CN108492447A - Dollar is towards recognition methods, electronic device and computer readable storage medium - Google Patents
Dollar is towards recognition methods, electronic device and computer readable storage medium Download PDFInfo
- Publication number
- CN108492447A CN108492447A CN201810230645.2A CN201810230645A CN108492447A CN 108492447 A CN108492447 A CN 108492447A CN 201810230645 A CN201810230645 A CN 201810230645A CN 108492447 A CN108492447 A CN 108492447A
- Authority
- CN
- China
- Prior art keywords
- pattern
- coordinate
- dollar
- image
- paper money
- 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
- G07D7/2008—Testing patterns thereon using pre-processing, e.g. de-blurring, averaging, normalisation or rotation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
- G06V10/507—Summing image-intensity values; Histogram projection analysis
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D7/20—Testing patterns thereon
- G07D7/2016—Testing patterns thereon using feature extraction, e.g. segmentation, edge detection or Hough-transformation
-
- G—PHYSICS
- 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
- G07D7/202—Testing patterns thereon using pattern matching
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of dollars towards recognition methods, and this method includes：Obtain two images up and down of dollar bill crosses paper money；Identify the area of the pattern in each image；The size of area of the pattern in more described two images, to judge the positive and negative of the bank note.The embodiment of the invention also discloses a kind of electronic device and computer readable storage mediums.Thereby, it is possible to the larger features of the area of the pattern area discrepancy using dollar bill front and reverse side to carry out positive and negative classification to dollar bill, reduces operation complexity when subsequently carrying out other identifications or true and false discriminating.
Description
Technical field
The present invention relates to image identification technical fields more particularly to a kind of dollar towards recognition methods, electronic device and meter
Calculation machine readable storage medium storing program for executing.
Background technology
Currently, before doing forge or true or paper money discriminating, first have to carry out value of money, version, towards etc. features identification, then
Can further it judge.Value of money point is first often done according to the size of bank note in the identification of the currency types such as RMB, Hongkong dollar, New Taiwan Dollar
Class, then version and Classification Oriented are done under same value of money, reduce the classification of classification, reduces the difficulty of identification.And dollar by
It is identical in the Paper Money Size of different values of money, the prioris such as size can not be used to carry out preliminary classification to the value of money of bank note.Currently
The dollar bill of circulation include seven kinds of values of money (1 yuan, 2 yuan, 5 yuan, 10 yuan, 20 yuan, 50 yuan, 100 yuan), there are three version (color version,
Big front page, small front page, wherein 1 yuan and 2 yuan is only had small front page).Positive positive, front is also possible that when being identified instead
Reversed this four of, reverse side positive to, reverse side towards.Therefore, it needs to be divided into 68 if doing the value of money of dollar, version, Classification Oriented
Class, relative to the difficulty for considerably increasing classification and identification the case where can using the geometric feature classifications such as size.
Invention content
It is a primary object of the present invention to propose a kind of dollar towards recognition methods, electronic device and computer-readable storage
Medium, it is intended to solve the problems, such as how to realize and quickly classify to dollar bill.
To achieve the above object, a kind of dollar provided by the invention is towards recognition methods, and the method comprising the steps of：
Obtain two images up and down of dollar bill crosses paper money；
Identify the area of the pattern in each image；And
The size of area of the pattern in more described two images, to judge the positive and negative of the bank note.
Optionally, the step of area of the pattern identified in each image includes：
The borderline region image of each described image is intercepted by the first preset range；
Pattern boundaries coordinate is oriented from the borderline region image；
The pattern width and height in each described image are calculated according to the pattern boundaries coordinate.
Optionally, the borderline region image includes four borderline region images up and down, described four up and down
Four edges circle up and down of the pattern in described image are separately included in borderline region image.
Optionally, first preset range includes：
Coboundary region：Picture altitude coordinate range is 5 to 50, and picture traverse coordinate range is 5 to W-5；Following battery limit (BL)
Domain：Picture altitude coordinate range is H-50 to H-5, and picture traverse coordinate range is 5 to W-5；Left margin region：Picture altitude is sat
Mark ranging from 5 to H-5, picture traverse coordinate range are 5 to 90；Right border area：Picture altitude coordinate range is 5 to H-5, figure
Image width degree coordinate range is W-90 to W-5, and wherein W is the overall width of described image, and H is the total height of described image.
Optionally, the size of the area of the pattern in more described two images, to judge the bank note just
The step of reverse side includes：
According to the first preset condition and pattern boundaries coordinate, pattern width and height, judge that the bank note is just
Face crosses paper money or reverse side crosses paper money.
Optionally, first preset condition is：
When the pattern width of upper figure is more than the pattern width of figure below, the pattern height of upper figure is more than the pattern height of figure below,
The left margin coordinate of upper figure is less than the left margin coordinate of figure below, and the coboundary coordinate of upper figure is less than the coboundary coordinate of figure below
When, the bank note is positive crosses paper money；
When the pattern width of upper figure is less than the pattern width of figure below, the pattern height of upper figure is less than the pattern height of figure below,
The left margin coordinate of upper figure is more than the left margin coordinate of figure below, and the coboundary coordinate of upper figure is more than the coboundary coordinate of figure below
When, the bank note is reverse side crosses paper money.
Optionally, this method further includes step：
Obtain the direct picture of the bank note；
The two specified area images in left and right are intercepted from the direct picture by the second preset range；
Statistics of histogram is carried out to the specified area image in the left and right two；
Judge the print in the specified area image in the left and right two according to the grey level histogram and the second preset condition
Chapter area image；
It is positive crosses paper money or reversed crosses paper money according to bank note described in the position judgment of the seal area image.
Optionally, the bank note described in the position judgment according to the seal area image is positive crosses paper money or reversed crosses paper money
In step, when the specified area image in left side is seal area image, indicate that the bank note is positive crosses paper money；When the finger on right side
Determine area image be seal area image when, indicate the bank note be reversed crosses paper money.
In addition, to achieve the above object, the present invention also proposes that a kind of electronic device, the electronic device include：Memory,
Processor and the dollar that can be run on the memory and on the processor is stored in towards recognizer, the dollar face
The step of being realized when being executed to recognizer by the processor such as above-mentioned dollar towards recognition methods.
Further, to achieve the above object, the present invention also provides a kind of computer readable storage medium, the computers
It is stored with dollar on readable storage medium storing program for executing towards recognizer, is realized such as when the dollar is executed by processor towards recognizer
The step of above-mentioned dollar is towards recognition methods.
Dollar proposed by the present invention can utilize U.S. towards recognition methods, electronic device and computer readable storage medium
The larger feature of the area of the pattern area discrepancy of yuan note front and reverse side, two images up and down when according to the bank note crosses paper money
In pattern boundaries, judge that the bank note is positive crosses paper money or reverse side crosses paper money, the bank note be subjected to positive and negative classification, is reduced
Operation complexity when other identifications or true and false discriminating is subsequently carried out, recognition speed and accuracy rate are promoted.Furthermore it is also possible to
According to the position in seal region in direct picture on the basis of positive and negative classification, judge that the bank note is positive crosses paper money or reversed
Crosses paper money, to further be refined to the classification of the bank note.
Description of the drawings
Fig. 1 is a kind of Organization Chart for electronic device that first embodiment of the invention proposes；
Fig. 2 is flow chart of a kind of dollar towards recognition methods that second embodiment of the invention proposes；
Fig. 3 is flow chart of a kind of dollar towards recognition methods that third embodiment of the invention proposes；
Fig. 4 is the schematic diagram of the alternative embodiment of interception borderline region image in the present invention；
Fig. 5 is the schematic diagram of the alternative embodiment of registration pattern boundary coordinate in the present invention；
Fig. 6 is flow chart of a kind of dollar towards recognition methods that fourth embodiment of the invention proposes；
Fig. 7 is a kind of schematic diagram of the specified area image in left and right in the present invention；
Fig. 8 is a kind of schematic diagram of grey level histogram in the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific implementation mode
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Embodiment one
As shown in fig.1, first embodiment of the invention proposes a kind of electronic device 2.In the present embodiment, the electronics dress
It can be the various devices towards identification function for needing to use dollar bill to set 2, such as carrying out currency true and false discriminating
Device etc..The electronic device 2 includes memory 20, processor 22 and dollar towards recognizer 28.
Wherein, the memory 20 includes at least a type of readable storage medium storing program for executing, and the electricity is installed on for storing
The operating system and types of applications software of sub-device 2, such as program code etc. of the dollar towards recognizer 28.In addition, described
Memory 20 can be also used for temporarily storing the Various types of data that has exported or will export.
The processor 22 can be in some embodiments central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips.The processor 22 is commonly used in the control electricity
The overall operation of sub-device 2.In the present embodiment, the processor 22 is for running the program code stored in the memory 20
Or processing data, such as the dollar is run towards recognizer 28 etc..
When the dollar is executed towards recognizer 28 by the processor 22, following steps are realized：
(1) two images (referred to as upper figure and figure below) up and down of dollar bill crosses paper money are obtained.
(2) area of the pattern in each image is identified.Including：
The borderline region image of each described image is intercepted by the first preset range；
Pattern boundaries coordinate is oriented from the borderline region image；
The pattern width and height in each described image are calculated according to the pattern boundaries coordinate.
(3) size of the area of the pattern in more described two images, to judge the positive and negative of the bank note.Packet
It includes：According to the first preset condition and the pattern boundaries coordinate, pattern width and height judge the bank note be front crosses paper money or
Reverse side crosses paper money.Wherein, first preset condition is：When the pattern width of upper figure is more than the pattern width of figure below, the figure of upper figure
Case height is more than the pattern height of figure below, and the left margin coordinate of upper figure is less than the left margin coordinate of figure below, and the coboundary of upper figure
When coordinate is less than the coboundary coordinate of figure below, it is believed that the bank note is positive crosses paper money；When the pattern width of upper figure is less than figure below
Pattern width, the pattern height of upper figure are less than the pattern height of figure below, and the left margin coordinate of upper figure is more than the left margin seat of figure below
Mark, and the coboundary coordinate of upper figure be more than figure below coboundary coordinate when, it is believed that the bank note be reverse side crosses paper money.
The detailed description of above-mentioned steps please refers to following second to fourth embodiment, and details are not described herein.
It will be understood by those skilled in the art that structure shown in Fig. 1 does not constitute the restriction to the electronic device 2,
The electronic device 2 can also include other necessary parts, either combine certain components or different components arrangement.
Embodiment two
As shown in fig.2, a kind of dollar of second embodiment of the invention proposition is applied to the electronics and fills towards recognition methods
It sets in 2.In the present embodiment, the execution sequence of the step in flow chart shown in Fig. 2 can change according to different requirements,
Certain steps can be omitted.This approach includes the following steps：
S100 obtains two images up and down of dollar bill crosses paper money.
Specifically, when dollar bill crosses paper money, positive positive, positive reversed, reverse side forward direction, reverse side reversed four be might have
Kind modes of emplacement, wherein front refers to the one side for having portrait, reverse side refers to the one side of no portrait, and forward direction refers to the figure of the bank note
Case is placed by correct upper and lower directions, refers to reversely that the pattern of the bank note turns upside down placement.Each time after crosses paper money, it will obtain
Upper and lower two images, referred to as upper figure and figure below.For example, when modes of emplacement crosses paper money of the bank note with positive forward direction, obtain
Upper figure is the front direct picture of the bank note, and obtained figure below is the reverse side direct picture of the bank note.
S102 identifies the area of the pattern in each image.
Specifically, after getting the upper figure and figure below of the bank note, figure is identified respectively from the upper figure and figure below
Case region.The area of the pattern refers to the region that currency pattern is printed in the bank note, that is, after removing surrounding white edge
Region.In the present embodiment, institute can be found out by way of positioning the boundary coordinate up and down of the pattern in the bank note
State the coordinate range of area of the pattern.
About the specific introduction of step S102, correlation step in Fig. 3 and Fig. 6 please be join.For example, step S102 is referred to figure
Step S302-S306 is realized in step S202-S206, Fig. 6 in 3, relate in Fig. 3, Fig. 6 it is more other the step of.
S104, the size of the area of the pattern in more described two images, to judge the positive and negative of the bank note.
Specifically, since the area of the pattern area difference of dollar bill front and reverse side is larger, positive pattern area compared with
Greatly, the pattern area of reverse side is smaller, first can carry out preliminary classification to dollar bill using this feature, judge the bank note
Obverse and reverse.When the area of the pattern area of the upper figure is more than the area of the pattern area of described figure below, the paper is indicated
Coin is positive crosses paper money；When the area of the pattern area of the upper figure is less than the area of the pattern area of described figure below, the paper is indicated
Coin is reverse side crosses paper money.
About the specific introduction of step S104, correlation step in Fig. 3 and Fig. 6 please be join.For example, step S104 is referred to figure
Step S308 is realized in step S208, Fig. 6 in 3, relate in Fig. 3, Fig. 6 it is more other the step of.
Embodiment three
As shown in fig.3, a kind of dollar of third embodiment of the invention proposition is applied to the electronics and fills towards recognition methods
It sets in 2.In the present embodiment, the execution sequence of the step in flow chart shown in Fig. 3 can change according to different requirements,
Certain steps can be omitted.This approach includes the following steps：
S200 obtains two images up and down of dollar bill crosses paper money.
Specifically, when dollar bill crosses paper money, positive positive, positive reversed, reverse side forward direction, reverse side reversed four be might have
Kind modes of emplacement.Each time after crosses paper money, two images up and down, referred to as upper figure and figure below will be obtained.For example, when the bank note is with just
When the modes of emplacement crosses paper money of face forward direction, obtained upper figure is the front direct picture of the bank note, and obtained figure below is the paper
The reverse side direct picture of coin.
S202 is intercepted the borderline region image of each described image by the first preset range.
Specifically, in order to identify the area of the pattern in described image (upper figure and figure below), registration pattern boundary is needed,
Before this, four borderline region images up and down can be first intercepted out from described image.Four boundaries up and down
Four edges circle up and down of the pattern in described image have been separately included in area image.As shown in figure 4, to be cut in the present invention
Take the schematic diagram of the alternative embodiment of borderline region image.Wherein, first preset range includes：
Coboundary region：Picture altitude coordinate range is 5 to 50, and picture traverse coordinate range is 5 to W-5；Following battery limit (BL)
Domain：Picture altitude coordinate range is H-50 to H-5, and picture traverse coordinate range is 5 to W-5；Left margin region：Picture altitude is sat
Mark ranging from 5 to H-5, picture traverse coordinate range are 5 to 90；Right border area：Picture altitude coordinate range is 5 to H-5, figure
Image width degree coordinate range is W-90 to W-5.W is the overall width of described image, and H is the total height of described image.
After interception, the upper figure and described figure below respectively obtain four borderline region images up and down.
S204 orients pattern boundaries coordinate from the borderline region image.
Specifically, it for the upper figure and figure below, is positioned from corresponding four borderline region images up and down respectively
Go out the boundary coordinate up and down of included pattern.Wherein, for up-and-down boundary area image, using row projection, boundary point
It finds, the mode of fitting a straight line orients pattern up-and-down boundary coordinate StartY and EndY.For right boundary area image, adopt
It is found with row projection, boundary point, the mode of fitting a straight line orients pattern right boundary coordinate StartX and EndX.Such as Fig. 5 institutes
Show, for the schematic diagram of the alternative embodiment of registration pattern boundary coordinate in the present invention.
In the present embodiment, the pattern up-and-down boundary coordinate in the upper figure is denoted as UpStartY and UpEndY, and pattern is left
Right margin coordinate UpStartX and UpEndX；Pattern up-and-down boundary coordinate in described figure below be denoted as DownStartY and
DownEndY, pattern right boundary coordinate DownStartX and DownEndX.
S206 calculates pattern width and height in each described image according to the pattern boundaries coordinate.
Specifically, it is calculated according to corresponding pattern right boundary coordinate StartX and EndX for the upper figure and figure below
Go out pattern width Width=EndX-StartX, according to corresponding pattern up-and-down boundary coordinate StartY and EndY, calculates figure
Case height Height=EndY-StartY (as shown in Figure 5).Wherein, the pattern width in the upper figure is denoted as UpWidth, figure
Case height is denoted as UpHeight；Pattern width in described figure below is denoted as DownWidth, and pattern height is denoted as DownHeight.
S208 judges the bank note for positive crosses paper money or reverse side crosses paper money according to the first preset condition.
Specifically, according to the first preset condition and pattern boundaries coordinate, pattern width and height, it can be determined that
It is positive crosses paper money or reverse side crosses paper money to go out the bank note.Wherein, first preset condition is：Under the pattern width of upper figure is more than
The pattern width of figure, the pattern height of upper figure are more than the pattern height of figure below, and the left margin coordinate of upper figure is less than the left side of figure below
Boundary's coordinate, and the coboundary coordinate of upper figure be less than figure below coboundary coordinate when, i.e. UpWidth>DownWidth&&UpHeight
>DownHeight&&UpStartX<DownStartX&&UpStartY<DownStartY, it is believed that the bank note is positive crosses paper money；
When the pattern width of upper figure is less than the pattern width of figure below, the pattern height of upper figure is less than the pattern height of figure below, a left side for upper figure
Boundary coordinate is more than the left margin coordinate of figure below, and the coboundary coordinate of upper figure is more than the coboundary coordinate of figure below, i.e. UpWidth
<DownWidth&&UpHeight<DownHeight&&UpStartX>DownStartX&&UpStartY>DownStartY recognizes
It is reverse side crosses paper money for the bank note.
The dollar that the present embodiment is proposed is towards recognition methods, two images up and down when can be according to the bank note crosses paper money
In pattern boundaries, judge that the bank note is positive crosses paper money or reverse side crosses paper money, the bank note be subjected to positive and negative classification, is simplified
Operation complexity when other identifications or true and false discriminating is subsequently carried out, recognition speed and accuracy rate are promoted.
Example IV
As shown in fig.6, a kind of dollar of fourth embodiment of the invention proposition is applied to the electronics and fills towards recognition methods
It sets in 2.In the present embodiment, the step S200- of step S300-S308 and second embodiment of the dollar towards recognition methods
S208 is similar, further includes step S310-S318 difference lies in this method.
This approach includes the following steps：
S300 obtains two images up and down of dollar bill crosses paper money.
S302 is intercepted the borderline region image of each described image by the first preset range.
Specifically, four borderline region images up and down, four sides up and down are intercepted out from described image
Four edges circle up and down of the pattern in described image have been separately included in battery limit (BL) area image.As shown in figure 4, in the present invention
Intercept the schematic diagram of the alternative embodiment of borderline region image.Wherein, first preset range includes：
Coboundary region：Picture altitude coordinate range is 5 to 50, and picture traverse coordinate range is 5 to W-5；Following battery limit (BL)
Domain：Picture altitude coordinate range is H-50 to H-5, and picture traverse coordinate range is 5 to W-5；Left margin region：Picture altitude is sat
Mark ranging from 5 to H-5, picture traverse coordinate range are 5 to 90；Right border area：Picture altitude coordinate range is 5 to H-5, figure
Image width degree coordinate range is W-90 to W-5.W is the overall width of described image, and H is the total height of described image.
S304 orients pattern boundaries coordinate from the borderline region image.
Specifically, it for the upper figure and figure below, is positioned from corresponding four borderline region images up and down respectively
Go out the boundary coordinate up and down of included pattern.Wherein, for up-and-down boundary area image, using row projection, boundary point
It finds, the mode of fitting a straight line orients pattern up-and-down boundary coordinate StartY and EndY.For right boundary area image, adopt
It is found with row projection, boundary point, the mode of fitting a straight line orients pattern right boundary coordinate StartX and EndX.Such as Fig. 5 institutes
Show, for the schematic diagram of the alternative embodiment of registration pattern boundary coordinate in the present invention.
In the present embodiment, the pattern up-and-down boundary coordinate in the upper figure is denoted as UpStartY and UpEndY, and pattern is left
Right margin coordinate UpStartX and UpEndX；Pattern up-and-down boundary coordinate in described figure below be denoted as DownStartY and
DownEndY, pattern right boundary coordinate DownStartX and DownEndX.
S306 calculates pattern width and height in each described image according to the pattern boundaries coordinate.
Specifically, it is calculated according to corresponding pattern right boundary coordinate StartX and EndX for the upper figure and figure below
Go out pattern width Width=EndX-StartX, according to corresponding pattern up-and-down boundary coordinate StartY and EndY, calculates figure
Case height Height=EndY-StartY (as shown in Figure 5).Wherein, the pattern width in the upper figure is denoted as UpWidth, figure
Case height is denoted as UpHeight；Pattern width in described figure below is denoted as DownWidth, and pattern height is denoted as DownHeight.
S308 judges the bank note for positive crosses paper money or reverse side crosses paper money according to the first preset condition.
Specifically, according to the first preset condition and pattern boundaries coordinate, pattern width and height, it can be determined that
It is positive crosses paper money or reverse side crosses paper money to go out the bank note.Wherein, first preset condition is：Under the pattern width of upper figure is more than
The pattern width of figure, the pattern height of upper figure are more than the pattern height of figure below, and the left margin coordinate of upper figure is less than the left side of figure below
Boundary's coordinate, and the coboundary coordinate of upper figure be less than figure below coboundary coordinate when, i.e. UpWidth>DownWidth&&UpHeight
>DownHeight&&UpStartX<DownStartX&&UpStartY<DownStartY, it is believed that the bank note is positive crosses paper money；
When the pattern width of upper figure is less than the pattern width of figure below, the pattern height of upper figure is less than the pattern height of figure below, a left side for upper figure
Boundary coordinate is more than the left margin coordinate of figure below, and the coboundary coordinate of upper figure is more than the coboundary coordinate of figure below, i.e. UpWidth
<DownWidth&&UpHeight<DownHeight&&UpStartX>DownStartX&&UpStartY>DownStartY recognizes
It is reverse side crosses paper money for the bank note.
S310 obtains the direct picture of the bank note.
Specifically, after judging that the bank note is positive crosses paper money or reverse side crosses paper money, it is also necessary to further judge the paper
The placement direction of coin.It in the present embodiment, can be according to the position in the seal region in the direct picture of the bank note, to judge
The bank note is positive crosses paper money or reversed crosses paper money.Therefore, first have to obtain the direct picture of the bank note.When the bank note is just
When the crosses paper money of face, the upper figure is the direct picture of the bank note；When the bank note is reverse side crosses paper money, described figure below is the paper
The direct picture of coin.
S312 is intercepted the two specified area images in left and right by the second preset range from the direct picture.
Specifically, in dollar bill, seal is generally printed on the position on the left of the forward bias of bank note front.That is,
When the bank note is positive crosses paper money, seal region will be positioned at the left side of the direct picture.And if the bank note is reversed mistake
Paper money, then seal region will be positioned at the right side of the direct picture (because the direct picture turns upside down).In order to identify
The seal region in direct picture is stated, the two specified area images in interception left and right first from the direct picture.Described second
Preset range can be pre-set according to the seal position feature of dollar bill.The specified area image is necessary to ensure that can
With comprising seal region, therefore, in the present embodiment, interception range (the i.e. described second default model of the specified area image
Enclose) it is larger.As shown in fig. 7, specifying the schematic diagram of area image for a kind of left and right in the present invention.
S314 carries out statistics of histogram to the specified area image in the left and right two.
Specifically, after intercepting out the two specified area images in left and right from the direct picture, by the left and right two
Specified area image carries out statistics of histogram respectively.As shown in figure 8, for a kind of signal of grey level histogram in the present invention
Figure.The grey level histogram is the statistics to grey level distribution in the specified area image, will be in the specified area image
All pixels, according to the size of gray value, count its appearance frequency.The horizontal axis of the grey level histogram indicates gray value,
Vertical pivot indicates the number of the pixel with certain gray value in the specified area image.
S316 judges the seal area image in the specified area image in the left and right two according to the second preset condition.
Specifically, since the seal of dollar bill is close to black, gray value is close to 0.It therefore, can be by analyzing institute
The corresponding grey level histogram of the specified area image in left and right two is stated, judges which is seal area image.In the present embodiment
In, second preset condition can be：When 0~20 pair of gray value in the corresponding grey level histogram of specified area image in left side
The number of pixels answered is more than 0~20 corresponding pixel of gray value in the corresponding grey level histogram of specified area image on right side
Number, and 100~150 corresponding number of pixels of gray value is less than right side in the corresponding grey level histogram of specified area image in left side
The corresponding grey level histogram of specified area image in 100~150 corresponding number of pixels of gray value, then the left side is specified
Area image is seal area image.Conversely, when gray value 0~20 in the corresponding grey level histogram of specified area image in left side
Corresponding number of pixels is less than 0~20 corresponding pixel of gray value in the corresponding grey level histogram of specified area image on right side
Number, and 100~150 corresponding number of pixels of gray value is more than right side in the corresponding grey level histogram of specified area image in left side
The corresponding grey level histogram of specified area image in 100~150 corresponding number of pixels of gray value, then the right side is specified
Area image is seal area image.
S318 is positive crosses paper money or reversed crosses paper money according to bank note described in the position judgment of the seal area image.
Specifically, when the specified area image in the left side is seal area image, indicate that the bank note is positive mistake
Paper money；When the specified area image on the right side is seal area image, indicate that the bank note is reversed crosses paper money.
The dollar that the present embodiment is proposed towards recognition methods, can after judging the positive and negative of dollar bill, into
One step judges that the bank note is positive crosses paper money or reversed crosses paper money, to institute according to the position in seal region in direct picture
The classification for stating bank note is further refined, and complexity when subsequently carrying out other identifications or true and false discriminating is reduced.
Embodiment five
The present invention also provides another embodiments, that is, provide a kind of computer readable storage medium, the computer
Readable storage medium storing program for executing is stored with dollar towards recognizer, and the dollar can be held towards recognizer by least one processor
Row, so that the step of at least one processor is executed such as above-mentioned dollar towards recognition methods.
It should be noted that herein, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that process, method, article or device including a series of elements include not only those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including this
There is also other identical elements in the process of element, method, article or device.
The embodiments of the present invention are for illustration only, can not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be expressed in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), including some instructions are used so that a station terminal (can be mobile phone, computer, service
Device, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited in above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form, all of these belong to the protection of the present invention.
Claims (10)
1. a kind of dollar is towards recognition methods, which is characterized in that the method comprising the steps of：
Obtain two images up and down of dollar bill crosses paper money；
Identify the area of the pattern in each image；And
The size of area of the pattern in more described two images, to judge the positive and negative of the bank note.
2. dollar according to claim 1 is towards recognition methods, which is characterized in that the pattern in each image of identification
The step of region includes：
The borderline region image of each described image is intercepted by the first preset range；
Pattern boundaries coordinate is oriented from the borderline region image；
The pattern width and height in each described image are calculated according to the pattern boundaries coordinate.
3. dollar according to claim 2 is towards recognition methods, which is characterized in that the borderline region image includes up and down
Four borderline region images are controlled, the pattern in described image is separately included in four borderline region images up and down
Four edges circle up and down.
4. dollar according to claim 3 is towards recognition methods, which is characterized in that first preset range includes：
Coboundary region：Picture altitude coordinate range is 5 to 50, and picture traverse coordinate range is 5 to W-5；Lower boundary region：Figure
Image height degree coordinate range is H-50 to H-5, and picture traverse coordinate range is 5 to W-5；Left margin region：Picture altitude coordinate model
It is 5 to H-5 to enclose, and picture traverse coordinate range is 5 to 90；Right border area：Picture altitude coordinate range is 5 to H-5, and image is wide
Degree coordinate range is W-90 to W-5, and wherein W is the overall width of described image, and H is the total height of described image.
5. dollar according to claim 2 is towards recognition methods, which is characterized in that in more described two images
The step of size of area of the pattern, positive and negative to judge the bank note includes：
According to the first preset condition and pattern boundaries coordinate, pattern width and height, judge that the bank note is positive mistake
Paper money or reverse side crosses paper money.
6. dollar according to claim 5 is towards recognition methods, which is characterized in that first preset condition is：
When the pattern width of upper figure is more than the pattern width of figure below, the pattern height of upper figure is more than the pattern height of figure below, upper figure
Left margin coordinate be less than figure below left margin coordinate, and the coboundary coordinate of upper figure be less than figure below coboundary coordinate when, institute
It is positive crosses paper money to state bank note；
When the pattern width of upper figure is less than the pattern width of figure below, the pattern height of upper figure is less than the pattern height of figure below, upper figure
Left margin coordinate be more than figure below left margin coordinate, and the coboundary coordinate of upper figure be more than figure below coboundary coordinate when, institute
It is reverse side crosses paper money to state bank note.
7. according to claim 2-6 any one of them dollars towards recognition methods, which is characterized in that this method further includes step
Suddenly：
Obtain the direct picture of the bank note；
The two specified area images in left and right are intercepted from the direct picture by the second preset range；
Statistics of histogram is carried out to the specified area image in the left and right two；
Judge the seal area in the specified area image in the left and right two according to the grey level histogram and the second preset condition
Area image；
It is positive crosses paper money or reversed crosses paper money according to bank note described in the position judgment of the seal area image.
8. dollar according to claim 7 is towards recognition methods, which is characterized in that according to the seal area image
In the step of bank note described in position judgment is positive crosses paper money or reversed crosses paper money, when the specified area image in left side is seal administrative division map
When picture, indicate that the bank note is positive crosses paper money；When the specified area image on right side is seal area image, the bank note is indicated
For reversed crosses paper money.
9. a kind of electronic device, which is characterized in that the electronic device includes：Memory, processor and it is stored in the storage
On device and the dollar that can run on the processor is towards recognizer, and the dollar is towards recognizer by the processor
The step of being realized when execution such as dollar described in any item of the claim 1 to 8 towards recognition methods.
10. a kind of computer readable storage medium, which is characterized in that be stored with a dollar face on the computer readable storage medium
To recognizer, realized as described in any item of the claim 1 to 8 when the dollar is executed by processor towards recognizer
The step of dollar is towards recognition methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810230645.2A CN108492447B (en) | 2018-03-20 | 2018-03-20 | Dollar-oriented identification method, electronic device and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810230645.2A CN108492447B (en) | 2018-03-20 | 2018-03-20 | Dollar-oriented identification method, electronic device and computer-readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108492447A true CN108492447A (en) | 2018-09-04 |
| CN108492447B CN108492447B (en) | 2020-09-15 |
Family
ID=63318787
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810230645.2A Active CN108492447B (en) | 2018-03-20 | 2018-03-20 | Dollar-oriented identification method, electronic device and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108492447B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050169511A1 (en) * | 2004-01-30 | 2005-08-04 | Cummins-Allison Corp. | Document processing system using primary and secondary pictorial image comparison |
| CN101908241A (en) * | 2010-08-03 | 2010-12-08 | 广州广电运通金融电子股份有限公司 | Method and system for identifying valued documents |
| CN102682514A (en) * | 2012-05-17 | 2012-09-19 | 广州广电运通金融电子股份有限公司 | Paper identification method and relative device |
| CN103886309A (en) * | 2014-02-27 | 2014-06-25 | 华中科技大学 | Method for identifying dollar denominations through facial recognition |
| CN104658097A (en) * | 2015-03-11 | 2015-05-27 | 华中科技大学 | RMB paper currency denomination identification method based on histogram matching of images |
| CN105261110A (en) * | 2015-10-26 | 2016-01-20 | 江苏国光信息产业股份有限公司 | Efficient DSP banknote serial number recognizing method |
| CN106683262A (en) * | 2016-12-27 | 2017-05-17 | 深圳怡化电脑股份有限公司 | Banknote face orientation identification method and apparatus thereof |
| CN106898085A (en) * | 2017-02-23 | 2017-06-27 | 深圳怡化电脑股份有限公司 | Identification bank note towards method and device |
| CN107705418A (en) * | 2017-10-10 | 2018-02-16 | 深圳怡化电脑股份有限公司 | A kind of bank note towards recognition methods, device, equipment and readable storage medium storing program for executing |
-
2018
- 2018-03-20 CN CN201810230645.2A patent/CN108492447B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050169511A1 (en) * | 2004-01-30 | 2005-08-04 | Cummins-Allison Corp. | Document processing system using primary and secondary pictorial image comparison |
| CN101908241A (en) * | 2010-08-03 | 2010-12-08 | 广州广电运通金融电子股份有限公司 | Method and system for identifying valued documents |
| CN102682514A (en) * | 2012-05-17 | 2012-09-19 | 广州广电运通金融电子股份有限公司 | Paper identification method and relative device |
| CN103886309A (en) * | 2014-02-27 | 2014-06-25 | 华中科技大学 | Method for identifying dollar denominations through facial recognition |
| CN104658097A (en) * | 2015-03-11 | 2015-05-27 | 华中科技大学 | RMB paper currency denomination identification method based on histogram matching of images |
| CN105261110A (en) * | 2015-10-26 | 2016-01-20 | 江苏国光信息产业股份有限公司 | Efficient DSP banknote serial number recognizing method |
| CN106683262A (en) * | 2016-12-27 | 2017-05-17 | 深圳怡化电脑股份有限公司 | Banknote face orientation identification method and apparatus thereof |
| CN106898085A (en) * | 2017-02-23 | 2017-06-27 | 深圳怡化电脑股份有限公司 | Identification bank note towards method and device |
| CN107705418A (en) * | 2017-10-10 | 2018-02-16 | 深圳怡化电脑股份有限公司 | A kind of bank note towards recognition methods, device, equipment and readable storage medium storing program for executing |
Non-Patent Citations (1)
| Title |
|---|
| 付祥旭: ""基于多光谱图像的美元识别与鉴伪技术研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108492447B (en) | 2020-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107808120B (en) | Glasses localization method, device and storage medium | |
| CN102667810B (en) | Face recognition in digital images | |
| CN109033940B (en) | A kind of image-recognizing method, calculates equipment and storage medium at device | |
| CN110084135A (en) | Face identification method, device, computer equipment and storage medium | |
| US7920725B2 (en) | Apparatus, method, and program for discriminating subjects | |
| CN112070015B (en) | Face recognition method, system, device and medium fusing occlusion scene | |
| CN109635656A (en) | Vehicle attribute recognition methods, device, equipment and medium neural network based | |
| EP1970859B1 (en) | Detecting method and detecting system for positions of face parts | |
| US20150016687A1 (en) | Method, system and computer storage medium for face detection | |
| CN102800148A (en) | RMB sequence number identification method | |
| CN103679168A (en) | Detection method and detection device for character region | |
| CN110135421A (en) | Licence plate recognition method, device, computer equipment and computer readable storage medium | |
| CN111259968A (en) | Illegal image recognition method, device, equipment and computer readable storage medium | |
| CN112396050B (en) | Image processing method, device and storage medium | |
| CN107358718B (en) | A kind of crown word number identification method, device, equipment and storage medium | |
| CN110738092B (en) | Invoice text detection method | |
| CN105809089A (en) | Multi-face detection method and device under complex background | |
| CN111553251A (en) | Certificate four-corner incomplete detection method, device, equipment and storage medium | |
| CN110378351A (en) | Seal discrimination method and device | |
| CN116052152A (en) | License plate recognition system based on contour detection and deep neural network | |
| CN109840453B (en) | Face matching method and device | |
| CN111881732B (en) | SVM (support vector machine) -based face quality evaluation method | |
| CN108492447A (en) | Dollar is towards recognition methods, electronic device and computer readable storage medium | |
| CN112434640A (en) | Method and device for determining rotation angle of document image and storage medium | |
| CN115049840B (en) | Screen-shot watermark identification method, storage medium and electronic device |
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 |