CN106780963A - Paper Currency Identification and device - Google Patents
Paper Currency Identification and device Download PDFInfo
- Publication number
- CN106780963A CN106780963A CN201611089483.2A CN201611089483A CN106780963A CN 106780963 A CN106780963 A CN 106780963A CN 201611089483 A CN201611089483 A CN 201611089483A CN 106780963 A CN106780963 A CN 106780963A
- Authority
- CN
- China
- Prior art keywords
- characteristic area
- row
- row coordinate
- coordinate
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D7/20—Testing patterns thereon
- G07D7/2016—Testing patterns thereon using feature extraction, e.g. segmentation, edge detection or Hough-transformation
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a kind of Paper Currency Identification and device.The method includes:Upper and lower two groups of characteristic areas are chosen in the front gray level image of bank note, characteristic area described in every group is constituted by left characteristic area and right characteristic area;Respectively feature pixel is searched in the left characteristic area and right characteristic area;According to the lookup result, Regional Representative's row coordinate of the left characteristic area and right characteristic area is determined respectively;According to Regional Representative's row coordinate, the signature identification of the upper group of characteristic area and the following group characteristic area is determined respectively;According to the signature identification, the currency type of the bank note is recognized.The embodiment of the present invention solves three kinds of low-denominations Iran's coin of adjoining dimensions when small areas occur and being stained, and can there is a problem of that currency type identification is inaccurate using existing Paper Currency Identification, realizes the effect of the currency type recognition accuracy for improving low-denomination Iran coin.
Description
Technical field
The present embodiments relate to image processing techniques, more particularly to a kind of Paper Currency Identification and device.
Background technology
In the daily life of Iran, the less Iranian coin circulation of denomination is maximum.At present, the less Iranian coin of denomination includes
20000 riyals, 50,000 riyals and 100,000 riyals.And above-mentioned three kinds of low-denominations Iran coin is very nearly the same in Paper Money Size,
Therefore, the low-denomination Iran coin of adjoining dimensions how is accurately identified, is just particularly important.
Gray level image of the prior art generally first to bank note carries out region interception, then area image again to being intercepted
Binary conversion treatment is carried out, to recognize the currency type of bank note.However, when above-mentioned three kinds of low-denominations Iran coin occurs what small areas were stained
During situation, will there is a problem of that the currency type identification of low-denomination Iran coin is inaccurate using existing Paper Currency Identification.
The content of the invention
The embodiment of the present invention provides a kind of Paper Currency Identification and device, to realize that the currency type for improving low-denomination Iran coin is known
The purpose of other accuracy rate.
In a first aspect, a kind of Paper Currency Identification is the embodiment of the invention provides, including:
Upper and lower two groups of characteristic areas are chosen in the front gray level image of bank note, characteristic area is by left feature described in every group
Region and right characteristic area are constituted;
Respectively feature pixel is searched in the left characteristic area and right characteristic area;
According to the lookup result, Regional Representative's row coordinate of the left characteristic area and right characteristic area is determined respectively;
According to Regional Representative's row coordinate, the spy of the upper group of characteristic area and the following group characteristic area is determined respectively
Levy mark;
According to the signature identification, the currency type of the bank note is recognized.
Further, it is described that upper and lower two groups of characteristic areas, feature described in every group are chosen in the front gray level image of bank note
Region is constituted by left characteristic area and right characteristic area, including:
For the left characteristic area of the upper group of characteristic area, the row coordinate of starting row is 300, and the row coordinate of initial row is
20, region a width of 200, and region it is high=ImageHeight*0.5-20, the ImageHeight represents the front gray scale
The height of image;
For the right characteristic area of the upper group of characteristic area, the row coordinate of starting row is 600, and the row coordinate of initial row is
20, region a width of 200, and region it is high=ImageHeight*0.5-20, the ImageHeight represents the front gray scale
The height of image;
For the left characteristic area of the following group characteristic area, the row coordinate of starting row is 300, the row coordinate of initial row=
ImageHeight*0.5-20, region a width of 200, and region be high=ImageHeight*0.5-20, the ImageHeight
Represent the height of the front gray level image;
For the right characteristic area of the following group characteristic area, the row coordinate of starting row is 600, the row coordinate of initial row=
ImageHeight*0.5-20, region a width of 200, and region be high=ImageHeight*0.5-20, the ImageHeight
Represent the height of the front gray level image.
Further, it is described to search feature pixel in the left characteristic area and right characteristic area respectively, including:
In organizing the left characteristic area or right characteristic area of characteristic area on described, for each column gray level image, from upper
Under, feature pixel is searched, the feature pixel meets condition:The preceding first predetermined number pixel of the feature pixel
The difference of the gray average of point and the gray average of rear first predetermined number pixel is more than 30, and rear first predetermined number
The gray average of individual pixel is less than 100;
In the left characteristic area or right characteristic area of the following group characteristic area, for each column gray level image, from lower and
On, feature pixel is searched, the feature pixel meets condition:The preceding first predetermined number pixel of the feature pixel
The difference of the gray average of point and the gray average of rear first predetermined number pixel is more than 30, and rear first predetermined number
The gray average of individual pixel is less than 100.
Further, according to the lookup result, the region generation of the left characteristic area and right characteristic area is determined respectively
Table row coordinate, including:
If finding the feature pixel, using the row coordinate of the feature pixel as row coordinate is represented, if not
The feature pixel is found, then when the row coordinate that represents of prostatitis gray level image is 0;
The number of row coordinate is represented described in statistics identical, occurrence number is designated as, and the identical is represented into row coordinate
Normalizing;
The row coordinate that represents after by normalizing sorts according to ascending order, the representative row after each described normalizing
Coordinate pair answers an occurrence number;
In units of the second predetermined number, towards the gradually big direction of the representative row coordinate after the sequence, the appearance is found
The summation of number of times is more than occurrence number described in first group of the first given threshold;
In representative row coordinate after the corresponding sequence of the first group of occurrence number, the maximum representative row is sat
It is denoted as the Regional Representative's row coordinate for the corresponding left characteristic area or right characteristic area;
If the number of the feature pixel for finding is less than the second given threshold, by the left characteristic area or the right side
Regional Representative's row setting coordinate of characteristic area is 0.
Further, according to Regional Representative's row coordinate, determine that the upper group of characteristic area and the following group are special respectively
The signature identification in region is levied, including:
In organizing characteristic area on described, if Regional Representative's row coordinate of the left characteristic area and/or the right side
Regional Representative's row coordinate of characteristic area is equal to 0, it is determined that the signature identification of the upper group of characteristic area is 0;
In organizing characteristic area on described, if Regional Representative's row coordinate of the left characteristic area and the right feature
Regional Representative's row coordinate in region is not equal to 0 and difference between the two meets pre-conditioned, it is determined that described upper group
The signature identification of characteristic area is 1, and otherwise, the signature identification of the upper group of characteristic area is 0, described pre-conditioned to be:It is described
Difference between Regional Representative's row coordinate of left characteristic area and Regional Representative's row coordinate of the right characteristic area
Less than 10;
In the following group characteristic area, if Regional Representative's row coordinate of the left characteristic area and/or the right side
Regional Representative's row coordinate of characteristic area is equal to 0, it is determined that the signature identification of the following group characteristic area is 0;
In the following group characteristic area, if Regional Representative's row coordinate of the left characteristic area and the right feature
Regional Representative's row coordinate in region is not equal to 0 and difference between the two meets pre-conditioned, it is determined that the following group
The signature identification of characteristic area is 1, and otherwise, the signature identification of the following group characteristic area is 0, described pre-conditioned to be:It is described
Difference between Regional Representative's row coordinate of left characteristic area and Regional Representative's row coordinate of the right characteristic area
Less than 10.
Further, according to the signature identification, the currency type of the bank note is recognized, including:
The signature identification is compared with the signature identification for prestoring, to recognize the currency type of the bank note.
Second aspect, the embodiment of the present invention additionally provides a kind of paper money identifier, and the paper money identifier includes:
Module is chosen, for choosing upper and lower two groups of characteristic areas, feature described in every group in the front gray level image of bank note
Region is constituted by left characteristic area and right characteristic area;
Searching modul, for searching feature pixel in the left characteristic area and right characteristic area respectively;
First determining module, for according to the lookup result, the left characteristic area and right characteristic area being determined respectively
Regional Representative's row coordinate;
Second determining module, for according to Regional Representative's row coordinate, determining the upper group of characteristic area and institute respectively
State the signature identification of the following group characteristic area;
Identification module, for according to the signature identification, recognizing the currency type of the bank note.
Further, the selection module includes:
First chooses unit, and for the left characteristic area for the upper group of characteristic area, the row coordinate of starting row is
300, the row coordinate of initial row is 20, region a width of 200, and region it is high=ImageHeight*0.5-20, it is described
ImageHeight represents the height of the front gray level image;
Second chooses unit, and for the right characteristic area for the upper group of characteristic area, the row coordinate of starting row is
600, the row coordinate of initial row is 20, region a width of 200, and region it is high=ImageHeight*0.5-20, it is described
ImageHeight represents the height of the front gray level image;
3rd chooses unit, and for the left characteristic area for the following group characteristic area, the row coordinate of starting row is
300, the row coordinate=ImageHeight*0.5-20 of initial row, region a width of 200, and region be high=ImageHeight*
0.5-20, the ImageHeight represent the height of the front gray level image;
4th chooses unit, and for the right characteristic area for the following group characteristic area, the row coordinate of starting row is
600, the row coordinate=ImageHeight*0.5-20 of initial row, region a width of 200, and region be high=ImageHeight*
0.5-20, the ImageHeight represent the height of the front gray level image.
Further, the searching modul includes:
First searching unit, in left characteristic area or right characteristic area that characteristic area is organized on described, for every
Row gray level image, from top to bottom, searches feature pixel, and the feature pixel meets condition:Before the feature pixel
The difference of the gray average of the gray average of the first predetermined number pixel and rear first predetermined number pixel be more than 30, and
The gray average of the first predetermined number pixel is less than 100 after described;
Second searching unit, in the left characteristic area or right characteristic area of the following group characteristic area, for every
Row gray level image, from bottom to top, searches feature pixel, and the feature pixel meets condition:Before the feature pixel
The difference of the gray average of the gray average of the first predetermined number pixel and rear first predetermined number pixel be more than 30, and
The gray average of the first predetermined number pixel is less than 100 after described.
Further, first determining module includes:
First determining unit, if for finding the feature pixel, the row coordinate of the feature pixel is made
To represent row coordinate, if not finding the feature pixel, when the row coordinate that represents of prostatitis gray level image is 0;
Statistics normalizing unit, the number of row coordinate is represented for counting described in identical, be designated as occurrence number, and will be described
Identical represents row Unitary coordinate;
Sequencing unit, sorts for the row coordinate that represents after by normalizing according to ascending order, described in each
Representative row coordinate pair after normalizing answers an occurrence number;
Unit is found, in units of the second predetermined number, towards the gradually big direction of the representative row coordinate after the sequence,
The summation of the occurrence number is found more than occurrence number described in first group of the first given threshold;
Second determining unit, in the representative row coordinate after the corresponding sequence of the first group of occurrence number, inciting somebody to action
The maximum row coordinate that represents is used as the corresponding left characteristic area or Regional Representative's row coordinate of right characteristic area;
Setup unit, if the number of the feature pixel for finding is less than the second given threshold, will be described
Regional Representative's row setting coordinate of left characteristic area or right characteristic area is 0.
Further, second determining module includes:
3rd determining unit, for organizing characteristic area on described in, if the Regional Representative of the left characteristic area
Regional Representative's row coordinate of row coordinate and/or the right characteristic area is equal to 0, it is determined that the spy of the upper group of characteristic area
Levy and be designated 0;
4th determining unit, for organizing characteristic area on described in, if the Regional Representative of the left characteristic area
Row coordinate and Regional Representative's row coordinate of the right characteristic area are not equal to 0 and difference between the two meets default bar
Part, it is determined that the signature identification of the upper group of characteristic area is 1, otherwise, the signature identification of the upper group of characteristic area is 0, institute
State and pre-conditioned be:Regional Representative's row coordinate of the left characteristic area and the Regional Representative of the right characteristic area
Difference between row coordinate is less than 10;
5th determining unit, in the following group characteristic area, if the Regional Representative of the left characteristic area
Regional Representative's row coordinate of row coordinate and/or the right characteristic area is equal to 0, it is determined that the spy of the following group characteristic area
Levy and be designated 0;
6th determining unit, in the following group characteristic area, if the Regional Representative of the left characteristic area
Row coordinate and Regional Representative's row coordinate of the right characteristic area are not equal to 0 and difference between the two meets default bar
Part, it is determined that the signature identification of the following group characteristic area is 1, otherwise, the signature identification of the following group characteristic area is 0, institute
State and pre-conditioned be:Regional Representative's row coordinate of the left characteristic area and the Regional Representative of the right characteristic area
Difference between row coordinate is less than 10.
Further, the identification module includes:
Compare recognition unit, for the signature identification to be compared with the signature identification for prestoring, to recognize the paper
The currency type of coin.
The embodiment of the present invention is then true respectively by choosing upper and lower two groups of characteristic areas in the front gray level image of bank note
The signature identification of the fixed upper group of characteristic area and the following group characteristic area, and then according to the signature identification, identification is described
The currency type of bank note, solves three kinds of low-denominations Iran's coin of adjoining dimensions when small areas occur and being stained, using existing bank note
Recognition methods can have that currency type identification is inaccurate, realize the effect of the currency type recognition accuracy for improving low-denomination Iran coin
Really.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the Paper Currency Identification in the embodiment of the present invention one;
Fig. 2 is a kind of structure chart of the paper money identifier in the embodiment of the present invention two.
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 limitation of the invention.It also should be noted that, in order to just
Part rather than entire infrastructure related to the present invention is illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is a kind of flow chart of Paper Currency Identification that the embodiment of the present invention one is provided, and the present embodiment is applicable to need
Will be to three kinds of Iranian coin of low-denomination:20000 riyals, 50,000 riyals and 100,000 riyals carry out the situation of currency type identification, the party
Method can be performed by paper money identifier, and wherein the device can realize that the device can be integrated in and test by software and/or hardware
In paper money device.With reference to Fig. 1, the Paper Currency Identification that the present embodiment is provided specifically may include steps of:
S110, upper and lower two groups of characteristic areas are chosen in the front gray level image of bank note, characteristic area described in every group by
Left characteristic area and right characteristic area are constituted.
Specifically, the front gray level image of bank note can be obtained first with sensor, then in the front gray scale of the bank note
Characteristic area and the following group characteristic area are organized on being chosen in image;Characteristic area is by left characteristic area and You Te described in described every group
Region composition is levied, that is, represents that the upper group of characteristic area is made up of left characteristic area and right characteristic area, the following group characteristic area
Domain is also made up of left characteristic area and right characteristic area.
Optionally, it is described that upper and lower two groups of characteristic areas, characteristic area described in every group are chosen in the front gray level image of bank note
Domain is constituted by left characteristic area and right characteristic area, including:
For the left characteristic area of the upper group of characteristic area, the row coordinate of starting row is 300, and the row coordinate of initial row is
20, region a width of 200, and region it is high=ImageHeight*0.5-20, the ImageHeight represents the front gray scale
The height of image;
For the right characteristic area of the upper group of characteristic area, the row coordinate of starting row is 600, and the row coordinate of initial row is
20, region a width of 200, and region it is high=ImageHeight*0.5-20, the ImageHeight represents the front gray scale
The height of image;
For the left characteristic area of the following group characteristic area, the row coordinate of starting row is 300, the row coordinate of initial row=
ImageHeight*0.5-20, region a width of 200, and region be high=ImageHeight*0.5-20, the ImageHeight
Represent the height of the front gray level image;
For the right characteristic area of the following group characteristic area, the row coordinate of starting row is 600, the row coordinate of initial row=
ImageHeight*0.5-20, region a width of 200, and region be high=ImageHeight*0.5-20, the ImageHeight
Represent the height of the front gray level image.
For example, with the left upper apex of bank note front gray level image as the origin of coordinates (0,0), when the front gray-scale map
During the height ImageHeight=500 of picture,
For the left characteristic area of the upper group of characteristic area, the row coordinate of starting row is 300, and the row coordinate of initial row is
20, region a width of 200, and region it is high=230;
For the right characteristic area of the upper group of characteristic area, the row coordinate of starting row is 600, and the row coordinate of initial row is
20, region a width of 200, and region it is high=230;
For the left characteristic area of the following group characteristic area, the row coordinate of starting row is 300, and the row coordinate of initial row is
230, region a width of 200, and region it is high=230;
For the right characteristic area of the following group characteristic area, the row coordinate of starting row is 600, and the row coordinate of initial row is
230, region a width of 200, and region it is high=230.
S120, in the left characteristic area and right characteristic area search feature pixel respectively.
Optionally, it is described to search feature pixel in the left characteristic area and right characteristic area respectively, including:
In organizing the left characteristic area or right characteristic area of characteristic area on described, for each column gray level image, from upper
Under, feature pixel is searched, the feature pixel meets condition:The preceding first predetermined number pixel of the feature pixel
The difference of the gray average of point and the gray average of rear first predetermined number pixel is more than 30, and rear first predetermined number
The gray average of individual pixel is less than 100;
In the left characteristic area or right characteristic area of the following group characteristic area, for each column gray level image, from lower and
On, feature pixel is searched, the feature pixel meets condition:The preceding first predetermined number pixel of the feature pixel
The difference of the gray average of point and the gray average of rear first predetermined number pixel is more than 30, and rear first predetermined number
The gray average of individual pixel is less than 100.
For example, when first predetermined number=20,
In organizing the left characteristic area or right characteristic area of characteristic area on described, for each column gray level image, from upper
Under, feature pixel is searched, the feature pixel meets condition:The gray scale of preceding 20 pixels of the feature pixel is equal
The difference of the gray average of value and rear 20 pixels is more than 30, and rear 20 gray averages of pixel are less than 100;
In the left characteristic area or right characteristic area of the following group characteristic area, for each column gray level image, from lower and
On, feature pixel is searched, the feature pixel meets condition:The gray scale of preceding 20 pixels of the feature pixel is equal
The difference of the gray average of value and rear 20 pixels is more than 30, and rear 20 gray averages of pixel are less than 100.
S130, according to the lookup result, Regional Representative's row of the left characteristic area and right characteristic area is determined respectively
Coordinate.
Optionally, according to the lookup result, the Regional Representative of the left characteristic area and right characteristic area is determined respectively
Row coordinate, including:
If finding the feature pixel, using the row coordinate of the feature pixel as row coordinate is represented, if not
The feature pixel is found, then when the row coordinate that represents of prostatitis gray level image is 0;
The number of row coordinate is represented described in statistics identical, occurrence number is designated as, and the identical is represented into row coordinate
Normalizing;
The row coordinate that represents after by normalizing sorts according to ascending order, the representative row after each described normalizing
Coordinate pair answers an occurrence number, for example, the value for representing the correspondence occurrence number of row coordinate 33 is 0, represents row coordinate
The value of the 34 correspondence occurrence numbers is 13, and the value for representing the correspondence occurrence number of row coordinate 35 is 10, represents row coordinate 36
The value of the correspondence occurrence number is 24, and the value for representing the correspondence occurrence number of row coordinate 37 is 54;
In units of the second predetermined number, towards the gradually big direction of the representative row coordinate after the sequence, the appearance is found
The summation of number of times is more than occurrence number described in first group of the first given threshold, for example, work as second predetermined number=5, it is described
When first given threshold is 100, i.e., in units of 5, towards the gradually big direction of the representative row coordinate after the sequence, find described
Occurrence number described in first group of the summation of occurrence number more than 100;
In representative row coordinate after the corresponding sequence of the first group of occurrence number, the maximum representative row is sat
The Regional Representative's row coordinate for the corresponding left characteristic area or right characteristic area is denoted as, if for example, the first group of occurrence number
Value be respectively above-mentioned 0,13,10,24,54, then the representative row coordinate after the corresponding sequence of the first group of occurrence number
In, the maximum row coordinate 37 that represents is sat as Regional Representative's row of the corresponding left characteristic area or right characteristic area
Mark;
If the number of the feature pixel for finding is less than the second given threshold, by the left characteristic area or the right side
Regional Representative's row setting coordinate of characteristic area is 0.For example, second given threshold can be 10.
S140, according to Regional Representative's row coordinate, the upper group of characteristic area and the following group characteristic area are determined respectively
The signature identification in domain.
Optionally, according to Regional Representative's row coordinate, the upper group of characteristic area and the following group feature are determined respectively
The signature identification in region, including:
In organizing characteristic area on described, if Regional Representative's row coordinate of the left characteristic area and/or the right side
Regional Representative's row coordinate of characteristic area is equal to 0, it is determined that the signature identification of the upper group of characteristic area is 0;
In organizing characteristic area on described, if Regional Representative's row coordinate of the left characteristic area and the right feature
Regional Representative's row coordinate in region is not equal to 0 and difference between the two meets pre-conditioned, it is determined that described upper group
The signature identification of characteristic area is 1, and otherwise, the signature identification of the upper group of characteristic area is 0, described pre-conditioned to be:It is described
Difference between Regional Representative's row coordinate of left characteristic area and Regional Representative's row coordinate of the right characteristic area
Less than 10;
In the following group characteristic area, if Regional Representative's row coordinate of the left characteristic area and/or the right side
Regional Representative's row coordinate of characteristic area is equal to 0, it is determined that the signature identification of the following group characteristic area is 0;
In the following group characteristic area, if Regional Representative's row coordinate of the left characteristic area and the right feature
Regional Representative's row coordinate in region is not equal to 0 and difference between the two meets pre-conditioned, it is determined that the following group
The signature identification of characteristic area is 1, and otherwise, the signature identification of the following group characteristic area is 0, described pre-conditioned to be:It is described
Difference between Regional Representative's row coordinate of left characteristic area and Regional Representative's row coordinate of the right characteristic area
Less than 10.
S150, according to the signature identification, recognize the currency type of the bank note.
Optionally, according to the signature identification, the currency type of the bank note is recognized, including:
The signature identification is compared with the signature identification for prestoring, to recognize the currency type of the bank note.
For example, for 20,000 riyals, the signature identification that prestores is:The upper group of signature identification of characteristic area is 0, under
The signature identification of group characteristic area is 0;For 50,000 riyals, the signature identification that prestores is:The upper group of feature of characteristic area
1 is designated, the signature identification of the following group characteristic area is 1;For 100,000 riyals, the signature identification that prestores is:Upper group special
It is 0 to levy the signature identification in region, and the signature identification of the following group characteristic area is 1.The signature identification that will be determined according to S140 with it is pre-
The signature identification deposited is compared, in just can identifying that examined banknote is 20,000 riyals, 50,000 riyals and 100,000 riyals
Any banknote.
The technical scheme of the present embodiment by choosing upper and lower two groups of characteristic areas in the front gray level image of bank note, then
The signature identification of the upper group of characteristic area and the following group characteristic area is determined respectively, and then according to the signature identification, is known
The currency type of not described bank note, solves three kinds of low-denominations Iran's coin of adjoining dimensions when small areas occur and being stained, using existing
Having Paper Currency Identification can have that currency type identification is inaccurate, and the currency type identification for realizing raising low-denomination Iran coin is accurate
The effect of rate.
Embodiment two
Fig. 2 is a kind of structure chart of the paper money identifier in the embodiment of the present invention two, and the present embodiment is applicable to needs
To three kinds of Iranian coin of low-denomination:20000 riyals, 50,000 riyals and 100,000 riyals carry out the situation of currency type identification.With reference to figure
2, the structure of the paper money identifier that the present embodiment is provided specifically can be as follows:
Module 210 is chosen, it is special described in every group for choosing upper and lower two groups of characteristic areas in the front gray level image of bank note
Region is levied to be constituted by left characteristic area and right characteristic area;
Searching modul 220, for searching feature pixel in the left characteristic area and right characteristic area respectively;
First determining module 230, for according to the lookup result, the left characteristic area and right characteristic area being determined respectively
Regional Representative's row coordinate in domain;
Second determining module 240, for according to Regional Representative's row coordinate, determine respectively the upper group of characteristic area and
The signature identification of the following group characteristic area;
Identification module 250, for according to the signature identification, recognizing the currency type of the bank note.
Optionally, the selection module includes:
First chooses unit, and for the left characteristic area for the upper group of characteristic area, the row coordinate of starting row is
300, the row coordinate of initial row is 20, region a width of 200, and region it is high=ImageHeight*0.5-20, it is described
ImageHeight represents the height of the front gray level image;
Second chooses unit, and for the right characteristic area for the upper group of characteristic area, the row coordinate of starting row is
600, the row coordinate of initial row is 20, region a width of 200, and region it is high=ImageHeight*0.5-20, it is described
ImageHeight represents the height of the front gray level image;
3rd chooses unit, and for the left characteristic area for the following group characteristic area, the row coordinate of starting row is
300, the row coordinate=ImageHeight*0.5-20 of initial row, region a width of 200, and region be high=ImageHeight*
0.5-20, the ImageHeight represent the height of the front gray level image;
4th chooses unit, and for the right characteristic area for the following group characteristic area, the row coordinate of starting row is
600, the row coordinate=ImageHeight*0.5-20 of initial row, region a width of 200, and region be high=ImageHeight*
0.5-20, the ImageHeight represent the height of the front gray level image.
Optionally, the searching modul includes:
First searching unit, in left characteristic area or right characteristic area that characteristic area is organized on described, for every
Row gray level image, from top to bottom, searches feature pixel, and the feature pixel meets condition:Before the feature pixel
The difference of the gray average of the gray average of the first predetermined number pixel and rear first predetermined number pixel be more than 30, and
The gray average of the first predetermined number pixel is less than 100 after described;
Second searching unit, in the left characteristic area or right characteristic area of the following group characteristic area, for every
Row gray level image, from bottom to top, searches feature pixel, and the feature pixel meets condition:Before the feature pixel
The difference of the gray average of the gray average of the first predetermined number pixel and rear first predetermined number pixel be more than 30, and
The gray average of the first predetermined number pixel is less than 100 after described.
Optionally, first determining module includes:
First determining unit, if for finding the feature pixel, the row coordinate of the feature pixel is made
To represent row coordinate, if not finding the feature pixel, when the row coordinate that represents of prostatitis gray level image is 0;
Statistics normalizing unit, the number of row coordinate is represented for counting described in identical, be designated as occurrence number, and will be described
Identical represents row Unitary coordinate;
Sequencing unit, sorts for the row coordinate that represents after by normalizing according to ascending order, described in each
Representative row coordinate pair after normalizing answers an occurrence number;
Unit is found, in units of the second predetermined number, towards the gradually big direction of the representative row coordinate after the sequence,
The summation of the occurrence number is found more than occurrence number described in first group of the first given threshold;
Second determining unit, in the representative row coordinate after the corresponding sequence of the first group of occurrence number, inciting somebody to action
The maximum row coordinate that represents is used as the corresponding left characteristic area or Regional Representative's row coordinate of right characteristic area;
Setup unit, if the number of the feature pixel for finding is less than the second given threshold, will be described
Regional Representative's row setting coordinate of left characteristic area or right characteristic area is 0.
Optionally, second determining module includes:
3rd determining unit, for organizing characteristic area on described in, if the Regional Representative of the left characteristic area
Regional Representative's row coordinate of row coordinate and/or the right characteristic area is equal to 0, it is determined that the spy of the upper group of characteristic area
Levy and be designated 0;
4th determining unit, for organizing characteristic area on described in, if the Regional Representative of the left characteristic area
Row coordinate and Regional Representative's row coordinate of the right characteristic area are not equal to 0 and difference between the two meets default bar
Part, it is determined that the signature identification of the upper group of characteristic area is 1, otherwise, the signature identification of the upper group of characteristic area is 0, institute
State and pre-conditioned be:Regional Representative's row coordinate of the left characteristic area and the Regional Representative of the right characteristic area
Difference between row coordinate is less than 10;
5th determining unit, in the following group characteristic area, if the Regional Representative of the left characteristic area
Regional Representative's row coordinate of row coordinate and/or the right characteristic area is equal to 0, it is determined that the spy of the following group characteristic area
Levy and be designated 0;
6th determining unit, in the following group characteristic area, if the Regional Representative of the left characteristic area
Row coordinate and Regional Representative's row coordinate of the right characteristic area are not equal to 0 and difference between the two meets default bar
Part, it is determined that the signature identification of the following group characteristic area is 1, otherwise, the signature identification of the following group characteristic area is 0, institute
State and pre-conditioned be:Regional Representative's row coordinate of the left characteristic area and the Regional Representative of the right characteristic area
Difference between row coordinate is less than 10.
Optionally, the identification module includes:
Compare recognition unit, for the signature identification to be compared with the signature identification for prestoring, to recognize the paper
The currency type of coin.
The paper money identifier that the present embodiment is provided, the Paper Currency Identification provided with any embodiment of the present invention belongs to
Same inventive concept, can perform the Paper Currency Identification that any embodiment of the present invention is provided, and possess execution Paper Currency Identification
Corresponding functional module and beneficial effect.Not ins and outs of detailed description in the present embodiment, reference can be made to the present invention is any real
The Paper Currency Identification of example offer is provided.
Note, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although the present invention is carried out 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
More other Equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (12)
1. a kind of Paper Currency Identification, it is characterised in that including:
Upper and lower two groups of characteristic areas are chosen in the front gray level image of bank note, characteristic area is by left characteristic area described in every group
Constituted with right characteristic area;
Respectively feature pixel is searched in the left characteristic area and right characteristic area;
According to the lookup result, Regional Representative's row coordinate of the left characteristic area and right characteristic area is determined respectively;
According to Regional Representative's row coordinate, the feature mark of the upper group of characteristic area and the following group characteristic area is determined respectively
Know;
According to the signature identification, the currency type of the bank note is recognized.
2. method according to claim 1, it is characterised in that described to choose upper and lower two in the front gray level image of bank note
Group characteristic area, characteristic area described in every group is constituted by left characteristic area and right characteristic area, including:
For the left characteristic area of the upper group of characteristic area, the row coordinate of starting row is 300, and the row coordinate of initial row is 20,
Region a width of 200, and region it is high=ImageHeight*0.5-20, the ImageHeight represents the front gray-scale map
The height of picture;
For the right characteristic area of the upper group of characteristic area, the row coordinate of starting row is 600, and the row coordinate of initial row is 20,
Region a width of 200, and region it is high=ImageHeight*0.5-20, the ImageHeight represents the front gray-scale map
The height of picture;
For the left characteristic area of the following group characteristic area, the row coordinate of starting row is 300, the row coordinate of initial row=
ImageHeight*0.5-20, region a width of 200, and region be high=ImageHeight*0.5-20, the ImageHeight
Represent the height of the front gray level image;
For the right characteristic area of the following group characteristic area, the row coordinate of starting row is 600, the row coordinate of initial row=
ImageHeight*0.5-20, region a width of 200, and region be high=ImageHeight*0.5-20, the ImageHeight
Represent the height of the front gray level image.
3. method according to claim 1, it is characterised in that described respectively in the left characteristic area and right characteristic area
Middle lookup feature pixel, including:
Organize on described in the left characteristic area or right characteristic area of characteristic area, for each column gray level image, from top to bottom, look into
Feature pixel, the feature pixel is looked for meet condition:The preceding first predetermined number pixel of the feature pixel
The difference of the gray average of gray average and rear first predetermined number pixel is more than 30, and the rear first predetermined number picture
The gray average of vegetarian refreshments is less than 100;
In the left characteristic area or right characteristic area of the following group characteristic area, for each column gray level image, from bottom to top, look into
Feature pixel, the feature pixel is looked for meet condition:The preceding first predetermined number pixel of the feature pixel
The difference of the gray average of gray average and rear first predetermined number pixel is more than 30, and the rear first predetermined number picture
The gray average of vegetarian refreshments is less than 100.
4. method according to claim 1, it is characterised in that according to the lookup result, the left feature is determined respectively
Region and Regional Representative's row coordinate of right characteristic area, including:
If finding the feature pixel, using the row coordinate of the feature pixel as row coordinate is represented, if not searching
To the feature pixel, then when the row coordinate that represents of prostatitis gray level image is 0;
The number of row coordinate is represented described in statistics identical, occurrence number is designated as, and the identical is represented into row Unitary coordinate;
The row coordinate that represents after by normalizing sorts according to ascending order, the representative row coordinate after each described normalizing
One occurrence number of correspondence;
In units of the second predetermined number, towards the gradually big direction of the representative row coordinate after the sequence, the occurrence number is found
Summation more than occurrence number described in first group of the first given threshold;After the corresponding sequence of the first group of occurrence number
Represent in row coordinate, described using maximum represents row coordinate as the corresponding left characteristic area or the region generation of right characteristic area
Table row coordinate;
If the number of the feature pixel for finding is less than the second given threshold, by the left characteristic area or right feature
Regional Representative's row setting coordinate in region is 0.
5. method according to claim 1, it is characterised in that according to Regional Representative's row coordinate, determine respectively described
The signature identification of upper group of characteristic area and the following group characteristic area, including:
In organizing characteristic area on described, if Regional Representative's row coordinate and/or the right feature of the left characteristic area
Regional Representative's row coordinate in region is equal to 0, it is determined that the signature identification of the upper group of characteristic area is 0;
In organizing characteristic area on described, if Regional Representative's row coordinate of the left characteristic area and the right characteristic area
Regional Representative's row coordinate be not equal to 0 and difference between the two meets pre-conditioned, it is determined that the upper group of feature
The signature identification in region is 1, and otherwise, the signature identification of the upper group of characteristic area is 0, described pre-conditioned to be:The left spy
The difference levied between Regional Representative's row coordinate in region and Regional Representative's row coordinate of the right characteristic area is less than
10;
In the following group characteristic area, if Regional Representative's row coordinate and/or the right feature of the left characteristic area
Regional Representative's row coordinate in region is equal to 0, it is determined that the signature identification of the following group characteristic area is 0;
In the following group characteristic area, if Regional Representative's row coordinate of the left characteristic area and the right characteristic area
Regional Representative's row coordinate be not equal to 0 and difference between the two meets pre-conditioned, it is determined that the following group feature
The signature identification in region is 1, and otherwise, the signature identification of the following group characteristic area is 0, described pre-conditioned to be:The left spy
The difference levied between Regional Representative's row coordinate in region and Regional Representative's row coordinate of the right characteristic area is less than
10。
6. method according to claim 1, it is characterised in that according to the signature identification, recognize the currency type of the bank note,
Including:
The signature identification is compared with the signature identification for prestoring, to recognize the currency type of the bank note.
7. a kind of paper money identifier, it is characterised in that including:
Module is chosen, for choosing upper and lower two groups of characteristic areas, characteristic area described in every group in the front gray level image of bank note
Constituted by left characteristic area and right characteristic area;
Searching modul, for searching feature pixel in the left characteristic area and right characteristic area respectively;
First determining module, for according to the lookup result, the area of the left characteristic area and right characteristic area being determined respectively
Domain represents row coordinate;
Second determining module, for according to Regional Representative's row coordinate, determine respectively the upper group of characteristic area and it is described under
The signature identification of group characteristic area;
Identification module, for according to the signature identification, recognizing the currency type of the bank note.
8. device according to claim 1, it is characterised in that the selection module includes:
First chooses unit, and for the left characteristic area for the upper group of characteristic area, the row coordinate of starting row is 300, is risen
The row coordinate for beginning be 20, region a width of 200, and region it is high=ImageHeight*0.5-20, the ImageHeight tables
Show the height of the front gray level image;
Second chooses unit, and for the right characteristic area for the upper group of characteristic area, the row coordinate of starting row is 600, is risen
The row coordinate for beginning be 20, region a width of 200, and region it is high=ImageHeight*0.5-20, the ImageHeight tables
Show the height of the front gray level image;
3rd chooses unit, and for the left characteristic area for the following group characteristic area, the row coordinate of starting row is 300, is risen
Row coordinate=the ImageHeight*0.5-20 for beginning, region a width of 200, and region be high=ImageHeight*0.5-20,
The ImageHeight represents the height of the front gray level image;
4th chooses unit, and for the right characteristic area for the following group characteristic area, the row coordinate of starting row is 600, is risen
Row coordinate=the ImageHeight*0.5-20 for beginning, region a width of 200, and region be high=ImageHeight*0.5-20,
The ImageHeight represents the height of the front gray level image.
9. device according to claim 1, it is characterised in that the searching modul includes:
First searching unit, in left characteristic area or right characteristic area that characteristic area is organized on described, for each column ash
Degree image, from top to bottom, searches feature pixel, and the feature pixel meets condition:Preceding the first of the feature pixel
The difference of the gray average of the gray average of predetermined number pixel and rear first predetermined number pixel is more than 30, and described
The gray average of the first predetermined number pixel is less than 100 afterwards;
Second searching unit, in the left characteristic area or right characteristic area of the following group characteristic area, for each column ash
Degree image, from bottom to top, searches feature pixel, and the feature pixel meets condition:Preceding the first of the feature pixel
The difference of the gray average of the gray average of predetermined number pixel and rear first predetermined number pixel is more than 30, and described
The gray average of the first predetermined number pixel is less than 100 afterwards.
10. device according to claim 1, it is characterised in that first determining module includes:
First determining unit, if for finding the feature pixel, using the row coordinate of the feature pixel as generation
Table row coordinate, if not finding the feature pixel, when the row coordinate that represents of prostatitis gray level image is 0;
Statistics normalizing unit, the number of row coordinate is represented for counting described in identical, be designated as occurrence number, and will be described identical
Representative row Unitary coordinate;
Sequencing unit, sorts for the row coordinate that represents after by normalizing according to ascending order, each described normalizing
Representative row coordinate pair afterwards answers an occurrence number;
Unit is found, in units of the second predetermined number, towards the gradually big direction of the representative row coordinate after the sequence, is found
The summation of the occurrence number is more than occurrence number described in first group of the first given threshold;
Second determining unit, for the representative row coordinate after the corresponding sequence of the first group of occurrence number in, by maximum
The row coordinate that represents as the corresponding left characteristic area or Regional Representative's row coordinate of right characteristic area;
Setup unit, if the number of the feature pixel for finding is less than the second given threshold, by the left spy
The Regional Representative's row setting coordinate for levying region or right characteristic area is 0.
11. devices according to claim 1, it is characterised in that second determining module includes:
3rd determining unit, for organizing characteristic area on described in, if Regional Representative's row of the left characteristic area is sat
Regional Representative's row coordinate of mark and/or the right characteristic area is equal to 0, it is determined that the feature mark of the upper group of characteristic area
Know is 0;
4th determining unit, for organizing characteristic area on described in, if Regional Representative's row of the left characteristic area is sat
Mark and be not equal to 0 with Regional Representative's row coordinate of the right characteristic area and difference between the two meets pre-conditioned,
Then determine that the signature identification of the upper group of characteristic area is 1, otherwise, the signature identification of the upper group of characteristic area is 0, described pre-
If condition is:Regional Representative's row coordinate of the left characteristic area is sat with Regional Representative's row of the right characteristic area
Difference between mark is less than 10;
5th determining unit, in the following group characteristic area, if Regional Representative's row of the left characteristic area is sat
Regional Representative's row coordinate of mark and/or the right characteristic area is equal to 0, it is determined that the feature mark of the following group characteristic area
Know is 0;
6th determining unit, in the following group characteristic area, if Regional Representative's row of the left characteristic area is sat
Mark and be not equal to 0 with Regional Representative's row coordinate of the right characteristic area and difference between the two meets pre-conditioned,
Then determine that the signature identification of the following group characteristic area is 1, otherwise, the signature identification of the following group characteristic area is 0, described pre-
If condition is:Regional Representative's row coordinate of the left characteristic area is sat with Regional Representative's row of the right characteristic area
Difference between mark is less than 10.
12. devices according to claim 1, it is characterised in that the identification module includes:
Compare recognition unit, for the signature identification to be compared with the signature identification for prestoring, to recognize the bank note
Currency type.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611089483.2A CN106780963B (en) | 2016-12-01 | 2016-12-01 | Paper Currency Identification and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611089483.2A CN106780963B (en) | 2016-12-01 | 2016-12-01 | Paper Currency Identification and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106780963A true CN106780963A (en) | 2017-05-31 |
CN106780963B CN106780963B (en) | 2019-08-27 |
Family
ID=58915461
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611089483.2A Expired - Fee Related CN106780963B (en) | 2016-12-01 | 2016-12-01 | Paper Currency Identification and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106780963B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001041899A (en) * | 1999-07-27 | 2001-02-16 | Toshiba Corp | Apparatus for discriminating contamination degree of paper sheet |
CN102034108A (en) * | 2010-12-06 | 2011-04-27 | 哈尔滨工业大学 | Multi-resolution network characteristic registration-based method for sorting face values and face directions of notes in sorter |
CN104036290A (en) * | 2014-06-11 | 2014-09-10 | 新达通科技股份有限公司 | Method and device for identifying face value of paper money |
CN104346858A (en) * | 2014-10-10 | 2015-02-11 | 新达通科技股份有限公司 | Paper currency face value identification method and device based on magnetic image |
CN104867225A (en) * | 2015-05-15 | 2015-08-26 | 深圳怡化电脑股份有限公司 | Banknote face orientation identification method and apparatus |
CN105139510A (en) * | 2015-08-25 | 2015-12-09 | 深圳怡化电脑股份有限公司 | Bank note identification method and system |
CN105654609A (en) * | 2015-12-29 | 2016-06-08 | 深圳怡化电脑股份有限公司 | Paper money processing method and paper money processing system |
-
2016
- 2016-12-01 CN CN201611089483.2A patent/CN106780963B/en not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001041899A (en) * | 1999-07-27 | 2001-02-16 | Toshiba Corp | Apparatus for discriminating contamination degree of paper sheet |
CN102034108A (en) * | 2010-12-06 | 2011-04-27 | 哈尔滨工业大学 | Multi-resolution network characteristic registration-based method for sorting face values and face directions of notes in sorter |
CN104036290A (en) * | 2014-06-11 | 2014-09-10 | 新达通科技股份有限公司 | Method and device for identifying face value of paper money |
CN104346858A (en) * | 2014-10-10 | 2015-02-11 | 新达通科技股份有限公司 | Paper currency face value identification method and device based on magnetic image |
CN104867225A (en) * | 2015-05-15 | 2015-08-26 | 深圳怡化电脑股份有限公司 | Banknote face orientation identification method and apparatus |
CN105139510A (en) * | 2015-08-25 | 2015-12-09 | 深圳怡化电脑股份有限公司 | Bank note identification method and system |
CN105654609A (en) * | 2015-12-29 | 2016-06-08 | 深圳怡化电脑股份有限公司 | Paper money processing method and paper money processing system |
Also Published As
Publication number | Publication date |
---|---|
CN106780963B (en) | 2019-08-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106056751B (en) | The recognition methods and system of serial number | |
Gatos et al. | Automatic table detection in document images | |
CN105261110B (en) | A kind of efficiently DSP paper money number recognition methods | |
CN104408449B (en) | Intelligent mobile terminal scene literal processing method | |
CN105139510B (en) | Paper Currency Identification and system | |
CN105303676A (en) | Banknote version identification method and banknote version identification system | |
CN106845542B (en) | Paper money number intelligent identification Method based on DSP | |
WO2013170663A1 (en) | Paper identifying method and related device | |
CN102800148A (en) | RMB sequence number identification method | |
CN106952393B (en) | Paper money identification method and device, electronic equipment and storage medium | |
CN105139508B (en) | A kind of method and device of detection bank note | |
CN103093185A (en) | Character recognition device, image processing device and methods thereof | |
CN106355744A (en) | Image identification method and device | |
CN111915635A (en) | Test question analysis information generation method and system supporting self-examination paper marking | |
CN104537364A (en) | Dollar bill denomination and edition identifying method based on texture analysis | |
CN106340116B (en) | A kind of recognition methods of bank note and device | |
CN106447910B (en) | A kind of method and device of paper money recognition | |
CN106898085A (en) | Identification bank note towards method and device | |
CN107481391B (en) | The detection method and device of bank note scribble | |
CN106355743A (en) | Banknote version identification method and device | |
CN106447904B (en) | Method and device for identifying paper money | |
CN105957237A (en) | Method and device for identifying version of banknote | |
CN106780963A (en) | Paper Currency Identification and device | |
CN106951902A (en) | A kind of image binaryzation processing method and processing device | |
CN104063874B (en) | Method for quantitatively evaluating gray level image binarization algorithms based on weight model |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190827 Termination date: 20211201 |
|
CF01 | Termination of patent right due to non-payment of annual fee |