Optical coin discrimination systems and methods for use with consumer-operated kiosks and the like

• US 9,594,982 B2
• Filed: 04/08/2015
• Issued: 03/14/2017
• Est. Priority Date: 06/05/2012
• Status: Active Grant

• Current Assignee: Coinstar Asset Holdings, LLC
• Original Assignee: Coinstar, LLC
• Inventors: Borg, Jeffrey Allan, Martin, Douglas A., Harrington, Timothy P.
• Primary Examiner(s): Bayat, Ali
• Application Number:
  US14/681,434
• Publication Number:
  US 20150235107A1
• Time in Patent Office: 706 Days
• Field of Search: 382/136
• US Class Current: 1/1
• CPC Class Codes: G06F 18/2323 based on graph theory, e.g. minimum spanning trees [MST] or graph cuts
• CPC Class Codes: G06V 10/431 Frequency domain transformation; Autocorrelation
• CPC Class Codes: G06V 20/66 Trinkets, e.g. shirt buttons or jewellery items recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 20/80 Recognising image objects characterised by unique random patterns
• CPC Class Codes: G07D 5/02 Testing the dimensions, e.g. thickness, diameter; Testing the deformation

Abstract

Systems and associated methods for optical coin discrimination are disclosed herein. In one embodiment, a method for discriminating coins includes obtaining a digital image of a coin, identifying the outline of the coin using a suitable algorithm, and determining the diameter of the coin using the outline of the coin. The method of this embodiment further includes 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 diameter of the coin, spectral peak location, spectral peak intensity of the coin and/or other aspects of the coin can then be compared to known values for different coins to discriminate the coin.

Claims

1. A method for identifying coins, the method comprising:

obtaining an image of a coin;

generating a rectangular image from the image of the coin;

based on the rectangular image of the coin, generating a 2D image of spectral features of the coin using a 2D spectral transform;

identifying an intensity of one of the spectral features; and

comparing the intensity of one of the spectral features to at least one known coin property.

2. The method of claim 1 wherein obtaining the image of the coin includes obtaining a digital image of the coin.

3. The method of claim 2 wherein the first image of the coin is a digital image, the method further comprising:

converting the digital image of the coin to a gray scale image of the coin.

4. The method of claim 1 wherein obtaining the image of the coin includes obtaining the image in response to a signal generated by a movement of the coin.

5. The method of claim 1 wherein generating a rectangular image includes applying a log-polar mapping to the image of the coin.

6. The method of claim 1 further comprising:

identifying a location of one of the spectral features in the 2D image; and

comparing the location of one of the spectral features to at least one known coin property.

7. The method of claim 1 wherein using the 2D spectral transform includes applying a Fourier transform.

8. The method of claim 1 wherein the spectral transform includes a Z-transform.

9. The method of claim 1 wherein generating a 2D image of spectral features of the coin includes applying a wavelet transform to the spectral features.

10. The method of claim 1, further comprising:

comparing at least one aspect of the image of the coin to at least one known coin property.

11. The method of claim 10 wherein the at least one coin property is a coin diameter.

12. The method of claim 1, further comprising:

identifying an outline of the coin.

13. The method of claim 12 wherein identifying the outline of the coin includes applying a Canny edge detection method to the image of the coin.

14. The method of claim 12 wherein identifying the outline of the coin includes applying at least one of Hough, Marr-Hildreth, Deriche, and Phase Congruency edge detection method to the image of the coin.

15. The method of claim 12, further comprising:

setting first image pixel values to zero outside the outline of the coin.

16. The method of claim 12, further comprising:

applying a Gaussian filter to the image of the coin.

17. A method for discriminating coins, the method comprising:

obtaining an image of a coin;

identifying an outline of the coin from the image of the coin;

generating a rectangular image from the image of the coin by a log-polar mapping;

performing a 2D spectral transform of the rectangular image to generate a 2D image of spectral features; and

discriminating the coin by;

identifying at least one of a location and an intensity of the spectral peak in the 2D image of spectral features, and

comparing at least one of the location and the intensity of the spectral peak in the 2D image of spectral features to at least one known coin property.

18. The method of claim 17 wherein obtaining the image of the coin includes obtaining the image of the coin in response to a signal generated by a coin movement.

19. The method of claim 17 wherein obtaining the image of the coin includes obtaining the image of the coin by a digital camera.

20. The method of claim 17, further comprising:

determining a diameter of the coin from the image of the coin.

21. A consumer operated coin counting apparatus comprising:

a coin input region configured to receive a plurality of coins;

a camera configured to capture images of individual coins;

means for generating 2D spectral images based on the images of the coins using a 2D spectral transform; and

means for discriminating the coins by;

identifying at least one of a location and an intensity of a spectral peak in the 2D spectral images, and

comparing at least one of the location and the intensity of the spectral peak in the 2D spectral images to at least one known coin property.

22. The apparatus of claim 21, further comprising means for comparing at least one aspect of the images of individual coins to at least one known coin property.

23. The apparatus of claim 21, further comprising means for generating log-polar images from the images of individual coins.

24. The apparatus of claim 21, further comprising means for detecting outline of the coins.

25. The apparatus of claim 21, further comprising means for detecting diameter of the coins.

26. A non-transitory computer-readable medium whose contents cause a computer to discriminate coins, the coins being discriminated by a method comprising:

receiving multiple coins;

capturing an image of a coin;

generating a 2D spectral image based on the image of the coin; and

discriminating the coins by;

identifying at least one of a location and an intensity of a spectral peak in the 2D spectral image, and

comparing at least one of the location and the intensity of the spectral peak to a known coin property.

27. The non-transitory computer readable medium of claim 26 wherein the method further comprises accepting or rejecting the coin based on results of discriminating.

28. The non-transitory computer readable medium of claim 26 wherein the method further comprises generating a second image from the coin using a log-polar mapping.

29. The non-transitory computer readable medium of claim 26 wherein generating the 2D spectral image includes a Fourier transform.