CN106340116B - A kind of recognition methods of bank note and device - Google Patents
A kind of recognition methods of bank note and device Download PDFInfo
- Publication number
- CN106340116B CN106340116B CN201610733157.4A CN201610733157A CN106340116B CN 106340116 B CN106340116 B CN 106340116B CN 201610733157 A CN201610733157 A CN 201610733157A CN 106340116 B CN106340116 B CN 106340116B
- Authority
- CN
- China
- Prior art keywords
- yin
- gray level
- yang
- character features
- 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.)
- Expired - Fee Related
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
Abstract
The embodiment of the invention discloses a kind of recognition methods of bank note and devices.This method comprises: obtaining the gray level image in the yin-yang character features region of bank note；Binary conversion treatment is carried out to the gray level image in yin-yang character features region, generates binary image；The pattern characteristics in yin-yang character features region are extracted according to binary image；According to pattern characteristics and setting identification condition, bank note is identified.According to the technical solution of the present invention, bank note can be rapidly and accurately identified, time efficiency is high, and algorithm complexity is low.
Description
Technical field
The present embodiments relate to the recognition methods of paper money recognition technology more particularly to a kind of bank note and devices.
Background technique
With China's economic development, bank note cash flow flux is continuously increased in the market, and bank note also increases anti-counterfeiting characteristic.It passes
The identification technology of system needs artificial setting identification point, and such methods are low to noise immunity, when characteristic area slightly pollute or inclined
It moves, identifies and be easy error, discrimination is low.
In the prior art, by neural network recognization bank note, acquisition banknote image first extracts image preprocessing
Characteristics of image collects a certain number of bank note feature samples, then trains neural network, the successful standard of training is neural network
All training samples can be correctly identified, to reach paper money recognition.
Disadvantage of the prior art bank note in identification process: if the sample of 1, acquisition does not reach needed for trained network
Sample, then repeat Image Acquisition, pretreatment and feature special zone, and such time efficiency is low；2, in sample collection procedure such as
There is exceptional sample in fruit, then identifies that the accuracy rate of bank note will decline；3, in neural network training process, if training is not
Successful then need to resurvey image pattern, repeatability is strong in this way, algorithm complexity is high.
Summary of the invention
The embodiment of the present invention provides recognition methods and the device of a kind of bank note, to improve recognition efficiency and accuracy.
In a first aspect, the embodiment of the invention provides a kind of recognition methods of bank note, comprising:
Obtain the gray level image in the yin-yang character features region of bank note；
Binary conversion treatment is carried out to the gray level image in yin-yang character features region, generates binary image；
The pattern characteristics in yin-yang character features region are extracted according to the binary image；
According to the pattern characteristics and setting identification condition, the bank note is identified.
Further, the gray level image in the yin-yang character features region for obtaining bank note, comprising:
Obtain the gray level image of entire paper coin；
The gray level image in region of the interception comprising yin-yang character features from the gray level image of the entire paper coin.
Further, the gray level image to yin-yang character features region carries out binary conversion treatment, generates two-value
Change image the step of include:
According to the gray level image in yin-yang character features region, the pixel gray level for meeting high brightness conditions is searched, is made
For binarization threshold；
Binary conversion treatment is carried out according to gray level image of the binarization threshold to yin-yang character features region, is generated
Binary image.
Further, the gray level image according to yin-yang character features region, lookup meet high brightness conditions
Pixel gray level includes: as binarization threshold
The quantity of pixel in yin-yang character features region is counted according to tonal gradation；
According to the sequence of tonal gradation from small to large, the pixel quantity of each tonal gradation is added up；
If cumulative quantitative value reaches the high brightness conditions quantitative proportion of setting, it is determined that the pixel being currently added to
Corresponding gray value is the binarization threshold.
Further, the pattern characteristics packet that yin-yang character features region is extracted according to the binary image
It includes:
The pattern precise boundary that yin-yang character features region is determined according to the binary image, as the pattern
Feature.
Further, the pattern precise boundary that yin-yang character features region is determined according to the binary image
Include:
According to the binary image, the number of black pixel in every row is calculated, determines there is the company of most black pixels
Up-and-down boundary of the position of continuous setting line number as yin-yang character pattern；
The number of black pixel in each column is calculated, determines there is the position conduct of the continuous setting columns of most black pixels
The right boundary of yin-yang character pattern；
Region between up-and-down boundary is bisected into upper and bottom section；
Calculate separately the upper and bottom section column and；
The region between right boundary is split according to preset interval, forms segmentation column part；
Calculate the pixel number of respective upper and bottom section in each segmentation column part；
If the black pixel number in upper part in each segmentation column part is greater than in each segmentation column part
The lower certain threshold value in part, is denoted as 1；
If the black pixel number in lower part in each segmentation column part is greater than in each segmentation column part
The upper certain threshold value in part, is denoted as -1.
Second aspect, the embodiment of the invention also provides a kind of identification devices of bank note, comprising:
Obtain module, the gray level image in the yin-yang character features region for obtaining bank note；
Processing module carries out binary conversion treatment for the gray level image to yin-yang character features region, generates two-value
Change image；
Extraction module, for extracting the pattern characteristics in yin-yang character features region according to the binary image；
Identification module, for identifying the bank note according to the pattern characteristics and setting identification condition.
Further, the acquisition module is specifically used for:
Obtain the gray level image of entire paper coin；
The gray level image in region of the interception comprising yin-yang character features from the gray level image of the entire paper coin.
Further, the processing module includes:
Threshold value determination unit, for the gray level image according to yin-yang character features region, lookup meets highlight bar
The pixel gray level of part, as binarization threshold；
Image generation unit, for according to the binarization threshold to the gray level image in yin-yang character features region into
Row binary conversion treatment generates binary image.
Further, described image generation unit is specifically used for:
The quantity of pixel in yin-yang character features region is counted according to tonal gradation；
According to the sequence of tonal gradation from small to large, the pixel quantity of each tonal gradation is added up；
If cumulative quantitative value reaches the high brightness conditions quantitative proportion of setting, it is determined that the pixel being currently added to
Corresponding gray value is the binarization threshold.
Further, the extraction module is specifically used for:
The pattern precise boundary that yin-yang character features region is determined according to the binary image, as the pattern
Feature.
Further, the extraction module is specifically used for:
According to the binary image, the number of black pixel in every row is calculated, determines there is the company of most black pixels
Up-and-down boundary of the position of continuous setting line number as yin-yang character pattern；
The number of black pixel in each column is calculated, determines there is the position conduct of the continuous setting columns of most black pixels
The right boundary of yin-yang character pattern；
Region between up-and-down boundary is bisected into upper and bottom section；
Calculate separately the upper and bottom section column and；
The region between right boundary is split according to preset interval, forms segmentation column part；
Calculate the pixel number of respective upper and bottom section in each segmentation column part；
If the black pixel number in upper part in each segmentation column part is greater than in each segmentation column part
The lower certain threshold value in part, is denoted as 1；
If the black pixel number in lower part in each segmentation column part is greater than in each segmentation column part
The upper certain threshold value in part, is denoted as -1.
The embodiment of the present invention provides recognition methods and the device of a kind of bank note, passes through the yin-yang character features area for obtaining bank note
The gray level image in domain, carries out binary conversion treatment to gray level image, generates binary image, extracts yin-yang text to binary image
The pattern characteristics of characteristic area solve the problems, such as the identification of bank note, have reached fast according to pattern characteristics and setting identification condition
Speed accurately identifies bank note, and time efficiency is high, the low effect of algorithm complexity.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the recognition methods of bank note in the embodiment of the present invention one；
Fig. 2 is a kind of flow chart of the recognition methods of bank note in the embodiment of the present invention two；
Fig. 3 is the schematic diagram of the gray level image in the region of character features containing yin-yang in the embodiment of the present invention two；
Fig. 4 is yin-yang character area binaryzation effect picture in the embodiment of the present invention two；
Fig. 5 is the segmentation effect figure of yin-yang character area in the embodiment of the present invention two；
Fig. 6 is a kind of structural schematic diagram of the identification device of bank note in the embodiment of the present invention three；
Fig. 7 is a kind of structural schematic diagram of the preferred embodiment of the identification device of bank note in the embodiment of the present invention three.
Specific embodiment
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 limiting 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.
Embodiment one
Fig. 1 is a kind of flow chart of the recognition methods for bank note that the embodiment of the present invention one provides, and the present embodiment is applicable to
Paper money recognition containing yin-yang character features, such as 2015 editions RMB are equally applicable to other with yin-yang character features area
The paper money recognition in domain.This method is executed by the identification device of bank note, and the mode which can be used software and/or hardware is real
It is existing, it is generally integrated in cash inspecting machine or automatic teller machine.This method specifically includes:
The gray level image in the yin-yang character features region of S101, acquisition bank note.
Specifically, there are many features in bank note, wherein yin-yang text is one of the notable feature of bank note.Image processing apparatus
Banknote image information is obtained by imaging sensor, gray processing processing is carried out to yin-yang character features region in banknote image, i.e.,
The yin-yang character features area image of the bank note of rgb format is converted into gray level image, and (gray level image is between black and white
There are many more the color depth of grade, tonal range is generally 0-255).
S102, binary conversion treatment is carried out to the gray level image in yin-yang character features region, generates binary image.
Preferably, binary conversion treatment is carried out according to gray level image of the binarization threshold to yin-yang character features region,
Generate binary image.
Specifically, the gray level image in yin-yang character features region further includes background and noise, in addition to including yin-yang text
Want that the extracting target from images object from multivalue, i.e., the characters cut in relief word in gray level image set a threshold value thus, the threshold value will
The data of image are divided into two parts, and the pixel greater than threshold value and the pixel less than threshold value will be greater than the pixel of threshold value
Pixel value is set as white, and the pixel less than threshold value is set as black, this threshold value is binarization threshold.I.e. to the yin-yang text
The gray level image of word characteristic area passes through binary conversion treatment, generates binary image, and binaryzation threshold will be greater than in binary image
The gray value of the pixel of value is set as 255, and the gray value less than the pixel of binarization threshold is set as 0, the point that gray value is 255
It is white pixel point, the point that gray value is 0 is black pixel point.Namely the gray level image in yin-yang character features region is presented
(background and characters cut in intaglio word are shown as white to apparent black and white effect in the gray level image in yin-yang character features region, positive text importing out
It is black).
S103, the pattern characteristics that yin-yang character features region is extracted according to the binary image.
Specifically, gray level image after binary conversion treatment, is shown as black white image, i.e. binary image, need at this time
The boundary for positioning yin-yang text by coordinate position from binary image is extracted special to the pattern in its yin-yang character features region
Sign.
Preferably, the pattern precise boundary that yin-yang character features region is determined according to the binary image, as
The pattern characteristics, comprising:
According to the binary image, the number of black pixel in every row is calculated, determines there is the company of most black pixels
Up-and-down boundary of the position of continuous setting line number as yin-yang character pattern；
The number of black pixel in each column is calculated, determines there is the position conduct of the continuous setting columns of most black pixels
The right boundary of yin-yang character pattern；
Region between up-and-down boundary is bisected into upper and bottom section；
Calculate separately the upper and bottom section column and；
The region between right boundary is split according to preset interval, forms segmentation column part；
Calculate the pixel number of respective upper and bottom section in each segmentation column part；
If the black pixel number in upper part in each segmentation column part is greater than in each segmentation column part
The lower certain threshold value in part, is denoted as 1；
If the black pixel number in lower part in each segmentation column part is greater than in each segmentation column part
The upper certain threshold value in part, is denoted as -1.
Specifically, each pixel is distributed in corresponding ranks coordinate in binary image according to binary image
In, the number of black pixel in every row in binary image is calculated first.RMB with the 100 yuan of face amounts of version in 2015 is
Example, after to its yin-yang character features region binary conversion treatment, obtains binary image, first calculates every row to binary image
In black pixel number, determine most continuous 34 row of black in binary image pixel (2015 editions 100 yuans
The height of yin-yang text is maximum position for position 34), at this time up-and-down boundary of the maximum position as yin-yang text.Equally
The number for calculating black pixel in binary image each column, determine black in binary image pixel it is most continuous 100
The position for arranging (width of 2015 editions 100 yuans of yin-yang text is 100) is maximum position, maximum position conduct at this time
The right boundary of yin-yang text.After having good positioning to the up-and-down boundary of yin-yang text, the region between up-and-down boundary is divided into up and down
Two parts, the height of 2015 editions 100 yuans of yin-yang text are 34, if will be divided into region in-between: top is divided into
Continuous 17 row, lower part are divided into lower boundary up continuous 17 row, will lead to will appear coincidence between 17 rows so down for coboundary
Place, to black pixel number inaccuracy is calculated later, to guarantee that the top and the bottom in the region between up-and-down boundary are divided completely
It cuts open, top will be carried out to its region and be divided into coboundary continuous 14 row down, lower part is divided into lower boundary up continuous 14 row.According to
Ready-portioned two parts up and down, calculate separately the number of the black pixel of upper and lower two parts column direction.Thus by yin-yang text
34*100 Ratage Coutpressioit is at 1*100 range.It then, will be between right boundary according to preset interval { 0,23,44,64,85,107 }
Region be split, (wherein, in the region between right boundary intercharacter divide relative position be fixed) to column side
To being divided into 5 regions.Calculate it is each segmentation column respective upper and bottom section black pixel number and.At this point, yin-yang
Text 1*100 is compressed into 1*5 range.If the sum of the black pixel number in upper part of each segmentation column is greater than each of corresponding
Divide column the black pixel number threshold value in lower part, be denoted as 1, if it is each segmentation column the black pixel number in lower part and it is big
In the black pixel number threshold value in upper part that corresponding each segmentation arranges, it is denoted as -1.Pattern characteristics { -1,1, -1,1, -1 }.
S104, according to the pattern characteristics and setting identification condition, identify the bank note.
Specifically, pattern characteristics compare, yin-yang character features area top divides in bank note to be detected and lower part column direction is every
In a spacer region stain pixel and, if stain picture in each spacer region of yin-yang text top and the bottom column direction of bank note to be detected
Element and with stain pixel in pattern characteristics and when being not much different, and preset interval is from left to right moved, check for figure
Pattern characteristics may recognize that the bank note if there are pattern characteristics for yin-yang text in bank note to be detected.In the prior art,
Paper money recognition needs the pixel to ranks all in characteristic area direction two-dimensions to be compared identification, and the embodiment of the present invention
In only need to be according to obtained pattern characteristics come the pixel of matching identification column direction dimension.Pixel ratio can be reduced in this way
Pair number, improve efficiency.
The embodiment of the present invention one provides the recognition methods of bank note, the gray scale in the yin-yang character features region by obtaining bank note
Image carries out binary conversion treatment to the gray level image in yin-yang character features region, generates binary image；According to binary image
Extract the pattern characteristics in yin-yang character features region；According to pattern characteristics and setting identification condition, can rapidly and accurately know
Other bank note, time efficiency is high, and algorithm complexity is low.
Embodiment two
Fig. 2 is a kind of method of paper money recognition provided by Embodiment 2 of the present invention, base of the present embodiment in a upper embodiment
On plinth, compared with previous embodiment, difference is, yin-yang character features image obtains, and advanced optimizes the choosing of binarization threshold
It takes.This method comprises:
S201, the gray level image for obtaining entire paper coin.
Specifically, first image processing apparatus by imaging sensor obtain entire paper coin image information, to entire paper
Coin image carries out gray processing processing, i.e., the banknote image of rgb format being converted into gray level image, (gray level image is in black and white
Between there are many more the color depth of grade, tonal range is generally 0-255).
S202, interception includes the gray level image in the region of yin-yang character features from the gray level image of the entire paper coin.
Specifically, with the position in yin-yang character features region in the bank note of face amount being opposite entire paper coin, position with version
Be it is fixed, device by coordinate setting is intercepted from the entire paper coin include yin-yang character features region grayscale image
Picture.As shown in Figure 3.
S203, according to the gray level image in yin-yang character features region, search the pixel ash for meeting high brightness conditions
Degree, as binarization threshold.
Specifically, gray level image is different from black white image, gray level image is typically shown as from most dark black to most bright
The gray scale of white, gray level image rate range are generally 0-255, and the gray level image in yin-yang character features region is in addition to including yin-yang
Text also has powerful connections and noise, to search the picture for meeting high brightness conditions from the extracting target from images object of multivalue
Vegetarian refreshments gray scale, high brightness conditions refer in gray level image to realize yin-yang character features area on the basis of certain pixel gray level
The gray level image middle-jiao yang, function of the spleen and stomach text pixel point in domain is gradually shown as black pixel, and characters cut in intaglio word and background pixel point are gradually shown as white
Pixel.If being able to satisfy the pixel gray level of high brightness conditions, threshold value of the pixel gray level as binaryzation.
Preferably, according to the gray level image in yin-yang character features region, the pixel for meeting high brightness conditions is searched
Gray scale includes: as binarization threshold
The quantity of pixel in yin-yang character features region is counted according to tonal gradation；
According to the sequence of tonal gradation from small to large, the pixel quantity of each tonal gradation is added up；
If cumulative quantitative value reaches the high brightness conditions quantitative proportion of setting, it is determined that the pixel being currently added to
Corresponding gray value is the binarization threshold.
Specifically, the tonal gradation of gray level image is generally 0-255, different grades of gray value corresponds to the picture of different number
Vegetarian refreshments, the gray value in gray level image there is same levels correspond to multiple pixels.According to corresponding to tonal gradation
Pixel, the quantity of the pixel in yin-yang character features region described in statistical pixel values distribution histogram.It is horizontal in histogram
The tonal gradation of the gray level image in coordinate representation yin-yang character features region, ordinate indicate corresponding grey scale grade in gray level image
Pixel quantity.According to the tonal gradation in histogram from the tonal gradation sequence of 0-255, by picture corresponding to each tonal gradation
Vegetarian refreshments quantity successively adds up, if cumulative quantitative value reaches the high brightness conditions quantitative proportion of setting, i.e. cumulative number
When amount is more than certain amount threshold value (such as 10% of whole region pixel number), corresponding to the pixel being added at this time
Gray value is binarization threshold.To exclude noise jamming, or show more clear (the characters cut in relief word in yin-yang character features region for image
It is shown as stain pixel, background and characters cut in intaglio word are shown as white point pixel), using total to the low point Zhan of the gray value in yin-yang text
The ratio of pixel number is no more than 10%, can set ratio as 0.1.
S204, it is carried out at binaryzation according to gray level image of the binarization threshold to yin-yang character features region
Reason generates binary image.
S204 is identical as one S102 of embodiment.As shown in Figure 4.
S205, the pattern characteristics that yin-yang character features region is extracted according to the binary image.
S205 is identical as one S103 of embodiment.As shown in figure 5, pattern characteristics are { -1,1, -1,1, -1 }.
S206, according to the pattern characteristics and setting identification condition, identify the bank note.
S206 is identical as one S104 of embodiment.
Second embodiment of the present invention provides the recognition methods of bank note, according to the practical ratio setting two accounted for of yin-yang text pixel point
Value threshold value according to pattern characteristics and identification condition, identifies bank note using binary conversion treatment image, improve accuracy of identification and
Time efficiency reduces algorithm complexity.
Embodiment three
Fig. 6 shows a kind of structural schematic diagram of the identification device of bank note of the embodiment of the present invention three.The device includes: to obtain
Modulus block 601, processing module 602, extraction module 603, identification module 604, are below specifically described each module.
The acquisition module 601, the gray level image in the yin-yang character features region for obtaining bank note；
The processing module 602 carries out binary conversion treatment for the gray level image to yin-yang character features region, raw
At binary image；
The extraction module 603, for extracting the pattern in yin-yang character features region according to the binary image
Feature；
The identification module 604, for identifying the bank note according to the pattern characteristics and setting identification condition.
Preferably, the acquisition module is specifically used for:
Obtain the gray level image of entire paper coin；
The gray level image in region of the interception comprising yin-yang character features from the gray level image of the entire paper coin.
Preferably, as shown in fig. 7, the processing module includes:
It is highlighted to search satisfaction for the gray level image according to yin-yang character features region for threshold value determination unit 6021
The pixel gray level of degree condition, as binarization threshold；
Image generation unit 6022, for the grayscale image according to the binarization threshold to yin-yang character features region
As carrying out binary conversion treatment, binary image is generated.
Preferably, described image generation unit is specifically used for:
The quantity of pixel in yin-yang character features region is counted according to tonal gradation；
According to the sequence of tonal gradation from small to large, the pixel quantity of each tonal gradation is added up；
If cumulative quantitative value reaches the high brightness conditions quantitative proportion of setting, it is determined that the pixel being currently added to
Corresponding gray value is the binarization threshold.
Preferably, the extraction module is specifically used for:
The pattern precise boundary that yin-yang character features region is determined according to the binary image, as the pattern
Feature.
Preferably, the extraction module is specifically used for:
According to the binary image, the number of black pixel in every row is calculated, determines there is the company of most black pixels
Up-and-down boundary of the position of continuous setting line number as yin-yang character pattern；
The number of black pixel in each column is calculated, determines there is the position conduct of the continuous setting columns of most black pixels
The right boundary of yin-yang character pattern；
Region between up-and-down boundary is bisected into upper and bottom section；
Calculate separately the upper and bottom section column and；
The region between right boundary is split according to preset interval, forms segmentation column part；
Calculate the pixel number of respective upper and bottom section in each segmentation column part；
If the black pixel number in upper part in each segmentation column part is greater than in each segmentation column part
The lower certain threshold value in part, is denoted as 1；
If the black pixel number in lower part in each segmentation column part is greater than in each segmentation column part
The upper certain threshold value in part, is denoted as -1.
The embodiment of the present invention three provides a kind of identification device of bank note, by carrying out two-value to the bank note containing yin-yang text
Change processing, obtains binary image, extracts the pattern characteristics in yin-yang character features region, according to the pattern characteristics and
Identification condition is set, identifies bank note, recognition efficiency and accuracy is improved to improve, reduces algorithm complexity.
Bank note provided by any embodiment of the invention can be performed in the identification device of bank note provided by the embodiment of the present invention
Recognition methods, have the corresponding functional module of execution method and beneficial effect.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to 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 by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (8)
1. a kind of recognition methods of bank note characterized by comprising
Obtain the gray level image in the yin-yang character features region of bank note；
Binary conversion treatment is carried out to the gray level image in yin-yang character features region, generates binary image；
The pattern characteristics in yin-yang character features region are extracted according to the binary image；
According to the pattern characteristics and setting identification condition, the bank note is identified；
The pattern characteristics that yin-yang character features region is extracted according to the binary image, comprising:
The pattern precise boundary that yin-yang character features region is determined according to the binary image, it is special as the pattern
Sign；
The pattern precise boundary that yin-yang character features region is determined according to the binary image, comprising:
According to the binary image, the number of black pixel in every row is calculated, determines there is continuously setting for most black pixels
Determine up-and-down boundary of the position of line number as yin-yang character pattern；
The number of black pixel in each column is calculated, determines the position that there is the continuous setting columns of most black pixels as yin-yang
The right boundary of character pattern；
Region between up-and-down boundary is bisected into upper and bottom section；
Calculate separately the upper and bottom section column and；
The region between right boundary is split according to preset interval, forms segmentation column part；
Calculate the pixel number of respective upper and bottom section in each segmentation column part；
If the black pixel number in upper part in each segmentation column part is greater than the lower part in each segmentation column part
Divide certain threshold value, is denoted as 1；
If the black pixel number in lower part in each segmentation column part is greater than the top in each segmentation column part
Divide certain threshold value, is denoted as -1.
2. the method as described in claim 1, which is characterized in that the grayscale image in the yin-yang character features region for obtaining bank note
Picture, comprising:
Obtain the gray level image of entire paper coin；
The gray level image in region of the interception comprising yin-yang character features from the gray level image of the entire paper coin.
3. the method as described in claim 1, which is characterized in that the gray level image to yin-yang character features region into
Row binary conversion treatment generates binary image, comprising:
According to the gray level image in yin-yang character features region, the pixel gray level for meeting high brightness conditions is searched, as two
Value threshold value；
Binary conversion treatment is carried out according to gray level image of the binarization threshold to yin-yang character features region, generates two-value
Change image.
4. method as claimed in claim 3, which is characterized in that the grayscale image according to yin-yang character features region
Picture searches the pixel gray level for meeting high brightness conditions, as binarization threshold, comprising:
The quantity of pixel in yin-yang character features region is counted according to tonal gradation；
According to the sequence of tonal gradation from small to large, the pixel quantity of each tonal gradation is added up；
If cumulative quantitative value reaches the high brightness conditions quantitative proportion of setting, it is determined that the pixel institute being currently added to is right
The gray value answered is the binarization threshold.
5. a kind of identification device of bank note characterized by comprising
Obtain module, the gray level image in the yin-yang character features region for obtaining bank note；
Processing module carries out binary conversion treatment for the gray level image to yin-yang character features region, generates binary picture
Picture；
Extraction module, for extracting the pattern characteristics in yin-yang character features region according to the binary image；
Identification module, for identifying the bank note according to the pattern characteristics and setting identification condition；
The extraction module is specifically used for:
The pattern precise boundary that yin-yang character features region is determined according to the binary image, it is special as the pattern
Sign；
The extraction module is specifically used for:
According to the binary image, the number of black pixel in every row is calculated, determines there is continuously setting for most black pixels
Determine up-and-down boundary of the position of line number as yin-yang character pattern；
The number of black pixel in each column is calculated, determines the position that there is the continuous setting columns of most black pixels as yin-yang
The right boundary of character pattern；
Region between up-and-down boundary is bisected into upper and bottom section；
Calculate separately the upper and bottom section column and；
The region between right boundary is split according to preset interval, forms segmentation column part；
Calculate the pixel number of respective upper and bottom section in each segmentation column part；
If the black pixel number in upper part in each segmentation column part is greater than the lower part in each segmentation column part
Divide certain threshold value, is denoted as 1；
If the black pixel number in lower part in each segmentation column part is greater than the top in each segmentation column part
Divide certain threshold value, is denoted as -1.
6. device as claimed in claim 5, which is characterized in that the acquisition module is specifically used for:
Obtain the gray level image of entire paper coin；
The gray level image in region of the interception comprising yin-yang character features from the gray level image of the entire paper coin.
7. device as claimed in claim 5, which is characterized in that the processing module includes:
Threshold value determination unit, for the gray level image according to yin-yang character features region, lookup meets high brightness conditions
Pixel gray level, as binarization threshold；
Image generation unit, for carrying out two according to gray level image of the binarization threshold to yin-yang character features region
Value processing, generates binary image.
8. device as claimed in claim 7, which is characterized in that described image generation unit is specifically used for:
The quantity of pixel in yin-yang character features region is counted according to tonal gradation；
According to the sequence of tonal gradation from small to large, the pixel quantity of each tonal gradation is added up；
If cumulative quantitative value reaches the high brightness conditions quantitative proportion of setting, it is determined that the pixel institute being currently added to is right
The gray value answered is the binarization threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610733157.4A CN106340116B (en) | 2016-08-26 | 2016-08-26 | A kind of recognition methods of bank note and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610733157.4A CN106340116B (en) | 2016-08-26 | 2016-08-26 | A kind of recognition methods of bank note and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106340116A CN106340116A (en) | 2017-01-18 |
| CN106340116B true CN106340116B (en) | 2019-06-07 |
Family
ID=57823042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610733157.4A Expired - Fee Related CN106340116B (en) | 2016-08-26 | 2016-08-26 | A kind of recognition methods of bank note and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106340116B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106952391B (en) * | 2017-02-27 | 2019-06-07 | 深圳怡化电脑股份有限公司 | One kind being stained Paper Currency Identification and device |
| CN107665538B (en) * | 2017-09-28 | 2020-08-18 | 深圳怡化电脑股份有限公司 | Paper currency classification method, device and equipment and readable storage medium |
| CN111353485B (en) * | 2018-12-20 | 2023-09-05 | 中国移动通信集团辽宁有限公司 | Seal identification method, device, equipment and medium |
| CN115147977B (en) * | 2021-03-30 | 2023-12-22 | 深圳怡化电脑股份有限公司 | Paper money discriminating method, paper money discriminating device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069900A (en) * | 2015-08-14 | 2015-11-18 | 深圳怡化电脑股份有限公司 | Method and device for processing banknote information |
| 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 |
| CN105761351A (en) * | 2016-01-08 | 2016-07-13 | 东方通信股份有限公司 | Structure characteristic-based character recognition method |
-
2016
- 2016-08-26 CN CN201610733157.4A patent/CN106340116B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069900A (en) * | 2015-08-14 | 2015-11-18 | 深圳怡化电脑股份有限公司 | Method and device for processing banknote information |
| 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 |
| CN105761351A (en) * | 2016-01-08 | 2016-07-13 | 东方通信股份有限公司 | Structure characteristic-based character recognition method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106340116A (en) | 2017-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106056751B (en) | The recognition methods and system of serial number | |
| CN111401372B (en) | Method for extracting and identifying image-text information of scanned document | |
| CN106340116B (en) | A kind of recognition methods of bank note and device | |
| CN104298982B (en) | A kind of character recognition method and device | |
| CN104091388B (en) | A kind of paper money discrimination method based on magnetic image and device | |
| CN101122953B (en) | Picture words segmentation method | |
| Agasti et al. | Fake currency detection using image processing | |
| CN104239850B (en) | Answer card filling information automatic recognition method based on image synthesis feature | |
| CN104036290A (en) | Method and device for identifying face value of paper money | |
| US11836969B2 (en) | Preprocessing images for OCR using character pixel height estimation and cycle generative adversarial networks for better character recognition | |
| CN104298989A (en) | Counterfeit identifying method and counterfeit identifying system based on zebra crossing infrared image characteristics | |
| CN101615252A (en) | A kind of method for extracting text information from adaptive images | |
| CN106803091B (en) | Method and system for identifying currency value of paper money | |
| Sawant et al. | Currency recognition using image processing and minimum distance classifier technique | |
| Sharan et al. | Detection of counterfeit Indian currency note using image processing | |
| CN104537364A (en) | Dollar bill denomination and edition identifying method based on texture analysis | |
| Agarwal et al. | An efficient algorithm for automatic car plate detection & recognition | |
| CN107742357A (en) | A kind of recognition methods of paper money number and device | |
| CN106447904B (en) | Method and device for identifying paper money | |
| CN104077562B (en) | A kind of scanning direction determination methods of test paper | |
| CN110414505A (en) | Processing method, processing system and the computer readable storage medium of image | |
| CN107527423B (en) | Paper money anti-counterfeiting identification method and paper money identification device | |
| KR102167433B1 (en) | Apparatus for automatic character generation based on multi-pattern character image recognition and method thereof | |
| Van Beusekom et al. | Automatic counterfeit protection system code classification | |
| KR102094234B1 (en) | Serial number recognition Apparatus and method for paper money |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190607 Termination date: 20210826 |