KR101680333B1 - Device and method for classifying open and close eyes - Google Patents

Device and method for classifying open and close eyes Download PDF

Info

Publication number
KR101680333B1
KR101680333B1 KR1020150036967A KR20150036967A KR101680333B1 KR 101680333 B1 KR101680333 B1 KR 101680333B1 KR 1020150036967 A KR1020150036967 A KR 1020150036967A KR 20150036967 A KR20150036967 A KR 20150036967A KR 101680333 B1 KR101680333 B1 KR 101680333B1
Authority
KR
South Korea
Prior art keywords
banknote
feature value
visible light
infrared
value
Prior art date
Application number
KR1020150036967A
Other languages
Korean (ko)
Other versions
KR20160112088A (en
Inventor
박강령
권승용
박영호
팜단투엔
Original Assignee
동국대학교 산학협력단
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 동국대학교 산학협력단 filed Critical 동국대학교 산학협력단
Priority to KR1020150036967A priority Critical patent/KR101680333B1/en
Publication of KR20160112088A publication Critical patent/KR20160112088A/en
Application granted granted Critical
Publication of KR101680333B1 publication Critical patent/KR101680333B1/en

Links

Images

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
    • G07D7/06—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 using wave or particle radiation
    • G07D7/12—Visible light, infrared or ultraviolet radiation
    • G06K9/6202—

Abstract

More particularly, the present invention relates to an apparatus and a method for extracting feature values from a bill image and determining a bill's normality using a purge system.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a device for determining banknote straightness,

More particularly, the present invention relates to an apparatus and a method for extracting feature values from a bill image and determining a bill's normality using a purge system.

In case of paper money such as ATM or vending machine, the paper money can not be recognized by the machine if the degree of contamination is more than a certain level. Such a problem causes malfunction of the machine or inconvenience that the user inserts another bill. If the judgment of whether or not the paper money is used is incorrect, the paper money that can not be used is circulated again or the usable paper money is discarded, so that the disposal of the paper money An unnecessary expense such as a cost or a cost for issuing a new banknote occurs. Therefore, as the demand for technology to more accurately judge the ortho of bank notes has been increasing, recent researches on ortho judging are proceeding.

BACKGROUND ART [0002] The background art of the present invention is disclosed in Korean Patent Laid-Open Publication No. 2005-0075153 (published on Jul. 20, 2005).

The present invention is based on a fuzzy system, and not only can a banknote discrimination process be accurately and efficiently performed by a simple image analysis without using a complicated image analyzing apparatus, An apparatus and method for an orthophonic judgment are provided.

The objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood from the following description.

According to an aspect of the present invention, there is provided an apparatus for determining banknote affairs.

The banknote correctness determining apparatus according to an embodiment of the present invention includes an image generating unit for capturing a visible light reflection image and an infrared light transmission image of the inputted bill, an image generating unit for setting a region of interest in the visible light reflection image and the infrared transmission image, A fuzzy rule for calculating fuzzy output values by applying a fuzzy rule by inputting a visible ray characteristic value and an infrared characteristic value, and applying the fuzzy rule to obtain a fuzzy output value; A reverse purge output score calculating unit for outputting the banknote output score by inverting and purifying the output values of the banknotes and the banknotes, and a banknote correcting unit for determining the banknote's trueness by comparing the banknote output score with a preset threshold value .

According to another aspect of the present invention, there is provided a bill determination method and a computer program for executing the method.

The method of determining banknote severity according to an embodiment of the present invention and a computer program for executing the same include the steps of: capturing a visible light reflection image and an infrared transmission image of a bill inserted; setting a region of interest in a visible light reflection image and an infrared transmission image; Obtaining an average of pixel values of a region of interest as a visible ray feature value and an infrared ray feature value, applying fuzzy rules to the visible ray feature value and the infrared feature value to calculate fuzzy output values, The step of outputting the banknote output number by inverting the fuzzy output values and the step of comparing the banknote output output score with a preset threshold value to determine the banknote's ortho.

The present invention can more accurately determine an affair of a banknote by using a visible light reflection image of the banknote and an infrared transparent image of the banknote.

The present invention uses a fuzzy rule system based on visible light reflection images of banknotes and infrared transmission images of banknotes to calculate the output score of banknotes, and thus the accuracy of banknote banknote determination is high.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 and FIG. 2 are views for explaining a banknote bill correcting apparatus according to an embodiment of the present invention. FIG.
FIGS. 3 to 7 are views for explaining a bill validation method according to an embodiment of the present invention. FIG.
8 is a view for explaining an experimental example of a banknote affair judging method according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Also, when a part is referred to as "including " an element, it does not exclude other elements unless specifically stated otherwise.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings.

1 and 2 are views for explaining a bill correcting apparatus according to an embodiment of the present invention.

1, a banknote bill correcting apparatus 100 identifies a denomination of inputted banknotes, calculates a number of output points of the banknotes using a fuzzy rule system based on a visible light reflection image of the banknote and an infrared transmission image of the banknote, . The bill correcting apparatus 100 includes a visible ray camera, an infrared camera, a processor for performing image processing, an input / output interface for input / output of image data, a memory for storing data and programs, can do. The banknote orthostatic determination apparatus 100 can classify two kinds of banknotes through the determination of banknotes.

Referring to FIG. 2, the bank bill authenticating apparatus 100 includes a banknote denomination identifying unit 110, an image generating unit 120, a feature value acquiring unit 130, a fuzzy rule applying unit 140, A banknote sorting unit 160, and a banknote sorting unit 170. The banknote sorting unit 160 includes a plurality of banknotes.

The banknote block denomination identifying unit 110 identifies denomination of the inputted banknote. The banknote denomination identifying unit 110 can identify the banknote of the zipper using a light transmission system or a magnetic sensor.

The image generating unit 120 picks up an image of visible light reflection and an infrared transmission image of the inputted bill. The image generating unit 120 includes a visible light camera and an infrared camera. The image generating unit 120 can generate a visible light reflection image and an infrared light transmission image for every number of cases such as a forward direction of a front face of a banknote, a reverse direction of a front face of a banknote, a forward direction of a back face of a banknote, have. This can generate an image for every number of cases since it is not known which direction the bill is being put in.

The feature value acquiring unit 130 sets a region of interest in the visible light reflection image and the infrared transmission image that are captured, and acquires an average of pixel values of the ROI as a visible light ray feature value and an infrared ray feature value, respectively. Here, the area of interest may be different depending on the type of banknote and the direction in which the banknote is fed, and may be an area in which nothing is printed or an area in which a hidden picture is printed.

The fuzzy rule application unit 140 normalizes the visible light feature value and the infrared feature value to a value between 0 and 1 in order to make the input value of the fuzzy system, and inputs the normalized visible light normalized feature value and the infrared normalized feature value And the fuzzy rule is applied to perform fuzzification to calculate fuzzy output values.

The inverse purge output score calculating unit 150 performs defuzzification of the purge output values to calculate the banknote output score. (FOM), Last Of Maximum (LOM), Middle Of Maximum (MOM), Mean Of Maxima (MEOM), Center Of Gravity (COG) Can be used.

The banknote orthogonality determination unit 160 compares the banknote output score with a preset threshold value to determine the orthogonality of the banknote. The predetermined threshold value can be set by at least one of the kind of the bank notes, the direction in which the bank notes are fed, and the reverse purge method.

The bill classifier 170 can classify and output two kinds of bills through the determination of the bill.

FIGS. 3 to 7 are diagrams for explaining a bill validation method according to an exemplary embodiment of the present invention.

Referring to FIG. 3, in step S310, the bank bill correcting apparatus 100 images an image of the inputted bill to generate a visible light reflection image and an infrared transmission image.

In step S320, the bill correcting apparatus 100 generates a visible light characteristic value and an infrared characteristic value by calculating a luminance average value of pixels included in a specific region of a bill of each of the generated visible light reflection image and infrared transmission image. As the paper money circulates in the society and the user's hands (including sebum or oil) are used, the brightness value of the visible light reflection image on the outer surface of the paper money becomes darker and the oil is attached to the inner part of the paper money, And the brightness of the infrared transmission image tends to be lowered.

In step S330, the bank bill correcting apparatus 100 performs normalization so as to display the calculated characteristic values in a range of 0 to 1, respectively, in order to input the calculated characteristic values to the fuzzy system.

In step S340, the bank bill correcting apparatus 100 calculates a fuzzy output value by performing a fuzzification by applying a normalized visible ray normalized feature value and an infrared normalized feature value to input values as a fuzzy rule.

Referring to FIG. 4, a table for fuzzing the normalized visible ray normalized feature value and the infrared normalized feature value with input values is set. The bank bill correcting apparatus 100 sets the input values to one of H (High), M (Middle) and L (Low) according to preset criteria, and sets the output value to H (High) and L (Low). The bank bill correcting apparatus 100 can determine a purge output value according to nine input sets using two input values.

The bank bill correcting apparatus 100 calculates the output values to which the fuzzy membership function is applied to the input values with the normalized visible ray normalized feature value and the infrared normalized feature value and outputs the fuzzy membership function using the Min (minimum) rule and the Max (max) Respectively.

Referring to FIG. 5, the apparatus 180 for determining the bank note orthogonality, for example, applies a fuzzy membership function to the fuzzy output values 0.6 (H), 0.6 0.4 (M) and 0.8 (M), 0.2 (H)).

Referring to FIG. 6, when the banknote paper bill determining apparatus 100 is, for example, 0.0 (L) and 0.2 (H), 0.0 and 0.2 can be calculated using the Min rule and the Max rule, , L and H are L, so that the output values can be finally calculated as 0.0 (L) and 0.2 (L). When the above-described method is performed for all the rows of the fuzzy rule table of FIG. 4, the banknote severity judging apparatus 100 calculates nine output values of Min (minimum) rule and Max (maximum) rule as shown in FIG. can do.

In step S350, the bank bill correcting apparatus 100 performs reverse fuzzing on the fuzzy output values to calculate the banknote output output score.

Referring to FIG. 7, the bank bill authenticating apparatus 100 can calculate the banknote output number by inverting the output value calculated by applying the MAX rule among the fuzzy output values. For example, the banknote transaction unit 100 determines whether the FOM (Last Of Maximum), the MOM (Middle Of Maximum), or the FOM ), MEOM (Mean Of Maxima), COG (Center Of Gravity), and WA (Weighted Average) method. The bank note transaction determining apparatus 100 uses a method such as First Of Maximum (FOM), Last Of Maximum (LOM), Middle Of Maximum (MOM), Mean Of Maxima Output scores of 0.2, 0.8, 0.6, 0.6 and 0.5 can be calculated.

In step S360, the bill correcting apparatus 100 judges whether or not the bill is correct by comparing the bill output score with a preset threshold value. Here, the predetermined threshold value may be set by at least one of the kind of the bank notes, the direction in which the bank notes are fed, and the reverse purging method.

8 is a diagram for explaining an experimental example of a banknote heights determination method according to an embodiment of the present invention.

FIG. 8 is a flowchart illustrating a method of determining the error rate of the determination of banknotes according to an embodiment of the present invention, which is performed for US dollars 1, 2, 5, 10, 20, It is a table. The width of the table is classified according to the kind of reverse fuzzy, and the vertical is classified according to the kind of bills and the direction of the photographed image. Here, A is the forward direction of the front face of the banknote, B is the forward direction of the front face of the banknote, C is the backward direction of the banknote, and D is the reverse direction of the back face of the banknote. For example, in the case of 20D (710), the reverse rate of US $ 20 bills was judged according to the reverse fuzzy type using the visible light reflection image and the infrared transmission image. Min (minimum) of FOM (First Of Maximum), LOM (Last Of Maximum), MOM (Middle Of Maximum), MeOM (Mean Of Maxima), COG (Center Of Gravity) ) And Max (maximum) method. The average error rate (820) of the WA Max method was the smallest (3.065476%). Therefore, the WA Max method can be applied to the method of judging banknotes of US bills.

The bill validation method according to various embodiments of the present invention can be implemented in the form of a program command that can be executed through various means such as servers. Further, a program for executing the bill validation method according to the present invention may be installed in a computer means and recorded in a computer-readable medium. The computer readable medium may include program instructions, data files, data structures, and the like, alone or in combination.

Program instructions to be recorded on a computer-readable medium may be those specially designed and constructed for the present invention or may be available to those skilled in the computer software arts. Examples of computer-readable media include magnetic media such as hard disks, floppy disks, and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Includes hardware devices specifically configured to store and execute program instructions such as magneto-optical media and ROM, RAM, flash memory, and the like.

The embodiments of the present invention have been described above. It will be understood by those skilled in the art that the foregoing description of the present invention has been presented for illustrative purposes and that those skilled in the art will readily understand that various changes in form and details may be made therein without departing from the spirit and scope of the invention. It will be possible. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. The scope of the present invention is defined by the appended claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present invention.

100:

Claims (14)

A banknote orthogonality determination apparatus comprising:
An image generating unit for generating a visible light reflection image and an infrared transmission image of the inputted bill;
A feature value acquiring unit that sets an area of interest in the visible light reflection image and the infrared transmission image and acquires an average of pixel values of the area of interest in a visible light ray feature value and an infrared ray feature value respectively;
A fuzzy rule application unit for applying fuzzy rules and calculating fuzzy output values by inputting the visible light feature value and the infrared feature value;
A reverse purge output score calculating unit for outputting the banknote output score by inverting the fuzzy output values; And
And a banknote correcting unit for comparing the banknote output number with a preset threshold value to determine an affair of the banknote.
The method according to claim 1,
The image generation unit
And generates the visible light reflection image and the infrared transmission image with respect to the forward direction of the front face of the banknote, the reverse direction of the front face of the banknote, the forward direction of the back face of the banknote, and the reverse direction of the back face of the banknote.
The method according to claim 1,
Further comprising a banknote denomination discriminating unit for discriminating the denomination of the inserted banknote.
The method of claim 3,
Wherein the region of interest is an area in which nothing is printed or a region in which a hidden picture is printed, which depends on the type of the banknote and the direction in which the banknote is fed.
The method according to claim 1,
The fuzzy rule application unit
Wherein the visible light ray characteristic value and the infrared ray characteristic value are normalized to a value between 0 and 1, and a fuzzy rule is applied by inputting a normalized visible ray normalized characteristic value and an infrared ray normalized characteristic value.
The method according to claim 1,
The reverse purge output score calculating unit
A banknote orthogonality determination apparatus using any one of a First Of Maximum (FOM), Last Of Maximum (LOM), Middle Of Maximum (MOM), Mean Of Maxima, Center Of Gravity (COG) .
The method according to claim 6,
Wherein the predetermined threshold value is set by at least one of a type of the banknote, a direction in which the banknote is fed, and a reverse purge method.
The method according to claim 1,
Further comprising a banknote sorting unit for sorting and outputting two kinds of banknotes through the normal judgment of the banknote.
A method for judging banknote straightness,
Capturing a visible light reflection image and an infrared transmission image of the inserted bill;
Setting an area of interest in the visible light reflection image and the infrared transmission image, and obtaining an average of pixel values of the area of interest as a visible light ray feature value and an infrared ray feature value, respectively;
Calculating a fuzzy output value by applying a fuzzy rule to the fuzzy rule using the visible light feature value and the infrared feature value as inputs;
Outputting the paper money output score by inverting the fuzzy output values; And
And comparing the bill output score with a preset threshold value to determine an affirmation of the bill.
10. The method of claim 9,
Further comprising the step of identifying a denomination of the inserted banknote.
10. The method of claim 9,
Wherein the step of calculating the fuzzy output values by applying the fuzzy rule and the fuzzy rule with the visible light feature value and the infrared feature value as inputs
Normalizing the visible light feature value and the infrared feature value to a value between 0 and 1; And
And applying a fuzzy rule based on the normalized visible ray normalized feature value and the infrared normalized feature value.
10. The method of claim 9,
(FOM), LOM (Last Of Maximum), MOM (Middle Of Maximum), MeOM (Mean Of Maxima), and COG (Center Of Output) Of gravity) and WA (weighted average) method.
10. The method of claim 9,
Wherein the predetermined threshold value is set by at least one of a type of the bank notes, an input direction of the bank notes, and a reverse purge method.
A computer program recorded on a computer-readable recording medium for executing the bill validation method according to any one of claims 9 to 13.
KR1020150036967A 2015-03-17 2015-03-17 Device and method for classifying open and close eyes KR101680333B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020150036967A KR101680333B1 (en) 2015-03-17 2015-03-17 Device and method for classifying open and close eyes

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150036967A KR101680333B1 (en) 2015-03-17 2015-03-17 Device and method for classifying open and close eyes

Publications (2)

Publication Number Publication Date
KR20160112088A KR20160112088A (en) 2016-09-28
KR101680333B1 true KR101680333B1 (en) 2016-11-29

Family

ID=57101291

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020150036967A KR101680333B1 (en) 2015-03-17 2015-03-17 Device and method for classifying open and close eyes

Country Status (1)

Country Link
KR (1) KR101680333B1 (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101388551B1 (en) 2012-12-28 2014-04-24 동국대학교 산학협력단 Method for determinating fitness and unfitness of banknote

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101388551B1 (en) 2012-12-28 2014-04-24 동국대학교 산학협력단 Method for determinating fitness and unfitness of banknote

Also Published As

Publication number Publication date
KR20160112088A (en) 2016-09-28

Similar Documents

Publication Publication Date Title
US7783083B2 (en) Apparatus and method for detecting occluded face and apparatus and method for discriminating illegal user using the same
US7957567B2 (en) Method, apparatus, and program for judging faces facing specific directions
US7639858B2 (en) Currency validation
JP5044567B2 (en) Medium item confirmation device and self-service device
EP1357520B1 (en) Method for verifying users and updating database, and face verification system using the same
CN101226655B (en) Validation template for valuable media of multiple classes
US8254644B2 (en) Method, apparatus, and program for detecting facial characteristic points
US8611665B2 (en) Method of recognizing a media item
JP4888217B2 (en) Person attribute estimation device
JP2007305030A (en) Red-eye processing method, device and program
Saboia et al. Eye specular highlights telltales for digital forensics: A machine learning approach
CN106710062B (en) Detect the method and device of bank note safety line
JP2006065447A (en) Discriminator setting device, degree-of-attention measuring device, discriminator setting method, degree-of-attention measuring method, and program
CN106780966A (en) A kind of paper money discrimination method and device
CN107134047A (en) White watermark detection method and device
KR20160007804A (en) Apparatus and method for recognizing media, financial device
CN108460775A (en) A kind of forge or true or paper money recognition methods and device
Zarin et al. A hybrid fake banknote detection model using OCR, face recognition and hough features
KR101680333B1 (en) Device and method for classifying open and close eyes
KR101965751B1 (en) Device and method for multi-national banknote classification based on convolutional neural network
KR101388551B1 (en) Method for determinating fitness and unfitness of banknote
JP2006018707A (en) Subject identification apparatus, identification method and identification program thereof, subject discriminator setting device, and setting method and setting program thereof
CN109543554A (en) Bill detection method, device, terminal and computer readable storage medium
WO2020232889A1 (en) Check encashment method, apparatus and device, and computer-readable storage medium
EP3410409B1 (en) Media security validation

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 20191030

Year of fee payment: 4