CN108460775A - A kind of forge or true or paper money recognition methods and device - Google Patents
A kind of forge or true or paper money recognition methods and device Download PDFInfo
- Publication number
- CN108460775A CN108460775A CN201710086364.XA CN201710086364A CN108460775A CN 108460775 A CN108460775 A CN 108460775A CN 201710086364 A CN201710086364 A CN 201710086364A CN 108460775 A CN108460775 A CN 108460775A
- Authority
- CN
- China
- Prior art keywords
- boundary
- information
- true
- characteristic area
- bank note
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
An embodiment of the present invention provides a kind of forge or true or paper money recognition methods and device, this method to include:The characteristic area for including denomination number is cut in the bank note gray level image that infrared light scanning obtains;Determine the boundary information of the included denomination number characteristic area Nei;According to the boundary information, the projection information of the characteristic area is obtained;According to the projection information, the true and false of the bank note is determined.The embodiment of the present invention by determining that boundary information accurately can carry out feature extraction to characteristic area, and then determines the true and false of bank note according to the projection information of boundary information, greatly improves the accuracy of forge or true or paper money identification by using above-mentioned technical proposal.
Description
Technical field
The present embodiments relate to technical field of information processing more particularly to a kind of forge or true or paper money recognition methods and devices.
Background technology
With the development of economy, the circulation of bank note is increasing, and many industries all occur being based on paper money recognition technology
Intelligent unmanned charge system.For example, paper money recognition technology can not only be applied in automatic vending ticketing, can also apply
To bank automatic teller machine or business hall the automatic systems such as machine of paying dues in.Meanwhile the invention of paper money counter is also each row
Industry provides a convenient, and the application of paper money identifier saves a large amount of human resources, greatly improves working efficiency.
Counterfeit money includes the currency forged, and refers to copying genuine note pattern, shape, color etc., the vacation made of various means
Coin inevitably will appear the case where meeting with counterfeit money in daily life, and it is more and more brilliant to forge means,
Very big puzzlement is caused to people’s lives, therefore the truth identification of bank note is of great significance.The process of the identification note true and false is logical
Include often:The current banknote image of a frame is acquired, and the pretreatments such as data extraction, edge enhancing, filtering are carried out to image, and is carried out
Subsequent image detect and genuine/counterfeit discriminating, wherein image detection and differentiation include Image Edge-Detection, feature extraction etc..It is existing
The method of forge or true or paper money recognition methods generally use binaryzation handles the image information of bank note, and then determines the true of bank note
Puppet, such as common OTSU algorithms, which divides the image into foreground and background two parts using threshold value, when variance is most between two parts
When big, then two parts difference for constituting image is bigger, and binary conversion treatment effect is better, but when target image and background gray scale difference
When other unobvious, it is possible that large area black region, or even the information of entire image is lost, seriously affect forge or true or paper money knowledge
Other accuracy.
Invention content
In view of this, a kind of forge or true or paper money recognition methods of offer of the embodiment of the present invention and device, true to solve existing bank note
The technological deficiency of pseudo- recognition methods accuracy difference.
In a first aspect, an embodiment of the present invention provides a kind of forge or true or paper money recognition methods, including:
The characteristic area for including denomination number is cut in the bank note gray level image that infrared light scanning obtains;
Determine the boundary information of the included denomination number characteristic area Nei;
According to the boundary information, the projection information of the characteristic area is obtained;
According to the projection information, the true and false of the bank note is determined.
Second aspect, an embodiment of the present invention provides a kind of forge or true or paper money identification devices, including:
Characteristic area determining module, for being cut in the bank note gray level image that infrared light scanning obtains comprising denomination number
Characteristic area;
Boundary information determining module, the boundary information for determining included denomination number in the characteristic area;
Projection information acquisition module, for according to the boundary information, obtaining the projection information of the characteristic area;
Truth identification module, for according to the projection information, determining the true and false of the bank note.
Technical solution provided in an embodiment of the present invention includes by being cut in the bank note gray level image that is obtained under infrared light
The characteristic area of denomination number, and determine the boundary information of characteristic area inner face specified number word, it is obtained accordingly according to boundary information
Projection information, and then determine the true and false of bank note.The embodiment of the present invention is by using above-mentioned technical proposal, by determining boundary information
Can feature extraction accurately be carried out to characteristic area, and then determine the true and false of bank note according to the projection information of boundary information, greatly
The big accuracy for improving forge or true or paper money identification.
Description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, certainly, the attached drawing in being described below is only some embodiments of the present invention, general for this field
For logical technical staff, without creative efforts, these attached drawings can also be modified and be replaced.
Fig. 1 a are a kind of flow diagram for forge or true or paper money recognition methods that the embodiment of the present invention one provides;
Fig. 1 b are the infrared external reflection image schematic diagram for the Thai Baht that the face amount that the embodiment of the present invention one provides is 1000;
Fig. 1 c be the embodiment of the present invention one provide cut after obtained characteristic area schematic diagram;
Fig. 2 is a kind of flow diagram of forge or true or paper money recognition methods provided by Embodiment 2 of the present invention;
Fig. 3 a are a kind of flow diagram for forge or true or paper money recognition methods that the embodiment of the present invention three provides;
Fig. 3 b are the boundary image schematic diagram that the embodiment of the present invention three provides;
Fig. 3 c are the first projection information schematic diagram that the embodiment of the present invention three provides;
Fig. 3 d are the second projection information schematic diagram that the embodiment of the present invention three provides;
Fig. 4 is a kind of flow diagram for forge or true or paper money recognition methods that the embodiment of the present invention four provides;
Fig. 5 is a kind of structural schematic diagram for forge or true or paper money identification device that the embodiment of the present invention five provides;
Fig. 6 is a kind of hardware architecture diagram for equipment that the embodiment of the present invention six provides.
Specific implementation mode
The present invention is described in further detail with reference to the accompanying drawings and examples.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
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
It should be mentioned that some exemplary embodiments are described as before exemplary embodiment is discussed in greater detail
The processing described as flow chart or method.Although each step is described as the processing of sequence, many of which by flow chart
Step can be implemented concurrently, concomitantly or simultaneously.In addition, the sequence of each step can be rearranged.When its operation
The processing can be terminated when completion, it is also possible to the additional step being not included in attached drawing.The processing can be with
Corresponding to method, function, regulation, subroutine, subprogram etc..
Embodiment one
Fig. 1 a are a kind of flow diagram for forge or true or paper money recognition methods that the embodiment of the present invention one provides, and this method is applicable in
It in forge or true or paper money identifies the case where, can be executed by forge or true or paper money identification device, wherein the device can be real by software and/or hardware
It is existing, it can generally be integrated in the equipment with cash examining function.As shown in Figure 1a, this method may include:
Step 101 cuts the characteristic area for including denomination number in the bank note gray level image that infrared light scanning obtains.
Illustratively, forge or true or paper money recognition methods provided in this embodiment is suitable for bank note, is particularly suitable for Thai Baht, infrared
It can be infrared external reflection image to scan obtained bank note gray level image, and Fig. 1 b are that the face amount that the embodiment of the present invention one provides is 1000
Thai Baht infrared external reflection image schematic diagram, image resolution ratio 100DPI*100DPI, the bank note shown in Fig. 1 b towards and court
In the case of, upper right corner denomination number is presented the lower half portion of " 1000 " printed words under infrared external reflection light, label in Fig. 1 b
Region shown in rectangle frame for 1 is the above-mentioned characteristic area for including denomination number, will in whole gray level image of bank note
This feature region cuts out, Fig. 1 c be the embodiment of the present invention one provide cut after obtained characteristic area schematic diagram.
Step 102, the boundary information for determining the included denomination number characteristic area Nei.
Illustratively, Boundary Recognition is carried out to the denomination number for being included in characteristic area, determines the side of denomination number
Boundary's information.
Step 103, according to the boundary information, obtain the projection information of the characteristic area.
Illustratively, image is projected usually to refer to and calculates image pixel gray value in one direction
With for example, projected in the horizontal direction to image, then calculate the image upper each included pixel of pixel column in the horizontal direction
The sum of gray value;The pixel gray value that being projected to image can also refer to image in a direction meets setting item
The pixel number of part is counted.According to obtained boundary information, the image of characteristic area is projected along preset direction
Obtain projection information.
Step 104, according to the projection information, determine the true and false of the bank note.
Illustratively, the boundary number of included denomination number and side in characteristic area can be determined according to projection information
The information such as boundary position, and then determine the true and false of bank note.
Technical solution provided in this embodiment, by being cut comprising denomination in the bank note gray level image that is obtained under infrared light
The characteristic area of number, and determine the boundary information of characteristic area inner face specified number word, it is projected accordingly according to boundary information
Information, and then determine the true and false of bank note.It is capable of the boundary information of the included denomination number in identification feature region, by determining boundary
Information accurately can carry out feature extraction to characteristic area, and then determine the true of bank note according to the projection information of boundary information
Puppet greatly improves the accuracy of forge or true or paper money identification.
Embodiment two
Fig. 2 is a kind of flow diagram of forge or true or paper money recognition methods provided by Embodiment 2 of the present invention, and the present embodiment exists
On the basis of above-described embodiment one, " boundary information for determining the included denomination number characteristic area Nei " is optimized,
As shown in Fig. 2, this method may include:
Step 201 cuts the characteristic area for including denomination number in the bank note gray level image that infrared light scanning obtains.
Step 202, according to wavelet modulus maxima algorithm and the second predetermined threshold value, determine and wrapped in the characteristic area
The boundary information of the number containing denomination.
Illustratively, gray matrix refers to the matrix for storing each pixel gray value in image.To as shown in Figure 1 b
Image, build corresponding with the pixel in characteristic area gray matrix and exist according to each pixel in the gray matrix
Pixel column position and pixel column position in image store the gray value of the pixel, then each pixel can be by the pixel
Position (x, y) in gray matrix identifies, wherein x indicates the pixel column position of the pixel, namely in gray matrix
Line position set, y indicates the pixel column position of the pixel, namely the column position in gray matrix.To each in gray matrix
Pixel at position determines whether the pixel belongs to according to wavelet modulus maxima algorithm and the second predetermined threshold value
The pixel in denomination digital boundary is stated, and searches all pixels point in denomination digital boundary, obtains the boundary of denomination number
Information.
Specifically, according to wavelet modulus maxima algorithm, determine whether a certain pixel belongs to above-mentioned denomination number side
Pixel in boundary includes the following steps:
Step A, derivation is carried out to Gaussian function, determines wavelet function.
Specifically, formula (1) is required Gaussian function, a certain scale is given to publicity (1), i.e., assignment is carried out to σ, such as
σ=2 in formula (1) find out the derivative of formula (1) along x and in the y-direction respectively, obtain shown in formula (2) and formula (3)
Two functions are wavelet function.
Step B, using wavelet function to any pixel point (x, y) on image, calculate the pixel gradient direction and
Wavelet transformation mode coefficient.
Specifically, the gray matrix of feature regional images is rolled up with wavelet function formula (2) and formula (3) respectively
Product, the first derivative after obtaining smoothlyWithAccording toWith
Calculate the gradient direction A of pixel (x, y)iF (x, y) (also referred to as argument), as shown in formula (4), and calculates the pixel
Wavelet transformation mode coefficient WiF, as shown in formula (5).
It should be noted that due to the x expressions pixel column in gray matrix, y indicates pixel column, according to formula (4)
The form of the argument calculation formula provided in the present embodiment isThe argument thus acquired is the angle with y-axis direction.
Step C, compare the wavelet transformation mode coefficient on the pixel eight neighborhood inside gradient direction, whether judge the pixel
Meet local model maximum value.
Typically, when being compared 8 neighborhood wavelet transformation mode coefficient, the argument that will be acquired in step B is divided into four kinds of sides
To:The first is 0 degree or 180 degree direction, i.e. horizontal direction, and second is 90 degree or 270 degree of directions, i.e. vertical direction, third
Kind is 45 degree or 225 degree of directions, i.e., positive diagonal, the 4th kind 135 degree or 315 degree of directions, i.e., negative diagonal.
Specifically, in the wavelet transformation mode coefficient on more a certain pixel eight neighborhood inside gradient direction, first judging should
The corresponding argument of pixel and any direction in above-mentioned four kinds of directions are closest, when different directions, the pixel of required comparison
Point is also different, and there are following four kinds of comparable situations:
Situation one, whenOrWhen
Compare the wavelet transformation mode coefficient of (x-1, y), (x, y) and (x+1, y) three position corresponding pixel points, that is, incite somebody to action (x,
Y) the wavelet transformation mode coefficient of pixel is compared at each a line up and down for wavelet transformation mode coefficient and the position translation, if
(x, y) corresponding wavelet transformation mode coefficient is maximum, then (x, y) corresponding pixel meets local model maximum value condition, and record should
The wavelet transformation mode coefficient of pixel.
Situation two, whenOrWhen
Compare (x, y-1), (x, y) and (x, y+1) these three position corresponding pixel points wavelet transformation mode coefficient, i.e., will
The wavelet transformation mode coefficient of pixel is compared at each row of the wavelet transformation mode coefficient of (x, y) and the position translation or so
Compared with if (x, y) corresponding wavelet transformation mode coefficient is maximum, (x, y) corresponding pixel meets local model maximum value condition, remembers
Record the wavelet transformation mode coefficient of the pixel.
Situation three, whenOrWhen
Compare (x-1, y-1), (x, y) and (x+1, y+1) these three position corresponding pixel points wavelet transformation mode coefficient, if
(x, y) corresponding wavelet transformation mode coefficient is maximum, then (x, y) corresponding pixel meets local model maximum value condition, and record should
The wavelet transformation mode coefficient of pixel.
Situation four, whenOrWhen
Compare (x+1, y-1), (x, y) and (x-1, y+1) these three position corresponding pixel points wavelet transformation mode coefficient, if
(x, y) corresponding wavelet transformation mode coefficient is maximum, then (x, y) corresponding pixel meets local model maximum value condition, and record should
The wavelet transformation mode coefficient of pixel.
If step D, pixel meets local model maximum value, further judge that the wavelet transformation mode coefficient of the pixel is
It is no to reach third predetermined threshold value, if so, determining that the pixel is the pixel in above-mentioned denomination digital boundary.
Specifically, according to the maximum value recorded in obtained wavelet transformation mode coefficient, to the WAVELET TRANSFORM MODULUS of all records
Coefficient is normalized, and third predetermined threshold value can be 0.25, if the small echo obtained after a certain pixel normalized
Transformation mode coefficient reaches 0.25, it is determined that the pixel is real edge pixel point, if being less than 0.25, it is determined that the pixel
For pseudo-edge pixel, the accuracy of the edge pixel point improved.
Step 203, according to the boundary information, obtain the projection information of the characteristic area;
Step 204, according to the projection information, determine the true and false of the bank note.
Technical solution provided in this embodiment calculates the gradient of each pixel according to wavelet modulus maxima algorithm
Direction, and gradient direction obtained by calculation determine the pixel in the neighborhood needed for the pixel relatively, without by eight
All pixels point in neighborhood carries out WAVELET TRANSFORM MODULUS coefficients comparison, to accelerate Boundary Recognition speed, by setting third
Predetermined threshold value, the pixel to meeting local model maximum value by wavelet transformation mode coefficient screen, and remove pseudo-edge pixel
Point, the accuracy of the edge pixel point improved realize more accurate Boundary Recognition, improve the accurate of forge or true or paper money identification
Property.
Embodiment three
Fig. 3 a are a kind of flow diagram for forge or true or paper money recognition methods that the embodiment of the present invention three provides, and this method is upper
On the basis of stating each embodiment, " according to the boundary information, obtaining the projection information of the characteristic area " is optimized.Such as
Shown in Fig. 3 a, this method may include:
Step 301 cuts the characteristic area for including denomination number in the bank note gray level image that infrared light scanning obtains.
Step 302, the boundary information for determining the included denomination number characteristic area Nei.
Step 303, the gray value that the included pixel of the characteristic area is adjusted according to the boundary information, obtain boundary
Image.
Illustratively, all pixels point that the above-mentioned boundary identified includes is determined according to boundary information, by characteristic area
The all pixels point gray value for including in the boundary of inner face specified number word is adjusted to 255, i.e. white point, in characteristic area it is remaining other
The gray value of pixel is adjusted to 0, i.e. stain, obtains the boundary image with apparent denomination digital boundary, as shown in Figure 3b.
Step 304 projects the boundary image, obtains the projection information.
Illustratively, as shown in Figure 3b, rectangular coordinate system is established to boundary image, X-axis indicates pixel row direction, with one
Pixel length in the horizontal direction is unit, and Y-axis indicates pixel column direction, in the length of vertical direction is single with a pixel
Position, " O " denotation coordination origin, it refers to the picture to boundary image in a direction to carry out projection to boundary image in the present embodiment
Vegetarian refreshments gray value meets the pixel number to impose a condition and is counted.
Optionally, the boundary image is projected, obtains the projection information and includes the following steps:
Step A, the boundary image is projected according to the first preset direction, obtains the first projection information.
Illustratively, in the boundary image of denomination number shown in Fig. 3 b, the first preset direction can be X-direction, i.e.,
Pixel row direction projects the pixel in boundary image according to X-direction, obtains above-mentioned first projection information, such as schemes
Shown in 3c, axis of abscissas indicates pixel column position in Fig. 3 c, and axis of ordinates indicates the picture that gray value in respective rows of pixels reaches 255
The total number of vegetarian refreshments, i.e., the white point total number in each pixel column.It should be noted that can also be by calculating boundary image edge
In X-direction each pixel column the sum of the gray value comprising pixel obtain above-mentioned first projection information.
Step B, according to first projection information and the second predetermined threshold value, the band of position where the boundary is determined.
Illustratively, b is it is found that the obtained boundary position of identification concentrates on the lower half portion of boundary image according to fig. 3, then root
It can determine that the row position range where the boundary of denomination number, the second predetermined threshold value can be 6 according to the first projection information, root
According to the projection information that Fig. 3 c are obtained, determine that white point number reaches the pixel line range of the second predetermined threshold value, as denomination number
The band of position where boundary, as the boundary of denomination number concentrates on pixel column 18-41 rows.
Step C, the boundary image in the band of position is projected according to the second preset direction, obtains the second projection
Information.
Illustratively, the second preset direction can be Y direction, i.e. pixel column direction, then by pixel column 18-41 line ranges
The pixel for including inside is projected according to pixel column direction, obtains the second projection information, as shown in Figure 3d, abscissa in Fig. 3 d
Axis expression pixel column position, gray value reaches the total number of 255 pixel during axis of ordinates expression respective pixel arranges, i.e., each
White point total number in pixel column.It should be noted that can also be included by calculating image each pixel column in Y direction
The sum of gray value of pixel obtains above-mentioned second projection information.
Step 304, according to the projection information, determine the true and false of the bank note.
Illustratively, according to the total number information of each pixel column white point, the true and false of bank note is determined.
Technical solution provided in this embodiment owns after the boundary information for obtaining denomination number to what boundary was included
The gray value of pixel is adjusted, and obtains the apparent boundary image of boundary characteristic, by default according to first to boundary image
Direction is projected, and is carried out preliminary screening to the pixel in boundary image, can effectively be avoided the non-denomination in boundary image
The interference of the noise spot occurred at digital boundary position so that the region where denomination digital boundary is accurately positioned, after screening
Borderline region in pixel projected according to the second preset direction, obtain the second projection information, and determine bank note
The true and false reduces the data volume handled needed for second of projection, and can improve the accuracy of obtained boundary pixel point information, real
Now more accurate Boundary Recognition is further ensured that the accuracy of forge or true or paper money identification.
Example IV
Fig. 4 is a kind of flow diagram for forge or true or paper money recognition methods that the embodiment of the present invention four provides, and the present embodiment exists
On the basis of the various embodiments described above, " according to the projection information, determining the true and false of the bank note " is optimized, this method can
To include:
Step 401 cuts the characteristic area for including denomination number in the bank note gray level image that infrared light scanning obtains.
Step 402, the boundary information for determining the included denomination number characteristic area Nei.
Step 403, according to the boundary information, obtain the projection information of the characteristic area.
Step 404, according to the projection information and third predetermined threshold value, determine boundary that the characteristic area includes
Number.
Illustratively, the column position where denomination digital boundary as shown in Figure 3d is deposited in obtained projection information image
In corresponding peak value, by sample statistics, above-mentioned third threshold is obtained in the case where image resolution ratio is 100DPI*100DPI
Value can be 8, when the white point total number in a certain pixel column reaches 8, then the pixel column is determined as denomination digital boundary institute
Pixel column, obtain boundary number and location information.
Step 405, according to the boundary number and the 4th predetermined threshold value, determine the true and false of the bank note.
Illustratively, in the case where image resolution ratio is 100DPI*100DPI, by sample statistics, face amount is obtained
Boundary number in 1000 Thai Baht genuine note should be 14, and above-mentioned 4th predetermined threshold value could be provided as just whole less than or equal to 14
Number, such as the 4th predetermined threshold value are 12, if detecting, the boundary number of current bank note reaches 12, it is determined that current bank note is genuine note,
If detecting, the boundary number of current bank note is less than 12, it is determined that current bank note is counterfeit money.It should be noted that the 4th default threshold
Value is closer to 14, then the accuracy of forge or true or paper money identification is higher, but false recognition rate can also improve, and therefore, should balance truth identification
Accuracy and false recognition rate suitable 4th predetermined threshold value is set.
Optionally, it according to the projection information, determines the true and false of the bank note, can also include:
According to the projection information and the 5th predetermined threshold value, the boundary position information that the characteristic area includes is determined;Root
According to the boundary position information and predetermined width threshold value, the true and false of the bank note is determined.
Illustratively, according to 404 identical method of above-mentioned steps, the location information on each boundary is obtained, i.e., where each boundary
Pixel column position, wherein the 5th predetermined threshold value can be identical as the 4th predetermined threshold value, can also be different.
Specifically, assuming to judge the denomination digital boundary number of current bank note according to the 5th predetermined threshold value for 14, each side
The corresponding pixel column position in boundary is respectively:10th, 18,21,28,32,39,42,48,54,61,68,73,80 and 88 arrange, then may be used
Pixel column position to be grouped, the first two pixel column 10 and 18 belongs to " 1 " in denomination digital " 1000 ", pixel column 21,
28,32 and 39 for four boundaries of first " 0 " from left to right column position, and so on determine the row of other digital boundaries
Position.Sample statistics are carried out by the Thai Baht to denomination 1000, obtain each digital corresponding column width, example in " 1000 " printed words
If the column width between pixel column 10 and pixel column 18 is 8, each number in the denomination number determined according to sample statistics
The corresponding predetermined width threshold value of each number is arranged in column width.If the column width of each digital boundary is satisfied by corresponding default width
Spend threshold value, it is determined that bank note is genuine note, to carry out more accurate truth identification to bank note.
In addition, can also according to the corresponding pixel column position in each boundary determined, calculate any two boundary it
Between column width, predetermined width threshold value can be according between Arbitrary Boundaries position column width carry out sample statistics obtain,
It need to only ensure that column width computation rule used by current detection bank note is calculated with column width when determining predetermined width threshold value to advise
Then it is consistent.
Further, first sentencing for denomination digital boundary number can also be carried out according to the method for step 404 and step 405
It is disconnected, when determining boundary number reaches four predetermined threshold values, further according to each boundary position information and above-mentioned predetermined width threshold value
Further truth identification is done to bank note, greatly improves the accuracy of forge or true or paper money identification.
Technical solution provided in this embodiment determines of denomination digital boundary according to the projection information of boundary image
Number determines the true and false of bank note according to the 4th predetermined threshold value of denomination digital boundary number and setting, can ensure forge or true or paper money
The accuracy of identification.
Embodiment five
Fig. 5 is the structural schematic diagram of a kind of forge or true or paper money identification device that the embodiment of the present invention five provides, which can be by
Software and or hardware realization can be generally integrated in the equipment with cash examining function, can be by executing forge or true or paper money recognition methods
To carry out forge or true or paper money identification.As shown in figure 5, the device may include:
Characteristic area acquisition module 501, for being cut comprising denomination in the bank note gray level image that infrared light scanning obtains
The characteristic area of number;
Boundary information determining module 502, the boundary information for determining included denomination number in the characteristic area;
Projection information acquisition module 503, for according to the boundary information, obtaining the projection information of the characteristic area;
Truth identification module 504, for according to the projection information, determining the true and false of the bank note.
Technical solution provided in this embodiment, by being cut comprising denomination in the bank note gray level image that is obtained under infrared light
The characteristic area of number, and determine the boundary information of characteristic area inner face specified number word, it is projected accordingly according to boundary information
Information, and then determine the true and false of bank note.Enable by determining that boundary information accurately carries out feature extraction to characteristic area,
And then the true and false of bank note is determined according to the projection information of boundary information, greatly improve the accuracy of forge or true or paper money identification.
On the basis of the above embodiments, the boundary information determining module 502 is additionally operable to:According to wavelet transform modulus maxima
Value-based algorithm and the second predetermined threshold value determine the boundary information of the included denomination number characteristic area Nei.
On the basis of the above embodiments, the projection information acquisition module 503 includes:
Boundary image acquiring unit, the ash for adjusting the included pixel of the characteristic area according to the boundary information
Angle value obtains boundary image;
Projection information acquiring unit obtains the projection information for being projected to the boundary image.
On the basis of the above embodiments, projection information acquiring unit includes:
First projection information obtains subelement and is obtained for being projected according to the first preset direction to the boundary image
To the first projection information;
Borderline region determination subelement, for according to first projection information and the second predetermined threshold value, determining the side
The band of position where boundary;
Second projection information obtains subelement, is used for the boundary image in the band of position according to the second preset direction
It is projected, obtains the second projection information.
On the basis of the above embodiments, the truth identification module 504 includes:
Boundary number determination unit, for according to the projection information and third predetermined threshold value, determining the characteristic area
Including boundary number;
Truth identification unit, for according to the boundary number and the 4th predetermined threshold value, determining the true and false of the bank note.
On the basis of the above embodiments, the truth identification module 504 further includes:
Boundary position information determination unit, for according to the projection information and the 5th predetermined threshold value, determining the feature
The boundary position information that region includes;
Forge or true or paper money recognition unit, for according to the boundary position information and predetermined width threshold value, determining the bank note
The true and false.
On the basis of the above embodiments, the bank note is Thai Baht.
Embodiment six
The embodiment of the present invention six provides a kind of equipment, including the forge or true or paper money identification that any embodiment of the present invention is provided
Device.
Specifically, as shown in fig. 6, the embodiment of the present invention provides a kind of equipment, which includes processor 60, memory
61, input unit 62 and output device 63;The quantity of processor 60 can be one or more in equipment, at one in Fig. 6
For reason device 60;Processor 60, memory 61, input unit 62 and output device 63 in equipment can by bus or other
Mode connects, in Fig. 6 for being connected by bus.
Memory 61 is used as a kind of computer readable storage medium, can be used for storing software program, computer can perform journey
Sequence and module, if the corresponding program instruction/module of forge or true or paper money recognition methods in the embodiment of the present invention is (for example, bank note is true
Characteristic area acquisition module 501, boundary information determining module 502, projection information acquisition module 503 in pseudo- identification device and true
Pseudo- identification module 504).Processor 60 is stored in software program, instruction and module in memory 61 by operation, to hold
Above-mentioned forge or true or paper money recognition methods is realized in the various function application of row equipment and data processing.
Memory 61 can include mainly storing program area and storage data field, wherein storing program area can store operation system
Application program needed for system, at least one function;Storage data field can be stored uses created data etc. according to equipment.This
Outside, memory 61 may include high-speed random access memory, can also include nonvolatile memory, for example, at least a magnetic
Disk storage device, flush memory device or other non-volatile solid state memory parts.In some instances, memory 61 can be further
Include the memory remotely located relative to processor 60, these remote memories can pass through network connection to equipment.It is above-mentioned
The example of network includes but not limited to internet, intranet, LAN, mobile radio communication and combinations thereof.
Input unit 62 can be used for receiving the number or character information of input, and generate with the user setting of equipment and
The related key signals input of function control.Output device 63 may include that display screen etc. shows equipment.
The embodiment of the present invention also provides a kind of storage medium including computer executable instructions, and the computer is executable
When being executed by computer processor for executing a kind of forge or true or paper money recognition methods, this method includes for instruction:
The characteristic area for including denomination number is cut in the bank note gray level image that infrared light scanning obtains;
Determine the boundary information of the included denomination number characteristic area Nei;
According to the boundary information, the projection information of the characteristic area is obtained;
According to the projection information, the true and false of the bank note is determined.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but the former is more in many cases
Good embodiment.Based on this understanding, technical scheme of the present invention substantially in other words contributes to the prior art
Part can be expressed in the form of software products, which can be stored in computer readable storage medium
In, such as the floppy disk of computer, read-only memory (Read-Only Memory, ROM), random access memory (Random
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be personal computer, server or the network equipment etc.) executes the method described in each embodiment of the present invention.
It is worth noting that, in the embodiment of above-mentioned forge or true or paper money identification device, included each unit and module are only
It is divided according to function logic, but is not limited to above-mentioned division, as long as corresponding function can be realized;Separately
Outside, the specific name of each functional unit is also only to facilitate mutually distinguish, the protection domain being not intended to restrict the invention.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope of present disclosure, all answer by the change or replacement that can be readily occurred in
It is included within the scope of the present invention.Therefore, protection scope of the present invention should be with the scope of the claims
It is accurate.
The forge or true or paper money identification device and equipment provided in above-described embodiment can perform any embodiment of the present invention and be provided
Forge or true or paper money recognition methods, have and execute the corresponding function module of this method and advantageous effect.Not in the above-described embodiments in detail
The technical detail described to the greatest extent, reference can be made to the forge or true or paper money recognition methods that any embodiment of the present invention is provided.
Note that 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 present invention is not limited to specific embodiments described here, can carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out to the present invention by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
May include other more equivalent embodiments, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. a kind of forge or true or paper money recognition methods, which is characterized in that including:
The characteristic area for including denomination number is cut in the bank note gray level image that infrared light scanning obtains;
Determine the boundary information of the included denomination number characteristic area Nei;
According to the boundary information, the projection information of the characteristic area is obtained;
According to the projection information, the true and false of the bank note is determined.
2. according to the method described in claim 1, it is characterized in that, determining the side of included denomination number in the characteristic area
Boundary's information, including:
According to wavelet modulus maxima algorithm and the second predetermined threshold value, included denomination number in the characteristic area is determined
Boundary information.
3. according to the method described in claim 1, it is characterized in that, according to the boundary information, the characteristic area is obtained
Projection information, including:
The gray value that the included pixel of the characteristic area is adjusted according to the boundary information, obtains boundary image;
The boundary image is projected, the projection information is obtained.
4. according to the method described in claim 3, it is characterized in that, projected to the boundary image, the projection is obtained
Information, including:
The boundary image is projected according to the first preset direction, obtains the first projection information;
According to first projection information and the second predetermined threshold value, the band of position where the boundary is determined;
Boundary image in the band of position is projected according to the second preset direction, obtains the second projection information.
5. according to the method described in claim 1, it is characterized in that, according to the projection information, the true and false of the bank note is determined,
Including:
According to the projection information and third predetermined threshold value, the boundary number that the characteristic area includes is determined;
According to the boundary number and the 4th predetermined threshold value, the true and false of the bank note is determined.
6. according to the method described in claim 1, it is characterized in that, according to the projection information, the true and false of the bank note is determined,
Including:
According to the projection information and the 5th predetermined threshold value, the boundary position information that the characteristic area includes is determined;
According to the boundary position information and predetermined width threshold value, the true and false of the bank note is determined.
7. according to the method described in claim 1-6 any one, which is characterized in that the bank note is Thai Baht.
8. a kind of forge or true or paper money identification device, which is characterized in that including:
Characteristic area determining module, for cutting the spy for including denomination number in the bank note gray level image that infrared light scanning obtains
Levy region;
Boundary information determining module, the boundary information for determining included denomination number in the characteristic area;
Projection information acquisition module, for according to the boundary information, obtaining the projection information of the characteristic area;
Truth identification module, for according to the projection information, determining the true and false of the bank note.
9. device according to claim 8, which is characterized in that
The boundary information determining module is specifically used for:According to wavelet modulus maxima algorithm and the second predetermined threshold value, determine
The boundary information of included denomination number in the characteristic area.
10. device according to claim 8, which is characterized in that the truth identification module includes:
Boundary number determination unit, for according to the projection information and third predetermined threshold value, determining that the characteristic area includes
Boundary number;
Truth identification unit, for according to the boundary number and the 4th predetermined threshold value, determining the true and false of the bank note.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710086364.XA CN108460775A (en) | 2017-02-17 | 2017-02-17 | A kind of forge or true or paper money recognition methods and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710086364.XA CN108460775A (en) | 2017-02-17 | 2017-02-17 | A kind of forge or true or paper money recognition methods and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108460775A true CN108460775A (en) | 2018-08-28 |
Family
ID=63229080
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710086364.XA Pending CN108460775A (en) | 2017-02-17 | 2017-02-17 | A kind of forge or true or paper money recognition methods and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108460775A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110415424A (en) * | 2019-06-17 | 2019-11-05 | 众安信息技术服务有限公司 | A kind of authentication method, apparatus, computer equipment and storage medium |
CN111627145A (en) * | 2020-05-19 | 2020-09-04 | 武汉卓目科技有限公司 | Method and device for identifying fine hollow image-text of image |
CN113139927A (en) * | 2020-01-02 | 2021-07-20 | 深圳怡化电脑股份有限公司 | Banknote crack detection method, device, equipment and readable medium |
CN117237966A (en) * | 2023-11-13 | 2023-12-15 | 恒银金融科技股份有限公司 | Banknote recognition method and device based on internal contour of denomination digital character |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120117049A (en) * | 2011-04-14 | 2012-10-24 | 삼성전자주식회사 | Method and apparatus for indentifying fake banknote in a poratable terminal |
CN103136845A (en) * | 2013-01-23 | 2013-06-05 | 浙江大学 | Renminbi (RMB) counterfeit identifying method based on crown-word image characters |
CN103702021A (en) * | 2013-12-29 | 2014-04-02 | 广州视声电子科技有限公司 | Currency detection camera |
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 |
CN104851184A (en) * | 2015-05-27 | 2015-08-19 | 深圳怡化电脑股份有限公司 | Recognition method of transversely spliced banknote and device thereof |
CN105184957A (en) * | 2015-09-28 | 2015-12-23 | 深圳怡化电脑股份有限公司 | Paper currency discrimination method and system |
CN105374105A (en) * | 2015-10-16 | 2016-03-02 | 浙江依特诺科技股份有限公司 | Method used by mobile terminal for identifying authenticity of banknote |
CN106340115A (en) * | 2015-07-14 | 2017-01-18 | 深圳怡化电脑股份有限公司 | Method and device for recognizing crown word number of banknote |
-
2017
- 2017-02-17 CN CN201710086364.XA patent/CN108460775A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120117049A (en) * | 2011-04-14 | 2012-10-24 | 삼성전자주식회사 | Method and apparatus for indentifying fake banknote in a poratable terminal |
CN103136845A (en) * | 2013-01-23 | 2013-06-05 | 浙江大学 | Renminbi (RMB) counterfeit identifying method based on crown-word image characters |
CN103702021A (en) * | 2013-12-29 | 2014-04-02 | 广州视声电子科技有限公司 | Currency detection camera |
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 |
CN104851184A (en) * | 2015-05-27 | 2015-08-19 | 深圳怡化电脑股份有限公司 | Recognition method of transversely spliced banknote and device thereof |
CN106340115A (en) * | 2015-07-14 | 2017-01-18 | 深圳怡化电脑股份有限公司 | Method and device for recognizing crown word number of banknote |
CN105184957A (en) * | 2015-09-28 | 2015-12-23 | 深圳怡化电脑股份有限公司 | Paper currency discrimination method and system |
CN105374105A (en) * | 2015-10-16 | 2016-03-02 | 浙江依特诺科技股份有限公司 | Method used by mobile terminal for identifying authenticity of banknote |
Non-Patent Citations (1)
Title |
---|
王丽荣: "《基于小波变换的目标检测方法研究》", 31 December 2008, 吉林人民出版社出版 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110415424A (en) * | 2019-06-17 | 2019-11-05 | 众安信息技术服务有限公司 | A kind of authentication method, apparatus, computer equipment and storage medium |
CN113139927A (en) * | 2020-01-02 | 2021-07-20 | 深圳怡化电脑股份有限公司 | Banknote crack detection method, device, equipment and readable medium |
CN111627145A (en) * | 2020-05-19 | 2020-09-04 | 武汉卓目科技有限公司 | Method and device for identifying fine hollow image-text of image |
CN117237966A (en) * | 2023-11-13 | 2023-12-15 | 恒银金融科技股份有限公司 | Banknote recognition method and device based on internal contour of denomination digital character |
CN117237966B (en) * | 2023-11-13 | 2024-01-30 | 恒银金融科技股份有限公司 | Banknote recognition method and device based on internal contour of denomination digital character |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7092554B2 (en) | Method for detecting eye and mouth positions in a digital image | |
US20170287252A1 (en) | Counterfeit Document Detection System and Method | |
US6792134B2 (en) | Multi-mode digital image processing method for detecting eyes | |
CN112686812B (en) | Bank card inclination correction detection method and device, readable storage medium and terminal | |
US8254644B2 (en) | Method, apparatus, and program for detecting facial characteristic points | |
KR20200118842A (en) | Identity authentication method and device, electronic device and storage medium | |
CN108460775A (en) | A kind of forge or true or paper money recognition methods and device | |
JP2002259994A (en) | Automatic image pattern detecting method and image processor | |
CN106952393B (en) | Paper money identification method and device, electronic equipment and storage medium | |
CN107016363A (en) | Bill images managing device, bill images management system and method | |
Youn et al. | Efficient multi-currency classification of CIS banknotes | |
CN107103683B (en) | Paper money identification method and device, electronic equipment and storage medium | |
CN114067186B (en) | Pedestrian detection method and device, electronic equipment and storage medium | |
CN106355744A (en) | Image identification method and device | |
CN106780966A (en) | A kind of paper money discrimination method and device | |
Roy et al. | Fake currency detection using image processing | |
CN106447910B (en) | A kind of method and device of paper money recognition | |
CN107680246B (en) | Method and equipment for positioning curve boundary in paper money pattern | |
CN113920434A (en) | Image reproduction detection method, device and medium based on target | |
Colaco et al. | Efficient Image Processing Technique for Authentication of Indian Paper Currency | |
CN111368856B (en) | Book spine extraction method and device of book checking system based on vision | |
Morinaga et al. | Classification between natural and graphics images based on generalized Gaussian distributions | |
Shinde et al. | Identification of fake currency using soft computing | |
Narra et al. | Indian Currency Classification and Fake Note Identification using Feature Ensemble Approach | |
CN109543554A (en) | Bill detection method, device, terminal and computer readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180828 |