DIGITAL IMAGE COIN DISCRIMINATION FOR USE WITH CONSUMER-OPERATED KIOSKS AND THE LIKE
Systems and associated methods for coin discrimination are disclosed herein. Disclosed methods for discriminating coins include recognizing strings of alphanumerical characters of the coin using Optical Character Recognition (OCR). The methods can include recognizing colors and/or reflectivity of the coin using, for example, pixel thresholding algorithms. The methods can further include adding a line to an image of the coin, and measuring angles between the line and the edges on the coin. The methods can also include generating a rectangular image of the coin using, for example, a log-polar transform, generating a series of, for example, Fourier transforms from the rectangular image, and identifying spectral peak locations and intensities in the Fourier transform results. The results of the OCR, color/reflectivity recognition, angle measurement, spectral peak location, spectral peak intensity of the coin and/or other features or aspects of coins can then be compared to known values for different coins to discriminate the coins.
1 . A computer-implemented method for identifying coins, the method comprising:
obtaining an image of a coin with a camera;
identifying at least one flat area in the image with a processor; and
discriminating the coin with the processor by comparing the at least one flat area to a stored property of a known coin.
2 . The method of claim 1 wherein the image is a first digital image, the method further comprising:
generating a second digital image from the first digital image, wherein the second digital image is a line image, and wherein identifying at least one flat area is performed at least partially on the second digital image.
3 . The method of claim 2 wherein identifying at least one flat area is based on detecting at least one portion of the second digital image that is free of lines.
4 . The method of claim 2 , further comprising:
converting the first digital image of the coin to a gray scale image.
5 . The method of claim 1 wherein the digital image is obtained in response to a signal generated by a coin movement.
6 . The method of claim 1 wherein the image is obtained by a digital camera running at a selected frame rate.
7 . A computer-implemented method for identifying coins, the method comprising:
obtaining a digital image of a coin with a camera;
performing a routine with a processor to identify a string of alphanumerical characters in the image;
performing Optical Character Recognition (OCR) with the processor to recognize the string; and
discriminating the coin by comparing the string of alphanumerical character to a stored property of a coin.
8 . The method of claim 7 wherein the image is a first digital image, the method further comprising:
generating a second digital image from the first digital image, wherein the second digital image is a log-polar mapping of the first digital image, and wherein identifying a string of alphanumerical characters is performed at least partially on the second digital image.
9 . The method of claim 7 , further comprising rotating the digital image.
10 . The method of claim 7 , further comprising
measuring a distance between at least two aspects in the digital image.
11 . The method of claim 7 wherein the string is a first string, the method further comprising:
identifying a second string of alphanumerical characters in the digital image; and
recognizing the second string based on performing the OCR.
12 . The method of claim 7 , further comprising:
performing a routine to identify a diameter or a thickness of the coin.
13 . The method of claim 8 , further comprising:
performing a Fourier transform of the second digital image to generate a transformed image; and
discriminating the coin by comparing at least one aspect of the transformed image to a stored property of a coin.
14 . The method of claim 13 wherein the at least one aspect is intensity of a peak in the transformed image.
15 . The method of claim 13 wherein the at least one aspect is location of a peak in the transformed image.
16 . The method of claim 7 , further comprising:
determining a first color in a first region of the digital image;
determining a second color in a second region of the digital image;
discriminating the coin by comparing at least one of the first and second colors to a stored property of a coin.
17 . The method of claim 16 wherein determining a first color and determining a second color is based on pixel value thresholding.
18 . A consumer operated coin counting system comprising:
a coin input region configured to receive a plurality of coins;
a digital camera configured to capture first digital images of individual coins;
means for identifying at least one flat area in the first digital images; and
means for discriminating the coin by comparing the at least one flat area to a stored property of a coin.
19 . The system of claim 18 , further comprising:
means for generating second digital images from the first digital images, wherein the second digital images are line images, and wherein identifying at least one flat area is based on detecting at least one portion of the second digital images that is free of lines.
20 . The system of claim 19 , further comprising:
means for generating third digital images from the second digital images using a log-polar mapping;
means for applying a Fourier-transform on the third digital images; and
means for discriminating the coin by comparing results of Fourier-transform to a stored property of a coin.
21 . The system of claim 18 , further comprising:
means for converting individual first digital images to individual gray scale image.
22 . The system of claim 18 , further comprising:
means for determining a diameter of the coin.
23 . The system of claim 18 , further comprising:
means for identifying aspects in the first digital images;
means for calculating distance between the aspects of the coin; and
means for discriminating the coin by comparing the distance to a stored property of a coin.
24 . A computer-readable medium whose contents cause a computer to discriminate coins, the coins being discriminated by a method comprising:
obtaining a digital image of a coin;
identifying a string of alphanumerical characters in the digital image;
recognizing the string based on Optical Character Recognition (OCR); and
discriminating the coin by comparing the string of alphanumerical character to a stored property of a coin.
25 . The computer readable medium of claim 24 , further comprising:
accepting or rejecting the coin based on results of discriminating.
26 . The computer readable medium of claim 24 , further comprising:
determining a first color in a first region of the digital image;
determining a second color in a second region of the digital image;
discriminating the coin by comparing at least one of the first and second colors to a stored property of a coin.
27 . The computer readable medium of claim 26 wherein determining a first color and determining a second color is based on pixel value thresholding.
28 . The computer readable medium of claim 29 wherein the digital image is a first digital image, further comprising:
generating a second digital image from the first digital image, wherein the second digital image is a line image;
identifying at least one edge in the second digital image;
adding an image of a line to the second digital image;
determining an angle between the at least one edge and the image of the line; and
discriminating the coin by comparing the angle to a stored property of a coin.
29 . The computer readable medium of claim 28 wherein the image of the line and the at least one edge intersect.
30 . The computer readable medium of claim 28 , further comprising:
rotating the second digital image.
31 . The computer readable medium of claim 24 , further comprising:
selecting a plurality of aspects in the digital image;
calculating a distance between at least two aspects; and
discriminating the coin by comparing the distance to a stored property of a coin.
32 . The computer readable medium of claim 24 , further comprising:
selecting a plurality of aspects in the digital image;
counting a number of aspects in the plurality of aspects; and
discriminating the coin by comparing the number to a stored property of coin.