CN106296975A - The recognition methods of a kind of dollar bill face amount and device - Google Patents
The recognition methods of a kind of dollar bill face amount and device Download PDFInfo
- Publication number
- CN106296975A CN106296975A CN201610641324.2A CN201610641324A CN106296975A CN 106296975 A CN106296975 A CN 106296975A CN 201610641324 A CN201610641324 A CN 201610641324A CN 106296975 A CN106296975 A CN 106296975A
- Authority
- CN
- China
- Prior art keywords
- bank note
- edge
- face amount
- external reflection
- infrared external
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D7/20—Testing patterns thereon
- G07D7/2016—Testing patterns thereon using feature extraction, e.g. segmentation, edge detection or Hough-transformation
Abstract
The invention discloses recognition methods and the device of a kind of dollar bill face amount, wherein, the method includes: obtain the infrared external reflection image of bank note back side characteristic area；Described infrared external reflection image is carried out rim detection, obtains edge detection results；The main edge of at least two of described infrared external reflection image is extracted based on edge detection results；Distance between quantity based on described main edge and described main edge, determines the face amount of described bank note.The embodiment of the present invention can quickly identify the face amount of bank note, and improves the accuracy identified.
Description
Technical field
The present invention relates to value of money identification technical field, particularly relate to recognition methods and the device of a kind of dollar bill face amount.
Background technology
In prior art, the bank note such as such as RMB, the banknote of different face amounts, it varies in size.Therefore, to bank note
Face amount identification during, can be easier by the face amount of the size identification bank note of bank note.
During inventor performs the present invention, find prior art exists following defect: dollar bill is as outward
The one of which of coin, its different denominations bank note size zero difference, the face amount of the bank note of this situation cannot be directly by bank note
Size is identified.Therefore, it is impossible to quickly identify the face amount of bank note.
Summary of the invention
In view of this, the present invention provides recognition methods and the device of a kind of dollar bill face amount, it is possible to quickly identify bank note
Face amount, and improve identify accuracy.
First aspect, embodiments provides the recognition methods of a kind of dollar bill face amount, including:
Obtain the infrared external reflection image of bank note back side characteristic area；
Described infrared external reflection image is carried out rim detection, obtains edge detection results；
The main edge of at least two of described infrared external reflection image is extracted based on edge detection results；
Distance between quantity based on described main edge and described main edge, determines the face amount of described bank note.
Further, the infrared external reflection image of described acquisition bank note back side characteristic area, including:
Obtain bank note resolution be longitudinal 150DPI, the back side infrared external reflection image of horizontal 150DPI；
From the pixel matrix of described infrared external reflection image, intercepting line number is between 100 to 200, and row number arrive 110
The region that pixel between 430 is formed, and using red as bank note back side characteristic area of the infrared external reflection image in described region
External reflectance image；Wherein, in the back side infrared external reflection image of bank note, the number of pixels across point is 610, the back side of described bank note
In infrared external reflection image, the number of longitudinal pixel is 260.
Further, described rim detection that described infrared external reflection image is carried out, obtain edge detection results and include:
By canny operator, described infrared external reflection image is carried out rim detection, obtain the first marginal point set；
In described first marginal point set, gray value is more than the pixel of first threshold as true marginal point；
If the gray value of target pixel points is between Second Threshold to first threshold and adjacent with described target pixel points
The gray value of at least one pixel more than first threshold, using described target pixel points as true marginal point；Wherein, gray value
It is false marginal point less than the pixel of Second Threshold；
The second marginal point set is formed based on described true marginal point.
Further, the described main edge of at least two extracting described infrared external reflection image based on edge detection results, bag
Include:
By Hough straight-line detection method, described second marginal point set is carried out straight-line detection, obtain at least two edges straight
Line；
If the distance between two-end-point on object edge straight line is more than pre-set length threshold, by straight for described object edge
Line is as the main edge of described infrared external reflection image.
Further, the distance between quantity based on described main edge and described main edge, determine the face amount of bank note,
Including:
If the quantity at described main edge is 2, then judge that the face amount of bank note is 20 dollars；
If the quantity at described main edge is 4, determine the face amount of bank note based on the distance between described main edge.
Further, the described face amount determining bank note based on the distance between described main edge, including:
In described 4 main edges,
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,15 ± 5 and 85 ± 5, it is judged that the face of bank note
Value is 5 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,70 ± 5 and 85 ± 5, it is judged that the face of bank note
Value is 10 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,115 ± 5 and 35 ± 5, it is judged that bank note
Face amount is 50 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 35 ± 5,20 ± 5 and 40 ± 5, it is judged that the face of bank note
Value is 100 dollars.
Second aspect, the embodiment of the present invention additionally provides the identification device of a kind of dollar bill face amount, including:
Image collection module, for obtaining the infrared external reflection image of bank note back side characteristic area；
Testing result acquisition module, for described infrared external reflection image carries out rim detection, obtains edge detection results；
Main edge extracting module, for extracting the main limit of at least two of described infrared external reflection image based on edge detection results
Edge；
Face amount determines module, for the distance between quantity based on described main edge and described main edge, determines institute
State the face amount of bank note.
Further, described image collection module, specifically for:
Obtain bank note resolution be longitudinal 150DPI, the back side infrared external reflection image of horizontal 150DPI；
From the pixel matrix of described infrared external reflection image, intercepting line number is between 100 to 200, and row number arrive 110
The region that pixel between 430 is formed, and using red as bank note back side characteristic area of the infrared external reflection image in described region
External reflectance image；Wherein, in the back side infrared external reflection image of bank note, the number of pixels across point is 610, the back side of described bank note
In infrared external reflection image, the number of longitudinal pixel is 260.
Further, described testing result acquisition module, specifically for:
By canny operator, described infrared external reflection image is carried out rim detection, obtain the first marginal point set；
In described first marginal point set, gray value is more than the pixel of first threshold as true marginal point；
If the gray value of target pixel points is between Second Threshold to first threshold and adjacent with described target pixel points
The gray value of at least one pixel more than first threshold, using described target pixel points as true marginal point；Wherein, gray value
It is false marginal point less than the pixel of Second Threshold；
The second marginal point set is formed based on described true marginal point.
Further, described main edge extracting module, specifically for:
By Hough straight-line detection method, the second marginal point set is carried out straight-line detection, obtain at least two edge lines；
If the distance between two-end-point on object edge straight line is more than pre-set length threshold, by straight for described object edge
Line is as the main edge of described infrared external reflection image.
Further, described face amount determines module, specifically for: if the quantity at described main edge is 2, then judge paper
The face amount of coin is 20 dollars；
If the quantity at described main edge is 4, determine the face amount of bank note based on the distance between described main edge.
Further, described determine that the face amount of bank note includes based on the distance between described main edge: on described 4 main limits
In edge,
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,15 ± 5 and 85 ± 5, it is judged that the face of bank note
Value is 5 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,70 ± 5 and 85 ± 5, it is judged that the face of bank note
Value is 10 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,115 ± 5 and 35 ± 5, it is judged that bank note
Face amount is 50 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 35 ± 5,20 ± 5 and 40 ± 5, it is judged that the face of bank note
Value is 100 dollars.
The recognition methods of a kind of dollar bill that the present invention provides and device, by obtaining the red of bank note back side characteristic area
External reflectance image, and extract the main edge to infrared external reflection image, the distance between quantity based on main edge and main edge
Determine the face amount of bank note, it is possible to quickly identify the face amount of bank note, and improve the accuracy identified.
Accompanying drawing explanation
By the detailed description that non-limiting example is made made with reference to the following drawings of reading, other of the present invention
Feature, purpose and advantage will become more apparent upon:
Fig. 1 a is the recognition methods flow chart of a kind of dollar bill face amount that the embodiment of the present invention one provides；
Fig. 1 b is the infrared external reflection image at the 5 dollar bill back sides that the embodiment of the present invention one provides；
Fig. 1 c is the infrared external reflection image at the 10 dollar bill back sides that the embodiment of the present invention one provides；
Fig. 1 d is the infrared external reflection image at the 20 dollar bill back sides that the embodiment of the present invention one provides；
Fig. 1 e is the infrared external reflection image at the 50 dollar bill back sides that the embodiment of the present invention one provides；
Fig. 1 f is the infrared external reflection image of 100 dollar bills that the embodiment of the present invention one provides；
Fig. 1 g is the infrared external reflection image of the 5 dollar bill back side characteristic areas that the embodiment of the present invention one provides；
Fig. 1 h is the infrared external reflection image of the 10 dollar bill back side characteristic areas that the embodiment of the present invention one provides；
Fig. 1 i is the infrared external reflection image of the 20 dollar bill back side characteristic areas that the embodiment of the present invention one provides；
Fig. 1 j is the infrared external reflection image of the 50 dollar bill back side characteristic areas that the embodiment of the present invention one provides；
Fig. 1 k is the infrared external reflection image of the 100 dollar bill back side characteristic areas that the embodiment of the present invention one provides；
Fig. 2 a is the recognition methods flow chart of a kind of dollar bill face amount that the embodiment of the present invention two provides；
Fig. 2 b is that the infrared external reflection image to 5 dollar bill back side characteristic areas that the embodiment of the present invention two provides carries out two
Image after value；
Fig. 2 c is that the infrared external reflection image to 10 dollar bill back side characteristic areas that the embodiment of the present invention two provides is carried out
Image after binaryzation；
Fig. 2 d is that the infrared external reflection image to 20 dollar bill back side characteristic areas that the embodiment of the present invention two provides is carried out
Image after binaryzation；
Fig. 2 e is that the infrared external reflection image to 50 dollar bill back side characteristic areas that the embodiment of the present invention two provides is carried out
Image after binaryzation；
Fig. 2 f is that the infrared external reflection image to 100 dollar bill back side characteristic areas that the embodiment of the present invention two provides is carried out
Image after binaryzation；
Fig. 3 is the identification apparatus structure block diagram of a kind of dollar bill face amount that the embodiment of the present invention three provides.
Detailed description of the invention
The present invention is described in further detail with embodiment below in conjunction with the accompanying drawings.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that, in order to just
Part related to the present invention is illustrate only rather than full content in description, accompanying drawing.
Embodiment one
Fig. 1 a is the recognition methods flow chart of a kind of dollar bill face amount that the embodiment of the present invention one provides, described method
The identification device having dollar bill face amount performs, and described device is performed by software and/or hardware, and described device typically configures
In the equipment such as computer.As shown in Figure 1a, the technical scheme that the present embodiment provides specifically includes:
S110: obtain the infrared external reflection image of bank note back side characteristic area.
In the present embodiment, exemplary, obtain the infrared external reflection image of bank note back side characteristic area, including: obtain bank note
Resolution be longitudinal 150DPI, the back side infrared external reflection image of horizontal 150DPI；Pixel from described infrared external reflection image
In matrix, intercepting line number is between 100 to 200, and the region that the pixel that row number are between 110 to 430 is formed, and by described
The infrared external reflection image in region is as the infrared external reflection image of bank note back side characteristic area；Wherein, the back side infrared external reflection of bank note
In image, the number of pixels across point is 610, and in the back side infrared external reflection image of described bank note, the number of longitudinal pixel is
260.It is to say, the number of the pixel of the back side infrared external reflection image of bank note is 610 × 260.Therefore, the back side of bank note is red
In the pixel matrix of external reflectance image, line number is at 1-610, and row number are at 1-260.
Fig. 1 b is the infrared external reflection image at the 5 dollar bill back sides that the embodiment of the present invention one provides；Fig. 1 c is that the present invention is real
Execute the infrared external reflection image at the 10 dollar bill back sides that example one provides；Fig. 1 d is 20 dollar bills that the embodiment of the present invention one provides
The infrared external reflection image at the back side；Fig. 1 e is the infrared external reflection image at the 50 dollar bill back sides that the embodiment of the present invention one provides；Figure
1f is the infrared external reflection image of 100 dollar bills that the embodiment of the present invention one provides.As shown in Fig. 1 b-1f, the paper of different denominations
The size of coin is identical；In the infrared external reflection image at the bank note back side, the pattern in the infrared external reflection image of each bank note is equal
Having disappearance, and the bank note of different denominations, in infrared external reflection image, position and the size of pattern disappearance are all different.At figure
In the back side infrared external reflection image of 1b-Fig. 1 f, intercepting line number is between 100 to 200, and the pixel that row number are between 110 to 430
The region that point is formed, and using the infrared external reflection image in described region as the infrared external reflection image of bank note back side characteristic area.Its
In, the infrared external reflection image of the bank note back side characteristic area of formation is as shown in Fig. 1 g-1k.In Fig. 1 g-1k, the paper of different denominations
In the infrared external reflection image of coin back side characteristic area, due to the disappearance of pattern, disappearance portion in the infrared external reflection image of characteristic area
The gray value with non-lack part is divided to differ greatly.
S120: described infrared external reflection image carries out rim detection, obtains edge detection results.
In the present embodiment, the edge of infrared external reflection image refers to the image significant part of regional area brightness flop, should
The gray scale section in region typically can be regarded as a step, both had to go to the toilet in the least buffer area drastic change from a gray value
To the gray value that another gray scale difference is bigger.As shown in Fig. 1 g-1k, the edge of infrared external reflection image be pattern lack part with
The border region of non-lack part.
In the present embodiment, optionally, described infrared external reflection image is carried out rim detection, obtains edge detection results,
Including: by canny operator, described infrared external reflection image is carried out rim detection, obtain the first marginal point set；Described
During one edge point set closes, gray value is more than the pixel of first threshold as true marginal point；If the gray scale of target pixel points
Value is between Second Threshold to first threshold and the gray value of at least one pixel adjacent with described target pixel points is more than
First threshold, using described target pixel points as true marginal point；Wherein, gray value is false edge less than the pixel of Second Threshold
Point；The second marginal point set is formed based on described true marginal point.In the present embodiment, first threshold and Second Threshold are according to many
Secondary test obtains.
Optionally, Second Threshold is less than first threshold.If the gray value of target pixel points at Second Threshold to the first threshold
The gray value of at least one pixel between value and adjacent with target pixel points is more than first threshold, target pixel points is made
Being true marginal point, wherein, the pixel adjacent with target pixel points includes the upside adjacent with target pixel points, downside, left side
Or the pixel on right side；Or upper left side, lower left side, upper right side or the lower right side adjacent with target pixel points can also be included
Pixel.
In the present embodiment, it is also possible to by other algorithm, infrared external reflection image is carried out rim detection, obtain first
Marginal point set.
S130: extract the main edge of at least two of described infrared external reflection image based on edge detection results.
In the present embodiment, optionally, at least two master of described infrared external reflection image is extracted based on edge detection results
Edge includes: by Hough line detection method, described second marginal point set is carried out straight-line detection, obtains at least two limits
Edge straight line；If the distance between two-end-point on object edge straight line is more than pre-set length threshold, by straight for described object edge
Line is as the main edge of described infrared external reflection image.
Concrete, the straight line formed in the second marginal point set is detected by true marginal point by Hough line detection method,
Generally, due to the non-lack part of pattern in the infrared external reflection image of specific region, the bank note back side there is also gray value difference
Bigger region, therefore, true marginal point in the second marginal point set the edge line formed exists a plurality of, and at least has two
Bar, during actual identification, the quantity of edge line is more than two.If between the two-end-point on a certain edge line away from
From more than pre-set length threshold, using this edge line as the main edge of the infrared external reflection image of bank note back side characteristic area.Its
In, pre-set length threshold is configured according to actual needs, it is possible to enable the main edge of formation distinguish pattern lack part with
Non-lack part.
In the present embodiment, it is also possible to by other line detection methods, the second marginal point set is carried out straight-line detection,
It is capable of detecting when the straight line that the second marginal point set is formed.
S140: the distance between quantity based on described main edge and described main edge, determines the face amount of described bank note.
In the present embodiment, the bank note of different face amounts, the distance between quantity and the main edge at main edge is different
's.The quantity at the main edge of bank note of 20 dollars is 2, the main limit of remaining 5 dollars, 10 dollars, 50 dollars and 100 dollar bills
The quantity of edge be the distance between 4, and main edge be different.5 whether are met beautiful according to the distance judged between main edge
Unit, 10 dollars, 50 dollars or the gauged distance of 100 dollars, be determined the face amount of bank note.
In the present embodiment, owing on bank note, the ink of printing is different, so the sensing that the ink on bank note is to infrared light
, there is pattern disappearance in the infrared external reflection image of the bank note back side characteristic area therefore formed, therefore pass through infrared external reflection in difference
Pattern disappearance in image can also distinguish the true and false of bank note.Concrete, when bank note is genuine note, infrared external reflection image exists
Pattern lacks, and when bank note is counterfeit money, there is not pattern disappearance in infrared external reflection image, or pattern disappearance has bright with genuine note
Aobvious difference.
The recognition methods of a kind of dollar bill face amount that the present embodiment provides, by obtaining the red of bank note back side characteristic area
External reflectance image, and extract the main edge to infrared external reflection image, the distance between quantity based on main edge and main edge
Determine the face amount of bank note, it is possible to quickly identify the face amount of bank note, and improve the accuracy identified.
Embodiment two
Fig. 2 a is the recognition methods flow chart of a kind of dollar bill face amount that the embodiment of the present invention two provides, in above-mentioned enforcement
On the basis of example, optionally, the distance between quantity based on described main edge and described main edge, determine the face of bank note
Value, including:
If the quantity at described main edge is 2, then judge that the face amount of bank note is 20 dollars；
If the quantity at described main edge is 4, determine the face amount of bank note based on the distance between described main edge.
Thus, the face amount of bank note is determined by the quantity at main edge and the spacing at main edge, it is possible to quickly identify paper
The face amount of coin.
Based on above-mentioned optimization, as shown in Figure 2 a, the technical scheme that the present embodiment provides is specific as follows:
S210: obtain the infrared external reflection image of bank note back side characteristic area.
S220: described infrared external reflection image carries out rim detection, obtains edge detection results.
S230: extract the main edge of at least two of described infrared external reflection image based on edge detection results.
S240: if the quantity at described main edge is 2, then judge that the face amount of bank note is 20 dollars.
S250: if the quantity at described main edge is 4, determine the face of bank note based on the distance between described main edge
Value.
In the present embodiment, Fig. 2 b is infrared to 5 dollar bill back side characteristic areas that the embodiment of the present invention two provides
Reflected image carries out the image after binaryzation；Fig. 2 c be the embodiment of the present invention two provide to 10 dollar bill back side characteristic areas
Infrared external reflection image carry out the image after binaryzation；Fig. 2 d is the special to the 20 dollar bill back sides of the embodiment of the present invention two offer
Levy the image after the infrared external reflection image in region carries out binaryzation；Fig. 2 e be the embodiment of the present invention two provide to 50 dollar bills
The infrared external reflection image of back side characteristic area carries out the image after binaryzation；Fig. 2 f be the embodiment of the present invention two provide to 100
The infrared external reflection image of dollar bill back side characteristic area carries out the image after binaryzation.Infrared external reflection image is being carried out two-value
During change, the gray value forming the pixel at main edge is set to 255, the gray value of other pixels is set to 0.As
Shown in Fig. 2 b-2f, having 2 main edges in the infrared external reflection image of 20 dollar bill back side characteristic areas, remaining bank note all has 4
The main edge of bar, and the spacing of adjacent major edge is different.
In the present embodiment, optionally, the described face amount determining bank note based on the distance between described main edge, including:
In described 4 main edges, if the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,15 ± 5 and 85 ± 5, sentence
The face amount of disconnected bank note is 5 dollars；If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,70 ± 5 and 85 ± 5,
The face amount judging bank note is 10 dollars；If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,115 ± 5 and 35
± 5, it is judged that the face amount of bank note is 50 dollars；If the number of the pixel at adjacent major edge interval is followed successively by 35 ± 5,20 ± 5
With 40 ± 5, it is judged that the face amount of bank note is 100 dollars.
Present embodiments provide the recognition methods of a kind of dollar bill face amount, by the quantity at main edge and main edge it
Spacing determines the face amount of bank note, it is possible to quickly identify the face amount of bank note.
Embodiment three
Fig. 3 is the identification apparatus structure block diagram of a kind of dollar bill face amount that the embodiment of the present invention three provides, described device
For performing the recognition methods of dollar bill face amount, as it is shown on figure 3, described device includes image collection module 310, testing result
Acquisition module 320, main edge extracting module 330 and face amount determine module 340.
Wherein, image collection module 310, for obtaining the infrared external reflection image of bank note back side characteristic area；
Testing result acquisition module 320, for described infrared external reflection image carries out rim detection, obtains rim detection knot
Really；
Main edge extracting module 330, for extracting at least two of described infrared external reflection image based on edge detection results
Main edge；
Face amount determines module 340, for the distance between quantity based on described main edge and described main edge, determines
The face amount of described bank note.
Further, described image collection module 310, specifically for:
Obtain bank note resolution be longitudinal 150DPI, the back side infrared external reflection image of horizontal 150DPI；
From the pixel matrix of described infrared external reflection image, intercepting line number is between 100 to 200, and row number arrive 110
The region that pixel between 430 is formed, and using red as bank note back side characteristic area of the infrared external reflection image in described region
External reflectance image；Wherein, in the back side infrared external reflection image of bank note, the number of pixels across point is 610, the back side of described bank note
In infrared external reflection image, the number of longitudinal pixel is 260.
Further, described testing result acquisition module 320, specifically for:
In described infrared image, gray value is more than the pixel of first threshold as marginal point；
If the gray value of target pixel points is between Second Threshold to first threshold and adjacent with described target pixel points
The gray value of at least one pixel more than first threshold, using described target pixel points as marginal point；Wherein, gray value is little
In the pixel of Second Threshold not as marginal point；
At least two edge lines are formed based on described marginal point.
Further, described main edge extracting module 330, specifically for:
By Hough straight-line detection method, described edge line is fitted, obtains at least two edge lines；
Length is more than the edge line of pre-set length threshold, as the main edge of described infrared external reflection image.
Further, described face amount determines module 340, specifically for: if the quantity at described main edge is 2, then sentence
The face amount of disconnected bank note is 2 dollars；
If the quantity at described main edge is 4, determine the face amount of bank note based on the distance between described main edge.
Further, the described face amount determining bank note based on the distance between described main edge, including:
In described 4 main edges,
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,15 ± 5 and 85 ± 5, it is judged that the face of bank note
Value is 5 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,70 ± 5 and 85 ± 5, it is judged that the face of bank note
Value is 10 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,115 ± 5 and 35 ± 5, it is judged that bank note
Face amount is 50 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 35 ± 5,20 ± 5 and 40 ± 5, it is judged that the face of bank note
Value is 100 dollars.
The identification device of a kind of dollar bill face amount that the embodiment of the present invention provides, by obtaining bank note back side characteristic area
Infrared external reflection image, and extract the main edge to infrared external reflection image, between quantity based on main edge and main edge
Distance determines the face amount of bank note, it is possible to quickly identifies the face amount of bank note, and improves the accuracy identified.
Note, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious change,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although by above example, the present invention is carried out
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other Equivalent embodiments more can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (12)
1. the recognition methods of a dollar bill face amount, it is characterised in that including:
Obtain the infrared external reflection image of bank note back side characteristic area；
Described infrared external reflection image is carried out rim detection, obtains edge detection results；
The main edge of at least two of described infrared external reflection image is extracted based on edge detection results；
Distance between quantity based on described main edge and described main edge, determines the face amount of described bank note.
The recognition methods of dollar bill face amount the most according to claim 1, it is characterised in that the described acquisition bank note back side is special
Levy the infrared external reflection image in region, including:
Obtain bank note resolution be longitudinal 150DPI, the back side infrared external reflection image of horizontal 150DPI；
From the pixel matrix of described infrared external reflection image intercept line number between 100 to 200, and row number 110 to 430 it
Between the region that formed of pixel, and using the infrared external reflection image in described region as the infrared external reflection of bank note back side characteristic area
Image；Wherein, in the back side infrared external reflection image of bank note, the number of pixels across point is 610, and the back side of described bank note is infrared instead
Penetrating the number of longitudinal pixel in image is 260.
The recognition methods of dollar bill face amount the most according to claim 2, it is characterised in that described to described infrared external reflection
Image carries out rim detection, obtains edge detection results and includes:
By canny operator, described infrared external reflection image is carried out rim detection, obtain the first marginal point set；
In described first marginal point set, gray value is more than the pixel of first threshold as true marginal point；
If the gray value of target pixel points between Second Threshold to first threshold and adjacent with described target pixel points extremely
The gray value of a few pixel is more than first threshold, using described target pixel points as true marginal point；Wherein, gray value is less than
The pixel of Second Threshold is false marginal point；
The second marginal point set is formed based on described true marginal point.
The recognition methods of dollar bill face amount the most according to claim 3, it is characterised in that described based on rim detection knot
Fruit extracts the main edge of at least two of described infrared external reflection image, including:
By Hough straight-line detection method, described second marginal point set is carried out straight-line detection, obtain at least two edge lines；
If the distance between two-end-point on object edge straight line is more than pre-set length threshold, described object edge straight line is made
Main edge for described infrared external reflection image.
The recognition methods of dollar bill face amount the most according to claim 2, it is characterised in that number based on described main edge
Distance between amount and described main edge, determines the face amount of bank note, including:
If the quantity at described main edge is 2, then judge that the face amount of bank note is 20 dollars；
If the quantity at described main edge is 4, determine the face amount of bank note based on the distance between described main edge.
The recognition methods of dollar bill face amount the most according to claim 5, it is characterised in that described based on described main edge
Between distance determine the face amount of bank note, including:
In described 4 main edges,
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,15 ± 5 and 85 ± 5, it is judged that the face amount of bank note is
5 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,70 ± 5 and 85 ± 5, it is judged that the face amount of bank note is
10 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,115 ± 5 and 35 ± 5, it is judged that the face amount of bank note
It it is 50 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 35 ± 5,20 ± 5 and 40 ± 5, it is judged that the face amount of bank note is
100 dollars.
7. the identification device of a dollar bill face amount, it is characterised in that including:
Image collection module, for obtaining the infrared external reflection image of bank note back side characteristic area；
Testing result acquisition module, for described infrared external reflection image carries out rim detection, obtains edge detection results；
Main edge extracting module, for extracting the main edge of at least two of described infrared external reflection image based on edge detection results；
Face amount determines module, for the distance between quantity based on described main edge and described main edge, determines described paper
The face amount of coin.
The identification device of dollar bill face amount the most according to claim 7, it is characterised in that described image collection module,
Specifically for:
Obtain bank note resolution be longitudinal 150DPI, the back side infrared external reflection image of horizontal 150DPI；
From the pixel matrix of described infrared external reflection image intercept line number between 100 to 200, and row number 110 to 430 it
Between the region that formed of pixel, and using the infrared external reflection image in described region as the infrared external reflection of bank note back side characteristic area
Image；Wherein, in the back side infrared external reflection image of bank note, the number of pixels across point is 610, and the back side of described bank note is infrared instead
Penetrating the number of longitudinal pixel in image is 260.
The identification device of dollar bill face amount the most according to claim 8, it is characterised in that described testing result obtains mould
Block, specifically for:
By canny operator, described infrared external reflection image is carried out rim detection, obtain the first marginal point set；
In described first marginal point set, gray value is more than the pixel of first threshold as true marginal point；
If the gray value of target pixel points between Second Threshold to first threshold and adjacent with described target pixel points extremely
The gray value of a few pixel is more than first threshold, using described target pixel points as true marginal point；Wherein, gray value is less than
The pixel of Second Threshold is false marginal point；
The second marginal point set is formed based on described true marginal point.
The identification device of dollar bill face amount the most according to claim 9, it is characterised in that described main edge extracting mould
Block, specifically for:
By Hough straight-line detection method, the second marginal point set is carried out straight-line detection, obtain at least two edge lines；
If the distance between two-end-point on object edge straight line is more than pre-set length threshold, described object edge straight line is made
Main edge for described infrared external reflection image.
The identification device of 11. dollar bill face amounts according to claim 8, it is characterised in that described face amount determines module,
Specifically for: if the quantity at described main edge is 2, then judge that the face amount of bank note is 20 dollars；
If the quantity at described main edge is 4, determine the face amount of bank note based on the distance between described main edge.
The identification device of 12. dollar bill face amounts according to claim 11, it is characterised in that described based on described main limit
Distance between edge determines that the face amount of bank note includes: in described 4 main edges,
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,15 ± 5 and 85 ± 5, it is judged that the face amount of bank note is
5 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,70 ± 5 and 85 ± 5, it is judged that the face amount of bank note is
10 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 30 ± 5,115 ± 5 and 35 ± 5, it is judged that the face amount of bank note
It it is 50 dollars；
If the number of the pixel at adjacent major edge interval is followed successively by 35 ± 5,20 ± 5 and 40 ± 5, it is judged that the face amount of bank note is
100 dollars.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610641324.2A CN106296975B (en) | 2016-08-05 | 2016-08-05 | method and device for identifying face value of dollar paper money |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610641324.2A CN106296975B (en) | 2016-08-05 | 2016-08-05 | method and device for identifying face value of dollar paper money |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106296975A true CN106296975A (en) | 2017-01-04 |
| CN106296975B CN106296975B (en) | 2019-12-10 |
Family
ID=57666066
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610641324.2A Expired - Fee Related CN106296975B (en) | 2016-08-05 | 2016-08-05 | method and device for identifying face value of dollar paper money |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106296975B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106846610A (en) * | 2017-01-20 | 2017-06-13 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note version and device |
| CN108335404A (en) * | 2018-02-07 | 2018-07-27 | 深圳怡化电脑股份有限公司 | Edge fitting method and money-checking equipment |
| 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 (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080069424A1 (en) * | 2006-09-20 | 2008-03-20 | Xu-Hua Liu | Method for characterizing texture of areas within an image corresponding to monetary banknotes |
| CN102750771A (en) * | 2012-07-13 | 2012-10-24 | 中山大学 | Method for identifying denominations of fifth series of renminbi applied in smart phone |
| CN103886309A (en) * | 2014-02-27 | 2014-06-25 | 华中科技大学 | Method for identifying dollar denominations through facial recognition |
| CN104346858A (en) * | 2014-10-10 | 2015-02-11 | 新达通科技股份有限公司 | Paper currency face value identification method and device based on magnetic image |
| CN104361674A (en) * | 2014-09-30 | 2015-02-18 | 浙江维融电子科技股份有限公司 | Paper money recognition method and device |
| US20150294523A1 (en) * | 2013-08-26 | 2015-10-15 | Vertifi Software, LLC | Document image capturing and processing |
| CN105303677A (en) * | 2015-10-29 | 2016-02-03 | 深圳怡化电脑股份有限公司 | Method and apparatus for obtaining boundary of banknote security thread |
-
2016
- 2016-08-05 CN CN201610641324.2A patent/CN106296975B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080069424A1 (en) * | 2006-09-20 | 2008-03-20 | Xu-Hua Liu | Method for characterizing texture of areas within an image corresponding to monetary banknotes |
| CN102750771A (en) * | 2012-07-13 | 2012-10-24 | 中山大学 | Method for identifying denominations of fifth series of renminbi applied in smart phone |
| US20150294523A1 (en) * | 2013-08-26 | 2015-10-15 | Vertifi Software, LLC | Document image capturing and processing |
| CN103886309A (en) * | 2014-02-27 | 2014-06-25 | 华中科技大学 | Method for identifying dollar denominations through facial recognition |
| CN104361674A (en) * | 2014-09-30 | 2015-02-18 | 浙江维融电子科技股份有限公司 | Paper money recognition method and device |
| CN104346858A (en) * | 2014-10-10 | 2015-02-11 | 新达通科技股份有限公司 | Paper currency face value identification method and device based on magnetic image |
| CN105303677A (en) * | 2015-10-29 | 2016-02-03 | 深圳怡化电脑股份有限公司 | Method and apparatus for obtaining boundary of banknote security thread |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106846610A (en) * | 2017-01-20 | 2017-06-13 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note version and device |
| CN106846610B (en) * | 2017-01-20 | 2019-04-26 | 深圳怡化电脑股份有限公司 | A kind of bank note version recognition methods and device |
| CN108335404A (en) * | 2018-02-07 | 2018-07-27 | 深圳怡化电脑股份有限公司 | Edge fitting method and money-checking equipment |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106296975B (en) | 2019-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104851184B (en) | A kind of recognition methods of horizontally-spliced bank note and device | |
| CN105957238A (en) | Banknote management method and system | |
| CN107610322B (en) | Banknote version identification method and device, electronic equipment and storage medium | |
| US20120045112A1 (en) | Method for a banknote detector device, and a banknote detector device | |
| 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 | |
| CN103279735A (en) | Dust stratification detection method and system for financial bill identification module | |
| CN104992494A (en) | Method and device for detecting authenticity of paper money | |
| CN102324132A (en) | Bank-note detecting method by identifying ultraviolet-light image and system | |
| CN104966349A (en) | ATM platform-based method of detecting new bank note and old bank note | |
| CN107134047B (en) | White watermark detection method and device | |
| CN106780966B (en) | A kind of paper money discrimination method and device | |
| CN106296975A (en) | The recognition methods of a kind of dollar bill face amount and device | |
| CN106683261B (en) | A kind of false distinguishing method and apparatus of bank note | |
| CN108806058A (en) | A kind of paper currency detecting method and device | |
| CN106447897A (en) | Method and apparatus for detecting magnetic characteristics of paper note | |
| CN108711213B (en) | Method and device for identifying black and white blocks of paper money zebra stripes | |
| CN106447908B (en) | Paper money counterfeit distinguishing method and device | |
| CN106600812A (en) | Paper currency recognition method and paper currency recognition device | |
| CN100555341C (en) | In image, determine verification method corresponding to the zone of financial ticket | |
| CN108510638B (en) | Paper money identification method and device | |
| CN111915792B (en) | Method and device for identifying zebra crossing image-text | |
| KR102273720B1 (en) | Bill discrimination apparatus | |
| CN108961530B (en) | Paper currency defect identification method and system | |
| CN106652168B (en) | Method and device for identifying currency value 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: 20191210 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |