CN106204616A - The recognition methods of a kind of Iran note denomination and device - Google Patents
The recognition methods of a kind of Iran note denomination and device Download PDFInfo
- Publication number
- CN106204616A CN106204616A CN201610578333.1A CN201610578333A CN106204616A CN 106204616 A CN106204616 A CN 106204616A CN 201610578333 A CN201610578333 A CN 201610578333A CN 106204616 A CN106204616 A CN 106204616A
- Authority
- CN
- China
- Prior art keywords
- pixel
- gray value
- face amount
- bank note
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/09—Recognition of logos
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
The embodiment of the invention discloses recognition methods and the device of a kind of Iran bank note face amount, wherein, the method includes: obtain the face amount difference area image of bank note；Described face amount difference area image is carried out binary conversion treatment, obtains binary image；The gray value sum of each pixel in setting regions is obtained from described binary image；The face amount of bank note described in gray value sum identification based on pixel each in described setting regions.The embodiment of the present invention can accurately identify the face amount of bank note by the image of the characteristic area of bank note, reduces and identifies difficulty.
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 Iran note denomination.
Background technology
In prior art, the bank note such as such as RMB, the banknote of different face amounts, it varies in size, and at bank note just
All there is obvious face amount digital information in face.Therefore, during the face amount identification to bank note, can be easier by bank note
The face amount of the digital information identification bank note in size or front.
During inventor performs the present invention, find prior art exists following defect: Iran's bank note is as outward
The one of which of coin, its different denominations bank note size zero difference, the face amount digital information of banknote only has the reverse side of banknote to have simultaneously
Obvious denomination numeral, front only has a part (offset printing is to printing word) for denomination numeral.The face of the bank note of this situation
Value cannot be directly identified by the size of bank note or the digital information in front, increases the difficulty of face amount identification.
Summary of the invention
In view of this, the embodiment of the present invention provides recognition methods and the device of a kind of Iran note denomination, it is possible to pass through paper
The image of the characteristic area of coin accurately identifies the face amount of bank note, reduces and identifies difficulty.
First aspect, embodiments provides the recognition methods of a kind of Iran bank note face amount, including:
Obtain the face amount difference area image of bank note；
Described face amount difference area image is carried out binary conversion treatment, obtains binary image；
The gray value sum of each pixel in setting regions is obtained from described binary image；
The face amount of bank note described in gray value sum identification based on pixel each in described setting regions.
Second aspect, the embodiment of the present invention additionally provides the identification device of a kind of Iran bank note face amount, including:
Image collection module, for obtaining the face amount difference area image of bank note；
Binary conversion treatment module, for described face amount difference area image is carried out binary conversion treatment, obtains binary picture
Picture；
Gray value sum acquisition module, for obtaining the gray scale of each pixel in setting regions from described binary image
Value sum；
Face amount identification module, for bank note described in gray value sum identification based on pixel each in described setting regions
Face amount.
The recognition methods of a kind of Iran bank note face amount that the embodiment of the present invention provides and device, by the face amount district to bank note
The binary conversion treatment of other area image, and by the gray value sum identification paper of each pixel of setting regions in binary image
The face amount of coin, it is possible to accurately identified the face amount of bank note by the image of the characteristic area of bank note, is reduced and identifies difficulty.
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 Iran bank note face amount that the embodiment of the present invention one provides；
Fig. 1 b is the banknote image that face amount is 50000 that the embodiment of the present invention one provides；
Fig. 1 c is the banknote image that face amount is 100000 that the embodiment of the present invention one provides；
Fig. 2 a is the recognition methods flow chart of a kind of Iran bank note face amount that the embodiment of the present invention two provides；
Fig. 2 b is the bank note binary image that face amount is 50000 that the embodiment of the present invention two provides；
Fig. 2 c is the bank note binary image that face amount is 100000 that the embodiment of the present invention two provides；
Fig. 3 is the identification apparatus structure block diagram of a kind of Iran bank note 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 be the embodiment of the present invention one provide a kind of Iran bank note face amount recognition methods flow chart, described method by
The identification device of Iran's bank note face amount performs, and described device is performed by software and/or hardware, and described device is generally disposed at
In the terminals such as computer.As shown in Figure 1a, the technical scheme that the present embodiment provides is specific as follows:
S110: obtain the face amount difference area image of bank note.
In the present embodiment, the face amount difference area image of described acquisition bank note includes: obtaining bank note is vertical in resolution
To 150DPI, the direct picture of horizontal 200DPI；From the pixel matrix of described direct picture intercept line number 20 to 105 it
Between and the region that formed of row pixel number between 45 to 230, and using the image in described region that intercepts as the face of bank note
Value difference area image.Wherein, the direct picture obtaining bank note can be taken pictures or the mode such as scanning to use.Horizontal stroke in direct picture
Being 1308 to the number of pixel, in the direct picture of bank note, the number of longitudinal pixel is 455, say, that bank note is just
The number of the pixel of face image is 1308 × 455.Therefore, in the pixel matrix of the direct picture of bank note line number at 1-1308
Between, row number are between 1-455.
Fig. 1 b is the banknote image that face amount is 50000 that the embodiment of the present invention one provides, and Fig. 1 c is the embodiment of the present invention one
The banknote image that face amount is 100000 provided, as shown in figs. lb and lc, the size phase of the image of the bank note of two different denominations
With.As shown in Figure 1 b, the face amount difference area image of bank note be the first rectangle frame 11 around the image in region.Such as Fig. 1 c institute
Show, the image that face amount difference area image is second 12 encircled area of rectangle frame of bank note.As shown in figs. lb and lc, in face amount
It is that in the bank note face amount difference area image of 50000 and 100000, at least one difference is: face amount is the paper of 50000
Coin face amount difference area image has " Fructus Persicae is heart-shaped " mark 13, and the bank note face amount difference area image that face amount is 100000 has
The mark 14 of " numeral 1 ".Wherein, in Fig. 1 b in the first rectangle frame 1 and Fig. 1 c the second rectangle frame 2 in the direct picture of bank note
Position is identical, and size is identical.
S120: described face amount difference area image is carried out binary conversion treatment, obtains binary image.
In the present embodiment, exemplary, described area image of distinguishing described face amount carries out binary conversion treatment, acquisition two
Value image includes: determine the first threshold of described face amount difference area image based on maximum variance between clusters；When described face amount
When in difference area image, the gray value of pixel is less than T1/k, described pixel gray value in binary image is arranged
It is 0；When in described face amount difference area image, the gray value of pixel is more than or equal to T1/k, by described pixel in binaryzation
Gray value in image is set to 1, and wherein, T1 is described first threshold, and k is coefficient.Optionally, k is 2, and the value of k can
To be other numerical value, it is configured as required.
In the present embodiment, maximum variance between clusters is determined to the method for first threshold of face amount difference area image such as
Under: according to the gamma characteristic of image, segmentation threshold divides the image into background and two parts of target, the class between background and target
Between variance the biggest, illustrate that the two-part difference of pie graph picture is the biggest.Wherein, the segmentation threshold of background and target is denoted as T, belongs to
Pixel number in target accounts for ratio the note w0, its average gray u0 of entire image；The pixel number belonging to background accounts for view picture figure
The ratio of picture is designated as w1, and its average gray is u1.The grand mean gray scale of image is designated as μ, and inter-class variance is designated as g；Then g=w0 (u0-
u)2+w1(u1-u)2, the whole face amount difference area image of traversal, i.e. choose different segmentation thresholds, and calculate inter-class variance.
When inter-class variance maximum, obtain corresponding segmentation threshold, be first threshold T1 of face amount difference area image.
On the basis of above-described embodiment, in image binaryzation processing procedure, it is also possible to according to comprising first threshold
The result that other formula calculate, is configured the gray value in binary image, to realize accurately identifying that the face amount of bank note is
Purpose.
S130: obtain the gray value sum of each pixel in setting regions from described binary image.
In the present embodiment, in binary image, setting regions can distinguish the face amount difference that face amount is 50000 bank note
" Fructus Persicae is heart-shaped " mark and " numeral 1 " mark in the face amount difference area image of the bank note that face amount is 100000 in area image.
Because " Fructus Persicae is heart-shaped " mark is different with the width that " numeral 1 " identifies, therefore can be by rationally selecting setting regions, it is simple to determine paper
The face amount of coin.
Optionally, " the Fructus Persicae heart during setting regions can be the face amount that face amount the is 50000 bank note difference region pre-set
Shape " region at mark place, or can also be a part for " Fructus Persicae heart-shaped " mark region.Setting regions is entered as required
For the purpose of row sets the face amount to realize distinguishing bank note.
S140: the face amount of bank note described in gray value sum identification based on pixel each in described setting regions.
In the present embodiment, exemplary, described based on the face amount of bank note described in described gray value sum identification, including:
If in described setting regions, the gray value sum of each pixel is less than Second Threshold, it is judged that the face amount of described bank note is 50000；
If in described setting regions, the gray value sum of each pixel is more than or equal to Second Threshold, it is judged that the face amount of described bank note is
100000.Wherein, Second Threshold obtains beforehand through test of many times, and can distinguish the face amount of bank note.
Present embodiments provide the recognition methods of a kind of Iran bank note face amount, by the face amount of bank note is distinguished area image
Binary conversion treatment, and by the face amount of the gray value sum identification bank note of each pixel of setting regions in binary image,
Can accurately be identified the face amount of bank note by the image of the characteristic area of bank note, reduce and identify difficulty.
Embodiment two
Fig. 2 a is the recognition methods flow chart of a kind of Iran bank note face amount that the embodiment of the present invention two provides, in above-mentioned enforcement
On the basis of example one, optionally, described from described binary image, each pixel gray value sum bag in setting regions is obtained
Include:
In described binary image, search described first floating frame by the first floating frame of setting height and covered
The region that in the region of lid, each pixel gray value sum is minimum；
When each pixel gray value sum minimum in the region that described first floating frame is covered, record described first
The line number of pixel matrix in the binary image that the coboundary of floating frame is corresponding, and described line number is recorded as strow；
In described binary image, and in the pixel region between line number is at strow+a to strow+b,
In search each pixel gray value in the region that covered of described second floating frame by setting the second floating frame of width
The region that sum is minimum；Wherein, b is more than a；
When the gray value sum minimum of each pixel in the region that described second floating frame is covered, record described
The row number of pixel matrix in the binary image that the left margin of two floating frames is corresponding, and described row number are recorded as stcol；
Determine the setting regions in binary image based on described line number and described row number, and calculate in described setting regions
The gray value sum of each pixel.
Thus, by the first floating frame can search first floating frame cover region in each pixel gray value it
With minimum region, and record the line number of pixel matrix in the binary image that the first floating frame coboundary is corresponding；Pass through
It is minimum that the line number of record and the second floating frame can search each pixel gray value sum in the second floating frame institute area of coverage
Region, and record the line number of pixel matrix in the binary image that the second floating frame left margin is corresponding, by record
Line number and row number can determine the setting regions in binary image.Setting regions is determined, it is possible to accurately by above-mentioned method
Identify bank note face amount.
Based on above-mentioned optimization, as shown in Figure 2 a, the technical scheme that the present embodiment provides is as follows:
S210: obtain the face amount difference area image of bank note.
S220: described face amount difference area image is carried out binary conversion treatment, obtains binary image.
S230: in described binary image, searches described first floating window by the first floating frame of setting height
The region that in the region that mouth is covered, each pixel gray value sum is minimum.
In the present embodiment, 12 pixel height sums during setting height is binary image；Wherein, the first floating window
Mouthful width can the most arbitrarily arrange, optionally, the first floating frame width for 90 pixel width sums, and
The left margin of the first floating frame covers the first row of the middle pixel matrix of binary image.Wherein, first floating frame
When being highly 12 pixel height sums in binary image, the height of the first floating frame is 50000 bank note less than face amount
Face amount difference region binary image in " Fructus Persicae heart-shaped " height of identifying, and again smaller than the face that face amount is 100000 bank note
The height that in the binary image in value difference region, " numeral 1 " identifies.When using the first floating frame to make a look up, Ke Yi
The position of the coboundary that the coboundary of the first floating frame covers binary image begins look for, the most successively by the first floating window
Mouth moves down the height of a pixel in binary image, and calculates successively in the region that the first floating frame is covered
Each pixel gray value sum, and find the district that in the region of the first floating frame covering, each pixel gray value sum is minimum
Territory.
Or, when using the first floating frame to make a look up, two-value can be covered in the coboundary of the first floating frame
The district that in the first floating frame institute overlay area, each pixel gray value sum is minimum is made a look up when changing the setting position of image
Territory.Setting position is to be determined by repeatedly identification test, it is possible to increase the efficiency of lookup.
S240: when each pixel gray value sum minimum in the region that described first floating frame is covered, records institute
State the line number of pixel matrix in the binary image that the coboundary of the first floating frame is corresponding, and described line number is recorded as
strow。
In the present embodiment, because binary image is the image that pixel matrix is formed, when the first floating frame is covered
Region in each pixel gray value sum minimum time, record the binary image that the coboundary of described first floating frame is corresponding
The line number of middle pixel matrix.If the face amount of bank note is 50000, when each pixel ash in the region that the first floating frame is covered
During angle value sum minimum, the coboundary of the first floating frame and " numeral 0 " phase in the binary image that face amount is 50000 bank note
Cut, as shown in Figure 2 b, when the face amount of bank note is 50000, in the binary image corresponding to the coboundary of the first floating frame
The position of pixel matrix row is the position at Fig. 2 b cathetus 21 place, and the line number that this row of recording this pixel matrix is corresponding
For strow.If the face amount of bank note is 100000, when pixel gray value sum each in the region that the first floating frame is covered
Hour, the coboundary of the first floating frame is tangent with " numeral 0 " in the binary image of the bank note that face amount is 100000.Such as figure
Shown in 2c, when the face amount of bank note is 100000, pixel square in the binary image corresponding to the coboundary of the first floating frame
The position that position is Fig. 2 c cathetus 22 place of battle array row, and line number corresponding to this row of recording this pixel matrix be strow.
Wherein, straight line 21 is identical with the straight line 22 position in binary image.
S250: in described binary image, and the pixel location between line number is at strow+a to strow+b
In territory, search each pixel gray scale in the region that described second floating frame is covered by setting the second floating frame of width
The region that value sum is minimum；Wherein, b is more than a.
In the present embodiment, a is 15, and b is 25；Set width as 40 pixel width in described binary image it
With.Wherein, the height of the second floating frame is configured as required.Optionally, in binary image, it may be determined that line number
Between strow+a to strow+b, and the region at the pixel place that row number are between 1-90.If the face amount of bank note is
50000, as shown in Figure 2 b, the 3rd rectangle frame 23 around region be line number between strow+a to strow+b, and row number
The region at the pixel place between 1-90.If the face amount of bank note is 100000, as shown in Figure 2 c, the 4th rectangle frame 24 is enclosed
Around region be line number between strow+a to strow+b, and the region at the pixel place that row are number between 1-90.Wherein,
3rd rectangle frame 23 and the 4th rectangle frame 24 size, and the position in binary image is identical.
In the present embodiment, optionally, the left margin of the second floating frame can be successively from the picture covering binary image
15th row of vegetarian refreshments matrix make a look up, to the 45th row, the region that each pixel gray value sum is minimum, so can improve lookup
Efficiency.Or when using the second floating frame to make a look up, the left margin of the second floating frame can cover binary image
Other row of pixel matrix, it is possible to the region that easy-to-look-up pixel gray value sum is minimum.
S260: when the gray value sum minimum of each pixel in the region that described second floating frame is covered, record
The row number of pixel matrix in the binary image that the left margin of described second floating frame is corresponding, and described row number are recorded as
stcol。
In the present embodiment, when the gray value sum minimum of pixel each in the region that the second floating frame is covered,
Record the row number of pixel matrix in the binary image that the left margin of the second floating frame is corresponding.If the face amount of bank note is
50000, when each pixel gray value sum minimum in the region that the second floating frame is covered, the left side of the second floating frame
Boundary identifies tangent with " Fructus Persicae is heart-shaped " in the binary image that face amount is 50000 bank note.As shown in Figure 2 b, when the face amount of bank note it is
When 50000, in the binary image corresponding to the second floating frame left margin, the position of pixel matrix row is figure cathetus 25
The position at place, and row number corresponding to these row of recording pixel matrix are stcol.If the face amount of bank note is 100000, when
In the region that two floating frames are covered during each pixel gray value sum minimum, the left margin of the second floating frame with face amount is
" numeral 1 " in the binary image of 50000 bank note identifies tangent.As shown in Figure 2 c, the left margin institute of the second floating frame is right
The position that position is Fig. 2 c cathetus 26 place of pixel matrix row in the binary image answered, and record pixel matrix
This row respective column number is stcol.
S270: determine the setting regions in binary image based on described line number and described row number, and calculate described setting
The gray value sum of each pixel in region.
In the present embodiment, exemplary, described determine setting in binary image based on described line number and described row number
Determine region, including: in described binary image, by line number between strow+m to strow+n, and row number arrive at stcol+p
The region that pixel between stcol+t is formed is as setting regions, and wherein, t is more than m more than p, n.Optionally, m is 20, and n is
28；P is 20, and t is 40.Wherein, p, t, m are relevant with the resolution of binary image with the value of n, when the resolution of binary image
When rate changes, p, t, m and n the most also can change.
When the face amount of bank note is 50000, as shown in Figure 2 b, setting regions be the 5th rectangle frame 27 around region.If
The face amount of bank note is 100000, as shown in Figure 2 b, setting regions be the 6th rectangle frame 28 around region.Such as 2b and Fig. 2 c institute
Showing, face amount is that the pixel number that gray value is 0 comprised in the setting regions of 50000 bank note is significantly greater than 100000 bank note
, the face amount of 50000 and 100000 bank note therefore can be distinguished by each pixel gray value sum in setting regions.
S280: the face amount of bank note described in gray value sum identification based on pixel each in described setting regions.
Present embodiments provide the recognition methods of a kind of Iran coin face amount, first can be searched by the first floating frame and float
The region that in the region that dynamic window covers, each pixel gray value sum is minimum, and it is corresponding to record the first floating frame coboundary
The line number of pixel matrix in binary image；Line number and the second floating frame by record can search the second floating frame
The region that in institute's area of coverage, each pixel gray value sum is minimum, and record the binary picture that the second floating frame left margin is corresponding
The line number of pixel matrix in Xiang, line number and row number by record can determine the setting regions in binary image.Pass through
Above-mentioned method determines setting regions, it is possible to the accurate face amount identifying bank note.
Embodiment three
Fig. 3 is the identification apparatus structure block diagram of a kind of Iran bank note face amount that the embodiment of the present invention three provides, described device
For performing the recognition methods of Iran's bank note face amount, as it is shown on figure 3, described device includes at image collection module 310, binaryzation
Reason module 320, gray value sum acquisition module 330 and face amount identification module 340.
Wherein, image collection module 310, for obtaining the face amount difference area image of bank note；
Binary conversion treatment module 320, for described face amount difference area image is carried out binary conversion treatment, obtains binaryzation
Image；
Gray value sum acquisition module 330, for obtaining each pixel in setting regions from described binary image
Gray value sum；
Face amount identification module 340, for paper described in gray value sum identification based on pixel each in described setting regions
The face amount of coin.
Further, described image collection module 310, specifically for: obtaining bank note in resolution is longitudinal 150DPI, horizontal stroke
To the direct picture of 200DPI；
Between 20 to 105 and row number are between 45 to 230 to intercept line number from the pixel matrix of described direct picture
Pixel formed region, and using intercept described region image as bank note face amount distinguish area image；Wherein, institute
Stating the number of pixels across point in the direct picture of bank note is 1308, the number of longitudinal pixel in the direct picture of described bank note
It is 455；
Binary conversion treatment module 320, specifically for: determine that described face amount distinguishes area image based on maximum variance between clusters
First threshold；
When in described face amount difference area image, the gray value of pixel is less than T1/k, by described pixel in binaryzation
Gray value in image is set to 0；
When in described face amount difference area image, the gray value of pixel is more than or equal to T1/k, by described pixel two
Gray value in value image is set to 1, and wherein, T1 is described first threshold, and k is coefficient.
Further, described gray value sum acquisition module, specifically for: in described binary image, by setting
First floating frame of height searches each pixel gray value sum minimum in the region that described first floating frame is covered
Region；
When each pixel gray value sum minimum in the region that described first floating frame is covered, record described first
The line number of pixel matrix in the binary image that the coboundary of floating frame is corresponding, and described line number is recorded as strow；
In described binary image, and in the pixel region between line number is at strow+a to strow+b,
By set the second floating frame of width search in the region that covered of described second floating frame each pixel gray value it
With minimum region；Wherein, b is more than a；
When the gray value sum minimum of each pixel in the region that described second floating frame is covered, record described
The row number of pixel matrix in the binary image that the left margin of two floating frames is corresponding, and described row number are recorded as stcol；
Determine the setting regions in binary image based on described line number and described row number, and calculate in described setting regions
The gray value sum of each pixel.
Further, 12 pixel height sums during setting height is described binary image；A is 15, and b is 25；If
Fixed width degree is 40 pixel width sums in described binary image.
Further, in described binary image, by line number between strow+m to strow+n, and row number exist
The region that pixel between stcol+p to stcol+t is formed is as setting regions, and wherein, t is more than m more than p, n.
Further, described face amount identification module 340 specifically for:
If in described setting regions, the gray value sum of each pixel is less than Second Threshold, it is judged that the face amount of described bank note
It is 50000；
If in described setting regions, the gray value sum of each pixel is more than or equal to Second Threshold, it is judged that described bank note
Face amount be 100000.
The identification device of a kind of Iran bank note face amount that the embodiment of the present invention provides, by distinguishing region to the face amount of bank note
The binary conversion treatment of image, and by the face of the gray value sum identification bank note of each pixel of setting regions in binary image
Value, it is possible to accurately identified the face amount of bank note by the image of the characteristic area of bank note, is reduced and identifies difficulty.
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 (11)
1. the recognition methods of an Iranian bank note face amount, it is characterised in that including:
Obtain the face amount difference area image of bank note；
Described face amount difference area image is carried out binary conversion treatment, obtains binary image；
The gray value sum of each pixel in setting regions is obtained from described binary image；
The face amount of bank note described in gray value sum identification based on pixel each in described setting regions.
Method the most according to claim 1, it is characterised in that
The face amount difference area image of described acquisition bank note includes:
Obtain bank note resolution be longitudinal 150DPI, the direct picture of horizontal 200DPI；
The picture that line number is between 20 to 105 and row number are between 45 to 230 is intercepted from the pixel matrix of described direct picture
Vegetarian refreshments formed region, and using intercept described region image as bank note face amount distinguish area image；Wherein, described paper
In the direct picture of coin, the number of pixels across point is 1308, and in the direct picture of described bank note, the number of longitudinal pixel is
455；
Described area image of distinguishing described face amount carries out binary conversion treatment, and acquisition binary image includes:
The first threshold of described face amount difference area image is determined based on maximum variance between clusters；
When in described face amount difference area image, the gray value of pixel is less than T1/k, by described pixel at binary image
In gray value be set to 0；
When in described face amount difference area image, the gray value of pixel is more than or equal to T1/k, by described pixel in binaryzation
Gray value in image is set to 1, and wherein, T1 is described first threshold, and k is coefficient.
Method the most according to claim 2, it is characterised in that described obtain in setting regions from described binary image
Each pixel gray value sum includes:
In described binary image, search what described first floating frame was covered by the first floating frame of setting height
The region that in region, each pixel gray value sum is minimum；
When each pixel gray value sum minimum in the region that described first floating frame is covered, record described first and float
The line number of pixel matrix in the binary image that the coboundary of window is corresponding, and described line number is recorded as strow；
In described binary image, and in the pixel region between line number is at strow+a to strow+b, pass through
Set the second floating frame of width and search in the region that covered of described second floating frame each pixel gray value sum
Little region；Wherein, b is more than a；
When the gray value sum minimum of each pixel in the region that described second floating frame is covered, record described second and float
The row number of pixel matrix in the binary image that the left margin of dynamic window is corresponding, and described row number are recorded as stcol；
Determine the setting regions in binary image based on described line number and described row number, and calculate in described setting regions each
The gray value sum of pixel.
Method the most according to claim 3, it is characterised in that setting height is 12 pixels in described binary image
Highly sum；A is 15, and b is 25；Set width as 40 pixel width sums in described binary image.
Method the most according to claim 3, it is characterised in that described determine binaryzation based on described line number and described row number
Setting regions in image, including:
In described binary image, by line number between strow+m to strow+n, and row number are at stcol+p to stcol+t
Between the region that formed of pixel as setting regions, wherein, t more than p, n more than m.
Method the most according to claim 5, it is characterised in that m is 20, n is 28；P is 20, and t is 40.
Method the most according to claim 2, it is characterised in that described based on bank note described in described gray value sum identification
Face amount, including:
If in described setting regions, the gray value sum of each pixel is less than Second Threshold, it is judged that the face amount of described bank note is
50000；
If in described setting regions, the gray value sum of each pixel is more than or equal to Second Threshold, it is judged that the face of described bank note
Value is 100000.
8. the identification device of an Iranian bank note face amount, it is characterised in that including:
Image collection module, for obtaining the face amount difference area image of bank note；
Binary conversion treatment module, for described face amount difference area image is carried out binary conversion treatment, obtains binary image；
Gray value sum acquisition module, for obtain from described binary image in setting regions the gray value of each pixel it
With；
Face amount identification module, for the face of bank note described in gray value sum identification based on pixel each in described setting regions
Value.
Device the most according to claim 8, it is characterised in that
Described image collection module, specifically for: obtain bank note resolution be longitudinal 150DPI, the front elevation of horizontal 200DPI
Picture；
The picture that line number is between 20 to 105 and row number are between 45 to 230 is intercepted from the pixel matrix of described direct picture
Vegetarian refreshments formed region, and using intercept described region image as bank note face amount distinguish area image；Wherein, described paper
In the direct picture of coin, the number of pixels across point is 1308, and in the direct picture of described bank note, the number of longitudinal pixel is
455；
Described binary conversion treatment module, specifically for: determine described face amount difference area image based on maximum variance between clusters
First threshold；
When in described face amount difference area image, the gray value of pixel is less than T1/k, by described pixel at binary image
In gray value be set to 0；
When in described face amount difference area image, the gray value of pixel is more than or equal to T1/k, by described pixel in binaryzation
Gray value in image is set to 1, and wherein, T1 is described first threshold, and k is coefficient.
Device the most according to claim 9, it is characterised in that
Described gray value sum acquisition module, specifically for:
In described binary image, search what described first floating frame was covered by the first floating frame of setting height
The region that in region, each pixel gray value sum is minimum；
When each pixel gray value sum minimum in the region that described first floating frame is covered, record described first and float
The line number of pixel matrix in the binary image that the coboundary of window is corresponding, and described line number is recorded as strow；
In described binary image, and in the pixel region between line number is at strow+a to strow+b, pass through
Set the second floating frame of width and search in the region that covered of described second floating frame each pixel gray value sum
Little region；Wherein, b is more than a；
When the gray value sum minimum of each pixel in the region that described second floating frame is covered, record described second and float
The row number of pixel matrix in the binary image that the left margin of dynamic window is corresponding, and described row number are recorded as stcol；
Determine the setting regions in binary image based on described line number and described row number, and calculate in described setting regions each
The gray value sum of pixel.
11. devices according to claim 9, it is characterised in that described face amount identification module specifically for:
If in described setting regions, the gray value sum of each pixel is less than Second Threshold, it is judged that the face amount of described bank note is
50000；
If in described setting regions, the gray value sum of each pixel is more than or equal to Second Threshold, it is judged that the face of described bank note
Value is 100000.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610578333.1A CN106204616B (en) | 2016-07-21 | 2016-07-21 | Method and device for identifying currency value of Iran paper money |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610578333.1A CN106204616B (en) | 2016-07-21 | 2016-07-21 | Method and device for identifying currency value of Iran paper money |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106204616A true CN106204616A (en) | 2016-12-07 |
| CN106204616B CN106204616B (en) | 2020-07-24 |
Family
ID=57492069
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610578333.1A Expired - Fee Related CN106204616B (en) | 2016-07-21 | 2016-07-21 | Method and device for identifying currency value of Iran paper money |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106204616B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106652168A (en) * | 2016-12-19 | 2017-05-10 | 深圳怡化电脑股份有限公司 | Paper currency value identification method and paper currency value identification device |
| 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 |
| CN107481389A (en) * | 2017-08-03 | 2017-12-15 | 恒银金融科技股份有限公司 | Banknote serial number area image binarization processing method |
| 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 (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1994003997A1 (en) * | 1992-08-03 | 1994-02-17 | Ricoh Company, Ltd. | Document identifier which can also identify special ticket, image forming apparatus using the identifier, image processor, and copying machine |
| CN102779275A (en) * | 2012-07-04 | 2012-11-14 | 广州广电运通金融电子股份有限公司 | Paper characteristic identification method and relative device |
| CN105139510A (en) * | 2015-08-25 | 2015-12-09 | 深圳怡化电脑股份有限公司 | Bank note identification method and system |
| CN105184290A (en) * | 2015-08-25 | 2015-12-23 | 深圳怡化电脑股份有限公司 | Target region extraction method and system |
| CN105243730A (en) * | 2015-10-28 | 2016-01-13 | 深圳怡化电脑股份有限公司 | Banknote identification method and system |
| CN105303676A (en) * | 2015-10-27 | 2016-02-03 | 深圳怡化电脑股份有限公司 | Banknote version identification method and banknote version identification system |
-
2016
- 2016-07-21 CN CN201610578333.1A patent/CN106204616B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1994003997A1 (en) * | 1992-08-03 | 1994-02-17 | Ricoh Company, Ltd. | Document identifier which can also identify special ticket, image forming apparatus using the identifier, image processor, and copying machine |
| CN102779275A (en) * | 2012-07-04 | 2012-11-14 | 广州广电运通金融电子股份有限公司 | Paper characteristic identification method and relative device |
| CN105139510A (en) * | 2015-08-25 | 2015-12-09 | 深圳怡化电脑股份有限公司 | Bank note identification method and system |
| CN105184290A (en) * | 2015-08-25 | 2015-12-23 | 深圳怡化电脑股份有限公司 | Target region extraction method and system |
| CN105303676A (en) * | 2015-10-27 | 2016-02-03 | 深圳怡化电脑股份有限公司 | Banknote version identification method and banknote version identification system |
| CN105243730A (en) * | 2015-10-28 | 2016-01-13 | 深圳怡化电脑股份有限公司 | Banknote identification method and system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106652168A (en) * | 2016-12-19 | 2017-05-10 | 深圳怡化电脑股份有限公司 | Paper currency value identification method and paper currency value identification device |
| CN106652168B (en) * | 2016-12-19 | 2020-07-21 | 深圳怡化电脑股份有限公司 | Method and device for identifying currency value of paper money |
| 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 |
| CN107481389A (en) * | 2017-08-03 | 2017-12-15 | 恒银金融科技股份有限公司 | Banknote serial number area image binarization processing method |
| CN107481389B (en) * | 2017-08-03 | 2019-06-07 | 恒银金融科技股份有限公司 | Banknote serial number area image binarization processing method |
| 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 |
|---|---|
| CN106204616B (en) | 2020-07-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106056751B (en) | The recognition methods and system of serial number | |
| US10430681B2 (en) | Character segmentation and recognition method | |
| CN103488984B (en) | Method and device for identifying second-generation identity cards based on intelligent mobile equipment | |
| CN106530310B (en) | A kind of pedestrian count method and device based on the identification of human body overhead | |
| JP4772839B2 (en) | Image identification method and imaging apparatus | |
| CN104091388B (en) | A kind of paper money discrimination method based on magnetic image and device | |
| US9324001B2 (en) | Character recognition device and character segmentation method | |
| US10410084B2 (en) | Devices, systems, and methods for anomaly detection | |
| CN106204616A (en) | The recognition methods of a kind of Iran note denomination and device | |
| Khanna et al. | Scanner identification using feature-based processing and analysis | |
| CN101834986B (en) | Imaging apparatus, mobile body detecting method, mobile body detecting circuit and program | |
| CN104809452A (en) | Fingerprint identification method | |
| CN101460937A (en) | Model- based dewarping method and apparatus | |
| CN105989659B (en) | A kind of similar character recognition methods and paper money code recognition methods | |
| CN109034050A (en) | ID Card Image text recognition method and device based on deep learning | |
| CN104077577A (en) | Trademark detection method based on convolutional neural network | |
| EP1081648B1 (en) | Method for processing a digital image | |
| CN105913040A (en) | Real time double cameras provided pedestrian detection system for use under scotopic vision conditions | |
| TW200818861A (en) | Color scanning to enhance bitonal image | |
| CN101520852A (en) | Vanishing point detecting device and detecting method | |
| CN104966107A (en) | Credit card card-number identification method based on machine learning | |
| CN103888682B (en) | Image processing equipment and image processing method | |
| CN106203397B (en) | Form based on tabular analysis technology in image differentiates and localization method | |
| CN103093185B (en) | Character recognition device, image processing apparatus and method thereof | |
| CN110598566A (en) | Image processing method, device, terminal and computer readable storage medium |
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: 20200724 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |