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
• • G—PHYSICS
  • G07—CHECKING-DEVICES
  • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
  • G07D11/00—Devices accepting coins; Devices accepting, dispensing, sorting or counting valuable papers
  • G07D11/50—Sorting or counting valuable papers
• • G—PHYSICS
  • G07—CHECKING-DEVICES
  • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
  • G07D2207/00—Paper-money testing devices
• • G—PHYSICS
  • G07—CHECKING-DEVICES
  • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
  • G07D2211/00—Paper-money handling devices

Definitions

• the present invention relates to a method and an apparatus for recognizing a denomination of paper money, and more particularly, to a method and an apparatus for converting a specific image into data using an image of a paper money and processing the data in a paper money counter or a forged paper money discriminator to recognize a denomination of paper money.
• Paper money counters are used in banks or the like to count paper money.
• Such conventional paper money counters having a function of discriminating denominations of paper money use a method of sensing only fragmentary characteristics of paper money such as sizes or colors to recognize denominations thereof.
• conventional paper money counters use a method of scanning images of paper money and comparing the scanned images with a standard paper money image to discriminate between the scanned images and the standard paper money image.
• the denominations are recognized using the sizes or colors.
• various denominations or similar denominations cannot be accurately discriminated.
• discrimination time is long, and it is difficult to discriminate the denominations with reference to damaged paper money or a state of an image of paper money.
• FIG. 1 is a flowchart illustrating a method of recognizing a denomination according to an embodiment of the present invention
• FIG. 2 is a diagram illustrating a process of extracting a specific image in the method illustrated in FIG. 1 ;
• FIG. 3 is a diagram illustrating a relationship between an output of a neural network function and an error determination in the method illustrated in FIG. 1 ;
• FIG. 4 is a schematic block diagram illustrating an apparatus for recognizing a denomination according to an embodiment of the present invention.
• FIG. 5 is a cross-sectional view illustrating a configuration of a denomination recognizing paper money counter according to an embodiment of the present invention.
• the present invention provides a method and an apparatus for constituting a discrimination algorithm using a mathematical process to further quickly and precisely discriminate a denomination of paper money.
• the present invention also provides a method and an apparatus for determining whether a recognition of a denomination is valid during a discrimination of the denomination of paper money.
• an image of paper money can be input and processed to recognize a denomination of the paper money.
• the denomination can be recognized as an output value so as to further quickly discriminate and calculate the denomination.
• output values of a function can be compared during the recognition of the denomination to determine a validity of the recognition of the denomination and check for errors. As a result, reliability of the recognition of the denomination can be improved.
• FIG. 1 is a flowchart illustrating a method of recognizing a denomination of paper money according to an embodiment of the present invention.
• an image of paper money is input.
• the paper money including figures, letters, colors, patterns, images, etc. is scanned using an image scanner to generate an image of the paper money so that the generated image can be input.
• the paper money is not limited to a banknote but may correspond to a check, a lottery ticket, a gift coupon, or the like.
• an analog-to-digital converter may convert the scanned image into a digital image and input the digital image.
• a specific portion is extracted from the image of the paper money to discriminate a denomination of the paper money.
• FIG. 2 is a flowchart illustrating operation S20 of the method illustrated in FIG. 1.
• operation S21 the image of the paper money is obtained.
• portions out with the paper money are also obtained.
• operation S22 an outline of the paper money is extracted to remove the unnecessary portions of the image. Only an area enclosed by the outline of the paper money is used. Alternatively, only a portion that characterizes each denomination of the paper money may be extracted in order to further reduce unnecessary processing.
• a center of the paper money to be used as a reference point is calculated to check a position of the portion that characterizes each denomination.
• a direction and a distance are calculated based on the center to calculate position coordinates, and an area of a corresponding position is extracted.
• a specific image is an image of a characterizing area may be a portion or a plurality of portions.
• input data is generated to represent the extracted specific image for a function that will be described later. All pixel values of the specific image may be generated as input data or the specific image may be processed to generate input data. If all pixel values of the specific image are generated as the input data, the specific image may be allocated to a frame having a predetermined standard pixel size so as to input the specific image into the function that will be described later. Pixels of the frame are quantitated to be assigned pixel values and arranged as a series of numeral sequences. For example, values "0" through "255" expressed as gray scales are defined as the quantitated pixel values.
• the image allocated to the frame may be divided into blocks having predetermined sizes, and pixel values of the blocks may be averaged. Alternatively, pixel values in horizontal or vertical directions of the image of the frame may be averaged. If pixel values are averaged to generate input data, an amount of data may be reduced. If pixel values are used in original form to generate input data, more precise data may be generated. Input data arranged in a series of numeral sequences is generated from the specific image. In operation S40, a neural network function is applied. In other words, the neural network function is applied to the input data obtained in operation S30.
• a neural network is the known art used for the recognition of letters, the recognition of patterns, or artificial intelligence, and thus its detailed description will be omitted.
• Combinations of upper/left and lower/right portions of front and back surfaces of each denomination of paper money are formed to be references for discriminating denominations to perform operations S20 and S30 with respect to a provided image so as to generate standard data corresponding to each of the combinations.
• Standard data is provided to and learnt by the neural network in advance.
• a backpropagation algorithm, a Boltzman machine learning method, or a simulated annealing learning method may be used for the neural network to learn the standard data. If the input data is input to the neural network function after leaning of the standard data, probability values corresponding to the combinations are output.
• operation S50 a determination is made as to whether an error is present. If it is determined in operation S50 that an error is not present or an error detection function is not given, a denomination corresponding to the highest probability value of the probability values output in operation S40 is output.
• operation S60 a determination is made as to whether recognition of a denomination is valid using the probability values output in operation S40. If it is determined in operation S60 that the recognition of the denomination is not valid, an error signal is output.
• FIG. 3 A process of detecting an error through a determination of validity is schematically illustrated in FIG. 3.
• input data is input into a neural network function, and probability values of combinations of each denomination of paper money are output.
• the probability values are arranged in a descending order so that highest and second highest probability values can be used in a determination as to whether a recognition of a denomination is valid. If the highest probability value is not more than or equal to a predetermined reference probability value, it is determined that an error is present in the recognition of the denomination. If the first probability value is more than or equal to the predetermined reference probability value, the first probability value is compared with the second probability value.
• a difference between the highest and second highest probability values is within a predetermined range, recognition of a denomination depending on the probability values may not be reliable. Thus, it is determined that an error is present in the recognition of the denomination. If the highest probability value exceeds the predetermined reference probability value and the difference between the highest and second highest probability values is not within the predetermined range, it is determined that the recognition of the denomination is reliable.
• the predetermined reference probability value and the allowed difference between the highest and second highest probability values are preset to predetermined values. The predetermined reference probability value and the allowed difference between the highest and second highest probability values are related to a denomination recognition rate and determination validity. If the allowed difference between the highest and second highest probability values is reduced, a frequency of error detection is reduced. If the allowed difference between the highest and second highest probability values is increased, a frequency of error detection is increased. If it is determined that Ihe errors are present during recognition of a denomination of paper money, error detection data is output.
• FIG. 4 is a schematic block diagram illustrating an apparatus for recognizing a denomination according to an embodiment of the present invention.
• a denomination recognizing apparatus 100 includes a preprocessor 110, a neural network function processor 120, an error detector 130, and a storage 140.
• the preprocessor 110 receives an image of paper money from an input unit 200 and processes the image.
• the neural network function processor 120 applies the processed image to a neural network.
• the error detector 130 detects an error present in a discrimination of a denomination.
• the storage 140 stores the processed image and standard data corresponding to each denomination.
• the denomination recognizing apparatus 100 receives the image of the paper money from the input unit 200, discriminates a denomination of the paper money, and outputs denomination recognition data and/or an error detection signal to an output unit 300.
• the preprocessor 110 obtains a scanned image of paper money from the input unit 200, extracts an outline of the paper money, calculates a center of the paper money, extracts an image of a portion that characterizes each denomination of the paper money based on the center, generates pixel values of the image as input data, and stores the input data in the storage 140.
• the neural network function processor 120 compares the input data to standard data of combinations corresponding to each denomination by applying a neural network function which has been learnt, outputs probability values corresponding to the standard data of the each denomination, and arranges the probability values in a descending order.
• the neural network function processor 120 outputs a denomination of standard data corresponding to a highest probability value to the output unit 300.
• the error detector 130 receives the probability values from the neural network function processor 120, calculates errors of the probability values to determine validity, and outputs the error detection signal to the output unit 300.
• the preprocessor 110 receives the image of the paper money from the input unit 200, converts the image into a digital image, and extracts a specific image which is an image of a specific portion.
• the preprocessor 110 generates input data using pixel values of the extracted specific image and stores the input data in the storage 140.
• the neural network function processor 120 reads the input data from the storage 140, inputs the input data in order for the neural network function to be applied thereto, arranges output function values in a descending order, outputs the output function values to the error detector 130 to determine whether a recognition of a denomination is valid, and if it is determined that the recognition of the denomination is valid, transmits a denomination corresponding to the output function values as recognition data to the output unit 300. Also, if it is determined that the recognition of the denomination is not valid, the error detector 130 transmits a denomination recognition error signal to the output unit 300.
• FIG. 5 is a cross-sectional view illustrating a configuration of a denomination recognizing paper money counter according to an embodiment of the present invention.
• the denomination recognizing paper money counter includes an inlet 10, a counter 20, an outlet 30, a display 40, a scanner 50, and a denomination recognizer 60. Paper money is put into the inlet 10.
• the counter 20 counts the number of pieces of paper money.
• the outlet 30 discharges the counted paper money.
• the display 40 displays information regarding the counted paper money.
• the scanner 50 scans an image of the paper money.
• the denomination recognizer 60 recognizes a denomination of the paper money.
• the inlet 10 has a shape so as to accommodate a plurality of pieces of paper money.
• the counter 20 counts a number of the plurality of pieces of paper money.
• a roller that is rotating separates each piece of paper money from the plurality of pieces of paper money to count the number of the plurality of pieces of paper money.
• the outlet 30 has a shape of a stand case in which each of the counted plurality of pieces of paper money is discharged and accumulated.
• the display 40 is a display window displaying denominations of the plurality of pieces of paper money and information regarding the counted paper money.
• the scanner 50 includes an image sensor scanning images of the plurality of pieces of paper money.
• the denomination recognizer 60 recognizes denominations using the images extracted by the scanner 50.
• the denomination recognizer 60 includes a function processor, a preprocessor, and a storage.
• the function processor recognizes denominations using a neural network function.
• the preprocessor processes the extracted images to be input into the function processor to generate input data.
• the storage stores the input data and data of the function processor.
• the operation of the denomination recognition paper money counter will now be described. If a stack of paper money is input through the inlet 10, the scanner 50 extracts images of the paper money. The extracted images are transmitted to the denomination recognizer 60, and the paper money which has passed the scanner 50 moves to the counter 20.
• the denomination recognizer 60 discriminate denominations of the transmitted images and transmits information regarding the denominations to the display 40.
• the paper money moved to the counter 20 is counted and discharged to the outlet 30 to be accumulated as a stack of paper money.
• information as to the counted paper money is transmitted to the display 40.
• the display 40 converts the information transmitted from the denomination recognizer 60 and the counter 20 into information which can be checked by a user and displays the converted information.
• a method of recognizing a denomination of paper money including: receiving an image of the paper money including figures and letters in order to extract an image of a specific portion which characterizes the denomination; allocating an image of the specific portion to an area having a predetermined number of pixels, converting values of quantitated pixels into numerical values, and arranging the numerical values in a sequence to generate input data; inputting the input data into a neural network which has learnt a plurality of pieces of standard data corresponding to various denominations of paper money to allow the input data to be compared with the plurality of pieces of standard data and outputting probability values corresponding to a number of cases of each denomination; and arranging the probability values output from the neural network in a descending order, selecting a case corresponding to standard data having the highest probability value, and outputting a denomination corresponding to the selected case as recognition data.
• the method may further include determining whether an error is present in the recognizing of a denomination of paper money by using the highest and second highest probability values of the probability values and outputting error detection data in order to determine a validity of a recognition of a denomination.
• the first probability value is less than or greater than a predetermined reference value and a difference between the first probability value and the second probability value is within a predetermined range, it is determined that the error is present.
• the plurality of pieces of standard data may be obtained through combinations of upper/left and lower/right portions of front and back surfaces of each denomination of paper money.
• An image of the specific portion may be divided into a plurality of blocks having predetermined sizes, pixel values of the blocks may be averaged, and input data may be generated using average values of the blocks.
• the receiving of an image of paper money including figures and letters in order to extract an image of a specific portion which characterizes the denomination may include: obtaining the image of the paper money; extracting an outline of the paper money of the obtained image; and extracting an area in a predetermined position as an image of the specific portion based on a center of the image.
• an apparatus for recognizing a denomination of paper money including: a preprocessor receiving an image of paper money including figures and letters, extracting an image of a portion characterizing the denomination, allocating the image to an area having a predetermined number of pixels, converting values of quantitated pixels of the area into numerical values, and arranging the numerical values in a sequence to generate input data; a function processor inputting the input data into a neural network which has learnt a plurality of pieces of standard data corresponding to various denominations of the paper money to allow the input data to be compared with the plurality of pieces of standard data, outputting probability values depending on a number of cases corresponding to each denomination, arranging the probability values in a descending order, selecting a case corresponding to standard data having the highest probability value, and outputting a denomination corresponding to the case as recognition data; and a storage storing the input data and the standard data preprocessed by the preprocessor.
• the apparatus may further include an error detector determining whether an error is present by using the highest and second highest probability values of the probability values output from the function processor and outputting error detection data in order to determine a validity of a recognition of the denomination of paper money.
• a denomination recognizing paper money counter including an inlet into which paper money is put, a counter counting the number of pieces of paper money, an outlet discharging the paper money, and a display displaying information regarding the counted paper money, including: a scanner scanning an image of the paper money put through the inlet; a preprocessor receiving the image of the paper money through the scanner, extracting an image of a portion characterizing a denomination, allocating the image of the portion characterizing the denomination to an area having a predetermined number of pixels, converting values of quantitated pixels of the area into numerical values, and arranging the numerical values in a sequence to generate input data; a function processor inputting the input data into a neural network which has learnt a plurality of pieces of standard data corresponding to various denominations of paper money to allow the input data to be compared with the plurality of pieces of standard data, outputting probability values depending on a number of cases of each of the denominations, arranging the probability values in a descending order, selecting

Landscapes

• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Engineering & Computer Science (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Inspection Of Paper Currency And Valuable Securities (AREA)
• Image Analysis (AREA)

Applications Claiming Priority (2)

Publications (1)

Family

ID=37669034

Family Applications (1)

Country Status (2)

Cited By (3)

Families Citing this family (6)

Citations (4)

• 2005
  • 2005-07-21 KR KR1020050066498A patent/KR100718728B1/ko active IP Right Grant
• 2006
  • 2006-07-21 WO PCT/KR2006/002878 patent/WO2007011187A1/en active Application Filing

Patent Citations (4)

Also Published As

Similar Documents

Legal Events