.
The quantity of S103, the quantity of black pixel point in the statistics binary image or white pixel point.
S104, by the quantity of the black pixel point or white pixel point quantity compared with preset threshold value, according to compare knot
Fruit identifies the version of bank note.
The bank note of different editions, black pixel point that the gray level image in distinguishing characteristics region generates and white pixel point
Number is different, and the number by counting its black pixel point or white pixel point just can recognize which version the bank note belongs to
This.
The present invention by obtain different editions bank note the inconsistent region of same position characteristics of image gray level image, it is right
Gray level image generates black pixel point and white pixel point after carrying out binaryzation, according to black pixel point or the number of white pixel point
It measures to identify the version of bank note, recognition methods is simple, accurately.
Preferably, as shown in Figure 2 a, step S101 includes：
S1011, the gray level image for obtaining entire paper coin.
S1012, the gray level image that distinguishing characteristics region is intercepted from the gray level image of the entire paper coin.
Preferably, as shown in Figure 2 b, step S102 includes：
S1021, calculate the distinguishing characteristics region gray level image average gray.
S1022, the gray level image in the distinguishing characteristics region is carried out using the average gray as binary-state threshold
Binary conversion treatment generates binary image.
Binary conversion treatment is carried out to the gray level image in distinguishing characteristics region according to average gray, generates binary image,
The gray value for the pixel for being more than average gray in binary image is set as 255, is less than the pixel of average gray
Gray value is set as 0；The point that gray value is 255 is white pixel point, and the point that gray value is 0 is black pixel point.
In practice, the brightness of image of each banknote acquisition is not fully unified, the banknote image brightness as caused by hardware
Deviation also has large effect to recognition result.When image is whole partially bright or partially dark, the gray value of characteristic area also can be corresponding
It is bigger than normal or less than normal, therefore select the average gray of distinguishing characteristics area pixel as binary-state threshold herein, figure can be followed
The intrinsic brilliance of picture adjusts, and has adaptivity, and compared with common fixed threshold, the binarization method of this paper is for extraction
The target signature accuracy in distinguishing characteristics region is more preferable, and effect is not much different compared with OTSU algorithms, but speed is faster.
As a kind of preferred embodiment of the present invention, the bank note is 100 yuans, and the preset threshold value includes first pre-
Set threshold value and the second preset threshold value.
As shown in figure 4, step S101 is specially S201：Obtain 100 yuans of bank note resolution ratio be longitudinal direction 150DPI,
The gray level image of lateral 200DPI, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=
[500：650], [380 Y=：415] the second gray level image.Second gray level image is the gray-scale map in region 2 shown in Fig. 3
Picture.
100 yuans of the placement direction is that the back side is positive, when 100 yuans of back side forward directions, with the resolution
Rate is that the left upper end of the gray level image of longitudinal direction 150DPI, transverse direction 200DPI indicates abscissa and vertical seat respectively as origin, X and Y
Mark.
Step S102 is specially S202：Binary conversion treatment is carried out to second gray level image, generates the second binary picture
Picture.
Step S103 is specially S203：Count the quantity N2 of the second black pixel point in second binary image.
Step S104 includes：
S204, judge whether the quantity N2 of second black pixel point is less than the second preset threshold value.
Preferably, the ranging from 800-1000 of the second preset threshold value, the second preset threshold value value 900 in the present embodiment.
S205, if so, identify the bank note be 1999 editions.
Whether the quantity N2 for judging second black pixel point is less than after the second preset threshold value, further includes：
S206, if it is not, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=[970：
1220], [330 Y=：415] the first gray level image；First gray level image is the gray level image in region 1 shown in Fig. 3.
S207, binary conversion treatment is carried out to first gray level image, generates the first binary image.
The quantity N1 of S208, the first black pixel point in statistics first binary image.
S209, judge whether the quantity N1 of first black pixel point is less than the first preset threshold value.
Preferably, the ranging from 6500-8500 of first preset threshold value, the first preset threshold value value in the present embodiment
7500。
S210, if so, identify the bank note be 2015 editions.
S211, if it is not, then identify the bank note be 2005 editions.
The different recognition sequences of three kinds of versions of bank note also have large effect to the run time of whole flow process, when
When 2015 millboard coin are just issued, the 100 of different editions yuan circulation is 2005 editions on the market>1999 editions>2015 editions.It at this time should be first
Selection area 2 preferentially determines whether 1999 editions.If it is being directly entered 1999 editions other identifying processings, if not selecting again
Determine region 1, differentiation is 2005 editions or 2015 editions.The identification for carrying out version according to this sequence helps to shorten the fortune of whole flow process
Make the time, it is efficient.
The quantity of white pixel point is that the sum of the pixel in binary image subtracts the quantity of black pixel point, because
This can pass through the number of the white pixel point in the statistics binary image as another preferred embodiment of the present embodiment
Amount, the corresponding preset threshold value of the white pixel point quantity is compared, the version of bank note is identified according to comparison result.
As a kind of preferred embodiment of the present invention, the bank note is 100 yuans, and the preset threshold value includes first pre-
Set threshold value and the second preset threshold value.
As shown in figure 5, step S101 is specially S301：Obtain 100 yuans of bank note resolution ratio be longitudinal direction 150DPI,
The gray level image of lateral 200DPI, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=
[970：1220], [330 Y=：415] the first gray level image.First gray level image is the gray-scale map in region 1 shown in Fig. 3
Picture.
100 yuans of the placement direction is that the back side is positive, when 100 yuans of back side forward directions, with the resolution
Rate is that the left upper end of the gray level image of longitudinal direction 150DPI, transverse direction 200DPI indicates abscissa and vertical seat respectively as origin, X and Y
Mark.
Step S102 is specially S202：Binary conversion treatment is carried out to first gray level image, generates the first binary picture
Picture.
Step S103 is specially S303：Count the quantity N1 of the first black pixel point in first binary image.
Step S104 includes：
S304, judge whether the quantity N1 of first black pixel point is less than the first preset threshold value.
Preferably, the ranging from 6500-8500 of the first preset threshold value, in the present embodiment, the first preset threshold value value 7500.
S305, if so, identify the bank note be 2015 editions.
Whether the quantity N1 for judging first black pixel point is less than after the first preset threshold value, further includes：
S306, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=[500：650]、Y
=[380：415] the second gray level image.Second gray level image is the gray level image in region 2 shown in Fig. 3.
S307, binary conversion treatment is carried out to second gray level image, generates the second binary image.
The quantity N2 of S308, the second black pixel point in statistics second binary image.
S309, judge whether the quantity N2 of second black pixel point is less than the second preset threshold value.
Preferably, the ranging from 800-1000 of the second preset threshold value, in the present embodiment, the second preset threshold value value 900.
S310, if so, identify the bank note be 1999 editions.
S311, if it is not, then identify the bank note be 2005 editions.
The different recognition sequences of three kinds of versions of bank note also have large effect to the run time of whole flow process, when
2015 millboard coin sphere of circulation are larger, and after the time is longer, 100 yuan of circulatioies of different editions are 2015 editions on the market>2005
Version>1999 editions.First selection area 1 is answered at this time, preferentially determines whether 2015 editions.If it is be directly entered 2015 editions other identification
Processing, if not selection area 2 again, differentiation is 2005 editions or 1999 editions.The identification for carrying out version according to this sequence helps
It is efficient in the running time for shortening whole flow process.
Therefore, according to the current intelligence of 100 yuans of 2015 new edition, can flexible adjustment algorithm flow, make entire
Identification process efficiency highest, the speed of service are most fast.
The quantity of white pixel point is that the sum of the pixel in binary image subtracts the quantity of black pixel point, because
This can pass through the number of the white pixel point in the statistics binary image as another preferred embodiment of the present embodiment
Amount, the corresponding preset threshold value of the white pixel point quantity is compared, the version of bank note is identified according to comparison result.
As another preferred embodiment of the present invention, the bank note is 100 face amount RMB.
Step S1011 is specially：Obtain the gray level image of longitudinal direction 150DPI, transverse direction 200DPI.The preset threshold value includes
First preset threshold value and the second preset threshold value.
Preferably, the ranging from 6500-8500 of the first preset threshold value, the ranging from 800-1000 of the second preset threshold value, this
In embodiment, the first preset threshold value value 7500, the second preset threshold value value 900.
With reference to figure 6, step S101 includes S401：It is longitudinal direction 150DPI, transverse direction that 100 yuans of bank note, which are obtained, in resolution ratio
The gray level image of 200DPI, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=[970：
1220], [330 Y=：415] the first gray level image and position is X=[500：650], [380 Y=：415] the second gray-scale map
Picture.
100 yuans of the placement direction is that the back side is positive, when 100 yuans of back side forward directions, with the resolution
Rate is that the left upper end of the gray level image of longitudinal direction 150DPI, transverse direction 200DPI indicates abscissa and vertical seat respectively as origin, X and Y
Mark.
The first gray level image such as Fig. 7 a of 1999 editions, 2005 editions and 2015 editions 100 face amount RMB, Fig. 7 b, Fig. 7 c institutes
Show.
The second gray level image such as Fig. 7 d of 1999 editions, 2005 editions and 2015 editions 100 face amount RMB, Fig. 7 e, Fig. 7 f institutes
Show.
Step S102 includes S402：Binary conversion treatment is carried out to first gray level image, generates the first binary image,
Binary conversion treatment is carried out with to second gray level image, generates the second binary image.
The first binary image such as Fig. 8 a, Fig. 8 b, Fig. 8 c of 1999 editions, 2005 editions and 2015 editions 100 face amount RMB
It is shown；The second binary image such as Fig. 8 d of 1999 editions, 2005 editions and 2015 editions 100 face amount RMB, Fig. 8 e, Fig. 8 f institutes
Show.
Step S103 includes S403：The quantity N1 of the first black pixel point of the first binary image kind is counted, and
Count the quantity N2 of the second black pixel point of the second binary image kind.
Step S104 includes：
If the quantity N1 of S404, the first black pixel point is less than the first preset threshold value, identify that the bank note is 2015
Version.
If the quantity N2 of S405, the second black pixel point is less than the second preset threshold value, identify that the bank note is 1999
Version.
If the quantity N1 of S406, the first black pixel point is more than or equal to the number of the first preset threshold value and the second black pixel point
It measures N2 and is more than or equal to the second preset threshold value, then identify that the bank note is 2005 editions.
Preferably, the ranging from 6500-8500 of first preset threshold value, the ranging from 800- of the first preset threshold value
1000, in the present embodiment, the first preset threshold value value 7500, the second preset threshold value value 900.
The number of the bank note of different editions, the black pixel point of the gray level image generation in distinguishing characteristics region is different,
Quantity by counting the black pixel point in two distinguishing characteristics regions just can recognize which version the bank note belongs to.
The quantity of white pixel point is that the sum of the pixel in binary image subtracts the quantity of black pixel point, because
This can pass through the number of the white pixel point in the statistics binary image as another preferred embodiment of the present embodiment
Amount, the corresponding preset threshold value of the white pixel point quantity is compared, the version of bank note is identified according to comparison result.
A kind of version recognition methods of bank note provided in an embodiment of the present invention, including：Obtain the distinguishing characteristics region of bank note
Gray level image, the distinguishing characteristics region is the inconsistent region of same position characteristics of image of different editions bank note；To institute
It states gray level image and carries out binary conversion treatment, generate black pixel point；Count the quantity of the black pixel point；By the quantity with
Preset threshold value compares, and identifies the version of bank note.The present invention is by obtaining the same position characteristics of image of different editions bank note not
The gray level image in consistent region generates black pixel point, according to the number of black pixel point after carrying out binaryzation to gray level image
It measures to identify the version of bank note, recognition methods is simple, accurately.The present invention can be according to the circulation of 2015 editions 100 face amount RMB
Situation, neatly adjustment algorithm flow, keeps entire identification process efficiency highest, the speed of service most fast.
On the other hand, the version identifying system of a kind of bank note, the system is corresponding with the version recognition methods of above-mentioned bank note,
Its not yet detailed content please refers to above method embodiment.
As shown in figure 9, the version identifying system of the bank note includes：
Acquisition module 101, obtains the gray level image in the distinguishing characteristics region of bank note, and the distinguishing characteristics region is same coin
The inconsistent region of the same position and characteristics of image of the different editions bank note of value.
Processing module 102 carries out binary conversion treatment to the gray level image in the distinguishing characteristics region, generates binary picture
Picture；.
Statistical module 103, quantity or white pixel point for counting the black pixel point in the binary image
Quantity.
Identification module 104, by the quantity of the black pixel point or white pixel point quantity compared with preset threshold value, according to
Comparison result identifies the version of bank note.
Preferably, the acquisition module 101 includes：
Acquiring unit 1011, the gray level image for obtaining entire paper coin.
Interception unit 1012, the gray-scale map for intercepting distinguishing characteristics region from the gray level image of the entire paper coin
Picture.
The processing module 102 includes：
Computing unit, the average gray of the gray level image for calculating the distinguishing characteristics region.
Processing unit is used for using the average gray as binary-state threshold to the gray-scale map in the distinguishing characteristics region
As carrying out binary conversion treatment, binary image is generated.
As another preferred embodiment, the bank note is 100 yuans.The preset threshold value includes the second preset threshold
Value.
The acquisition module 101 is used for：It is longitudinal direction 150DPI, transverse direction that 100 yuans of bank note, which are obtained, in resolution ratio
The gray level image of 200DPI, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=[500：
650], [380 Y=：415] the second gray level image.
The processing module 102 is used for：Binary conversion treatment is carried out to second gray level image, generates the second binary picture
Picture.
The statistical module 103 is used for：Count the quantity N2 of the second black pixel point in second binary image.
The identification module 104 is used for：Judge whether the quantity N2 of second black pixel point is less than the second preset threshold
Value, if so, identifying that the bank note is 1999 editions.
The preset threshold value further includes the first preset threshold value.
The acquisition module 101 is additionally operable to：When the quantity N2 of second black pixel point is more than or equal to the second preset threshold
Value, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=[970：1220], [330 Y=：
415] the first gray level image.
Processing module 102 is additionally operable to：Binary conversion treatment is carried out to first gray level image, generates the first binary picture
Picture.
Statistical module 103 is additionally operable to：Count the quantity N1 of the first black pixel point in first binary image.
Identification module 104 is additionally operable to：Judge whether the quantity N1 of first black pixel point is less than the first preset threshold value,
If so, identifying that the bank note is 2015 editions；If it is not, then identifying that the bank note is 2005 editions.
As another preferred embodiment, the preset threshold value includes the first preset threshold value.
The acquisition module 101 is used for：It is longitudinal direction 150DPI, transverse direction that 100 yuans of bank note, which are obtained, in resolution ratio
The gray level image of 200DPI, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=[970：
1220], [330 Y=：415] the first gray level image.
The processing module 102 is used for：Binary conversion treatment is carried out to first gray level image, generates the first binary picture
Picture.
The statistical module 103 is used for：Count the quantity N1 of the first black pixel point in first binary image.
The identification module 104 is used for：
Judge whether the quantity N1 of first black pixel point is less than the first preset threshold value, if so, identifying described
Bank note is 2015 editions.
The preset threshold value further includes the second preset threshold value.
The acquisition module 101 is additionally operable to：When first gray level image quantity N1 be more than or equal to the first preset threshold value,
From the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=[500：650], [380 Y=：415]
Second gray level image.
Processing module 102 is additionally operable to：Binary conversion treatment is carried out to second gray level image, generates the second binary picture
Picture.
Statistical module 103 is additionally operable to：Count the quantity N2 of the second black pixel point in second binary image.
Identification module 104 is additionally operable to：Judge whether the quantity N2 of second black pixel point is less than the second preset threshold value,
If so, identifying that the bank note is 1999 editions；If it is not, then identifying that the bank note is 2005 editions.
As another preferred embodiment, the bank note is 100 face amount RMB.The preset threshold value includes the first preset threshold
Value and the second preset threshold value.
The acquisition module 101 is used for：It is longitudinal direction 150DPI, transverse direction that 100 yuans of bank note, which are obtained, in resolution ratio
The gray level image of 200DPI, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=[970：
1220], [330 Y=：415] the first gray level image and position is X=[500：650], [380 Y=：415] the second gray-scale map
Picture.
The processing module 102 is used for：Binary conversion treatment is carried out to first gray level image, generates the first binary picture
Picture, and binary conversion treatment is carried out to second gray level image, generate the second binary image.
The statistical module 103 is used for：The quantity N1 of the first black pixel point of the first binary image kind is counted,
With the quantity N2 for the second black pixel point for counting the second binary image kind.
The identification module 104 is used for：
If the quantity N1 of the first black pixel point is less than the first preset threshold value, identify that the bank note is 2015 editions.
If the quantity N2 of the second black pixel point is less than the second preset threshold value, identify that the bank note is 1999 editions.
If the quantity N1 of the first black pixel point is more than or equal to the quantity N2 of the first preset threshold value and the second black pixel point
More than or equal to the second preset threshold value, then identify that the bank note is 2005 editions.
The quantity of white pixel point is that the sum of the pixel in binary image subtracts the quantity of black pixel point, because
This can pass through the number of the white pixel point in the statistics binary image as another preferred embodiment of the present embodiment
Amount, the corresponding preset threshold value of the white pixel point quantity is compared, the version of bank note is identified according to comparison result.
A kind of version identifying system of bank note provided by the invention, acquisition module, the distinguishing characteristics area for obtaining bank note
The gray level image in domain, the distinguishing characteristics region are the inconsistent region of the same position characteristics of image of different editions bank note；Place
Module is managed, for carrying out binary conversion treatment to the gray level image, generates black pixel point；Statistical module, it is described for counting
The quantity of black pixel point；Identification module, for the quantity compared with preset threshold value, to be identified the version of bank note.This hair
The bright gray level image by obtaining the inconsistent region of same position characteristics of image of different editions bank note carries out gray level image
Black pixel point is generated after binaryzation, the version of bank note is identified according to the quantity of black pixel point, and recognition methods is simple, accurate
Really.
The technical principle of the embodiment of the present invention is described above in association with specific embodiment, these descriptions are intended merely to explain this
The principle of inventive embodiments, and it cannot be construed to the limitation to protection domain of the embodiment of the present invention in any way, this field
Technical staff would not require any inventive effort the other specific implementation modes that can associate the embodiment of the present invention, these sides
Formula is fallen within the protection domain of the embodiment of the present invention.
Claims (7)
1. a kind of version recognition methods of bank note, feature are being, including：
The gray level image in the distinguishing characteristics region of bank note is obtained, the distinguishing characteristics region is the different editions bank note of same value of money
Same position and the inconsistent region of characteristics of image, the gray level image in the distinguishing characteristics region include the first gray level image and
Second gray level image；
Calculate the average gray of the gray level image in the distinguishing characteristics region；
Binary conversion treatment is carried out to the gray level image in the distinguishing characteristics region using the average gray as binary-state threshold,
Binary image is generated, the binary image includes being carried out at binaryzation to first gray level image in the distinguishing characteristics region
It manages the first obtained binary image and what binary conversion treatment obtained is carried out to second gray level image in the distinguishing characteristics region
Second binary image；
Count the quantity of the black pixel point in the binary image, the quantity of the black pixel point, including the first two-value
Change the quantity of the quantity and the black pixel point in the second binary image of the black pixel point in image；
By the quantity of the black pixel point compared with preset threshold value, the version of bank note is identified according to comparison result, wherein institute
It includes the first preset threshold value and the second preset threshold value, the quantity and preset threshold value by the black pixel point to state preset threshold value
Compare, includes comparing the quantity of the black pixel point in the first binary image and the first preset threshold value, and by the two or two
The quantity of black pixel point in value image and the second preset threshold value compare.
2. version recognition methods as described in claim 1, which is characterized in that the ash in the distinguishing characteristics region for obtaining bank note
Spending image includes：
Obtain the gray level image of entire paper coin；
The gray level image in distinguishing characteristics region is intercepted from the gray level image of the entire paper coin.
3. version recognition methods as claimed in claim 2, which is characterized in that
The gray level image in distinguishing characteristics region for obtaining bank note includes：It is vertical that 100 yuans of bank note, which are obtained, in resolution ratio
To the gray level image of 150DPI, transverse direction 200DPI, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position
For X=[500：650], [380 Y=：415] the second gray level image；
The gray level image to the distinguishing characteristics region carries out binary conversion treatment, generates binary image and includes：To described
Second gray level image carries out binary conversion treatment, generates the second binary image；
The quantity of black pixel point in the statistics binary image includes：It counts in second binary image
The quantity N2 of second black pixel point；
It is described by the black pixel point compared with preset threshold value, identify that the version of bank note includes according to comparison result：Judge
Whether the quantity N2 of second black pixel point is less than the second preset threshold value, if so, identifying that the bank note is 1999 editions；
If it is not, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=[970：1220], Y=
[330：415] the first gray level image；
Binary conversion treatment is carried out to first gray level image, generates the first binary image；
Count the quantity N1 of the first black pixel point in first binary image；
Judge whether the quantity N1 of first black pixel point is less than the first preset threshold value；
If so, identifying that the bank note is 2015 editions；
If it is not, then identifying that the bank note is 2005 editions.
4. version recognition methods as claimed in claim 2, which is characterized in that
The gray level image in distinguishing characteristics region for obtaining bank note includes：It is vertical that 100 yuans of bank note, which are obtained, in resolution ratio
To the gray level image of 150DPI, transverse direction 200DPI, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position
For X=[970：1220], [330 Y=：415] the first gray level image；
The gray level image to the distinguishing characteristics region carries out binary conversion treatment, generates binary image and includes：To described
First gray level image carries out binary conversion treatment, generates the first binary image；
The quantity of black pixel point in the statistics binary image includes：It counts in first binary image
The quantity N1 of first black pixel point；
It is described by the black pixel point compared with preset threshold value, identify that the version of bank note includes according to comparison result：Judge
Whether the quantity N1 of first black pixel point is less than the first preset threshold value, if so, identifying that the bank note is 2015 editions；
If it is not, from the longitudinal direction 150DPI, transverse direction 200DPI gray level image in interception position be X=[500：650], Y=
[380：415] the second gray level image；
Binary conversion treatment is carried out to second gray level image, generates the second binary image；
Count the quantity N2 of the second black pixel point in second binary image；
Judge whether the quantity N2 of second black pixel point is less than the second preset threshold value；
If so, identifying that the bank note is 1999 editions；
If it is not, then identifying that the bank note is 2005 editions.
5. version recognition methods as claimed in claim 2, which is characterized in that the ash in the distinguishing characteristics region for obtaining bank note
Spending image includes：
100 yuans of bank note are obtained in the gray level image that resolution ratio is longitudinal direction 150DPI, transverse direction 200DPI, from the longitudinal direction
150DPI, transverse direction 200DPI gray level image in interception position be X=[970：1220], [330 Y=：415] the first gray-scale map
Picture and position are X=[500：650], [380 Y=：415] the second gray level image；
The gray level image to the distinguishing characteristics region carries out binary conversion treatment, generates binary image and includes：
Binary conversion treatment is carried out to first gray level image, generates the first binary image, and to second gray level image
Binary conversion treatment is carried out, the second binary image is generated；
The quantity of black pixel point in the statistics binary image includes：
Count the quantity N1 of the first black pixel point of the first binary image kind, and statistics second binary image
The quantity N2 of second black pixel point of kind；
It is described by the black pixel point compared with preset threshold value, identify that the version of bank note includes according to comparison result：
If the quantity N1 of the first black pixel point is less than the first preset threshold value, identify that the bank note is 2015 editions；
If the quantity N2 of the second black pixel point is less than the second preset threshold value, identify that the bank note is 1999 editions；
If the quantity N1 of the first black pixel point is more than or equal to the first preset threshold value and the quantity N2 of the second black pixel point is more than
Equal to the second preset threshold value, then identify that the bank note is 2005 editions.
6. a kind of version identifying system of bank note, which is characterized in that including：
Acquisition module, the gray level image in the distinguishing characteristics region for obtaining bank note, the distinguishing characteristics region are same value of money
Different editions bank note same position and the inconsistent region of characteristics of image, the gray level image in the distinguishing characteristics region include
First gray level image and the second gray level image；
Processing module, the average gray of the gray level image for calculating the distinguishing characteristics region, and the gray scale is averaged
It is worth and binary conversion treatment is carried out to the gray level image in the distinguishing characteristics region as binary-state threshold, generates binary image, institute
It includes carrying out the first two-value that binary conversion treatment obtains to first gray level image in the distinguishing characteristics region to state binary image
Change image and the second binary image that binary conversion treatment obtains is carried out to second gray level image in the distinguishing characteristics region；
Statistical module, the quantity for counting the black pixel point in the binary image, the quantity of the black pixel point,
The quantity of quantity including the black pixel point in the first binary image and the black pixel point in the second binary image；
Identification module, for compared with preset threshold value, bank note to be identified according to comparison result for the quantity of the black pixel point
Version, wherein the preset threshold value includes the first preset threshold value and the second preset threshold value, described by the black pixel point
Quantity includes by the quantity of the black pixel point in the first binary image and the first preset threshold value ratio compared with preset threshold value
Compared with, and the quantity of the black pixel point in the second binary image and the second preset threshold value compared.
7. version identifying system as claimed in claim 6, which is characterized in that the acquisition module includes：
Acquiring unit, the gray level image for obtaining entire paper coin；
Interception unit, the gray level image for intercepting distinguishing characteristics region from the gray level image of the entire paper coin.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510705726.XA CN105303676B (en) | 2015-10-27 | 2015-10-27 | A kind of version recognition methods of bank note and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510705726.XA CN105303676B (en) | 2015-10-27 | 2015-10-27 | A kind of version recognition methods of bank note and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105303676A CN105303676A (en) | 2016-02-03 |
| CN105303676B true CN105303676B (en) | 2018-08-24 |
Family
ID=55200891
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510705726.XA Expired - Fee Related CN105303676B (en) | 2015-10-27 | 2015-10-27 | A kind of version recognition methods of bank note and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105303676B (en) |
Families Citing this family (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105957238B (en) * | 2016-05-20 | 2019-02-19 | 聚龙股份有限公司 | A kind of paper currency management method and its system |
| CN106204616B (en) * | 2016-07-21 | 2020-07-24 | 深圳怡化电脑股份有限公司 | Method and device for identifying currency value of Iran paper money |
| CN106355744B (en) * | 2016-08-24 | 2019-07-26 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of Indonesian Rupiah value of money and device |
| CN106340116B (en) * | 2016-08-26 | 2019-06-07 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note and device |
| CN106447904B (en) * | 2016-09-09 | 2020-09-15 | 深圳怡化电脑股份有限公司 | Method and device for identifying paper money |
| CN108073921B (en) * | 2016-11-10 | 2021-10-08 | 深圳怡化电脑股份有限公司 | Method and device for identifying banknote information |
| CN106530483B (en) * | 2016-11-10 | 2019-04-26 | 深圳怡化电脑股份有限公司 | A kind of bank note is 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 |
| CN106600810B (en) * | 2016-12-05 | 2019-04-26 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note and device |
| CN108171864B (en) * | 2016-12-05 | 2020-04-28 | 深圳怡化电脑股份有限公司 | Method and device for identifying paper money version |
| CN106600812B (en) * | 2016-12-14 | 2019-12-06 | 深圳怡化电脑股份有限公司 | Paper money identification method and device |
| CN106846609A (en) * | 2016-12-16 | 2017-06-13 | 恒银金融科技股份有限公司 | It is a kind of based on perceiving the bank note face amount of Hash towards recognition methods |
| CN106815923A (en) * | 2016-12-29 | 2017-06-09 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note version and device |
| CN106780967B (en) * | 2017-01-09 | 2019-06-11 | 深圳怡化电脑股份有限公司 | A kind of bank note version recognition methods and device |
| CN106875542B (en) * | 2017-01-09 | 2020-01-14 | 深圳怡化电脑股份有限公司 | Method and device for identifying paper money version |
| CN106875539B (en) * | 2017-01-11 | 2019-04-26 | 深圳怡化电脑股份有限公司 | The detection method and device of bank note |
| CN108399677A (en) * | 2017-02-08 | 2018-08-14 | 深圳怡化电脑股份有限公司 | A kind of bank note version recognition methods and device |
| CN106898078B (en) * | 2017-02-21 | 2019-12-06 | 深圳怡化电脑股份有限公司 | Port currency version identification method and device |
| CN107103683B (en) * | 2017-04-24 | 2019-12-10 | 深圳怡化电脑股份有限公司 | Paper money identification method and device, electronic equipment and storage medium |
| CN107134047B (en) * | 2017-05-11 | 2020-06-09 | 深圳怡化电脑股份有限公司 | White watermark detection method and device |
| CN107240184B (en) * | 2017-06-05 | 2020-03-27 | 深圳怡化电脑股份有限公司 | Method, device and equipment for identifying versions of plastic coins |
| CN107610322B (en) * | 2017-10-11 | 2020-02-07 | 深圳怡化电脑股份有限公司 | Banknote version identification method and device, electronic equipment and storage medium |
| CN108711213B (en) * | 2018-03-30 | 2020-01-14 | 深圳怡化电脑股份有限公司 | Method and device for identifying black and white blocks of paper money zebra stripes |
| CN111768410B (en) * | 2019-05-22 | 2024-04-05 | 北京沃东天骏信息技术有限公司 | Image processing method and device |
| CN112530079B (en) * | 2019-09-17 | 2022-10-11 | 深圳怡化电脑股份有限公司 | Method, device, terminal equipment and storage medium for detecting bill factors |
| CN112232331A (en) * | 2020-12-17 | 2021-01-15 | 恒银金融科技股份有限公司 | Recognition and classification method for infrared image characteristic region of paper money |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102136058A (en) * | 2011-04-26 | 2011-07-27 | 中国农业大学 | Bar code image identification method |
| CN103093468A (en) * | 2013-01-22 | 2013-05-08 | 清华大学 | Dense object segmentation method based on image morphology |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7187795B2 (en) * | 2001-09-27 | 2007-03-06 | Cummins-Allison Corp. | Document processing system using full image scanning |
| US8351699B2 (en) * | 2008-12-18 | 2013-01-08 | Accusoft Corporation | Methods and apparatus for auto image binarization |
| CN104537364A (en) * | 2015-01-29 | 2015-04-22 | 华中科技大学 | Dollar bill denomination and edition identifying method based on texture analysis |
| CN104715240A (en) * | 2015-03-25 | 2015-06-17 | 华中科技大学 | Hong Kong dollar texture image version classifying method based on gray-level co-occurrence matrix |
-
2015
- 2015-10-27 CN CN201510705726.XA patent/CN105303676B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102136058A (en) * | 2011-04-26 | 2011-07-27 | 中国农业大学 | Bar code image identification method |
| CN103093468A (en) * | 2013-01-22 | 2013-05-08 | 清华大学 | Dense object segmentation method based on image morphology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105303676A (en) | 2016-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105303676B (en) | A kind of version recognition methods of bank note and system | |
| CN104091388B (en) | A kind of paper money discrimination method based on magnetic image and device | |
| US9827599B2 (en) | Banknote recognition and classification method and system | |
| CN106952393B (en) | Paper money identification method and device, electronic equipment and storage medium | |
| CN107103683B (en) | Paper money identification method and device, electronic equipment and storage medium | |
| CN107610322B (en) | Banknote version identification method and device, electronic equipment and storage medium | |
| CN104318238A (en) | Method for extracting crown word numbers from scanned banknote images in banknote detection module | |
| CN107180479B (en) | Bill identification method, device, equipment and storage medium | |
| CN106780966B (en) | A kind of paper money discrimination method and device | |
| CN104899965A (en) | Multi-national paper money serial number identification method based on sorting machine | |
| CN106920318B (en) | Method and device for identifying paper money | |
| CN107038794B (en) | Method, device and equipment for identifying authenticity of paper money and storage medium | |
| CN105069899B (en) | The method and banknote tester of a kind of currency examination | |
| CN106875545A (en) | The discrimination method and device of a kind of bank note | |
| CN108510639B (en) | Paper money counterfeit discriminating method and device, currency detector and storage medium | |
| CN106600812B (en) | Paper money identification method and device | |
| CN107578526B (en) | Banknote identification method and device, terminal equipment and readable storage medium | |
| CN104537364A (en) | Dollar bill denomination and edition identifying method based on texture analysis | |
| CN106898078B (en) | Port currency version identification method and device | |
| CN106447904B (en) | Method and device for identifying paper money | |
| CN107705414B (en) | A kind of recognition methods of bank note, device, terminal device and storage medium | |
| CN107527423B (en) | Paper money anti-counterfeiting identification method and paper money identification device | |
| CN103489255A (en) | Device and method for detecting defect of bank note | |
| CN109543554B (en) | Bill detection method, device, terminal and computer readable storage medium | |
| CN106951902A (en) | A kind of image binaryzation processing method and processing device |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180824 Termination date: 20211027 |