Identifying coins from scrap

1. A method comprising:

capturing, by a camera, visual image data of each piece of a collection of materials comprising monetary coins and pieces that are not monetary coins;

classifying certain pieces of the collection of materials as monetary coins as a function of visual characteristics obtained from the captured visual image data, wherein the visual characteristics are unique to monetary coins; and

classifying a remainder of the pieces of the collection of materials as not monetary coins, wherein the classifying of the collection of materials is performed with a neural network implementing one or more machine learning algorithms previously trained to recognize the visual characteristics unique to monetary coins.

2. The method as recited in claim 1 , further comprising sorting by an automated sorting device the certain pieces of the collection of materials classified as monetary coins from the remainder of the pieces of the collection of materials classified as not monetary coins.

3. The method as recited in claim 1 , further comprising classifying pieces of the collection of materials having a circular shape and also having a hole formed therethrough as not monetary coins.

4. The method as recited in claim 1 , wherein the classifying certain pieces of the collection of materials as monetary coins includes classifying the monetary coins into different denominations as a function of the visual characteristics.

5. The method as recited in claim 1 , wherein the one or more machine learning algorithms perform the classifying of the collection of materials as a function of a knowledge base of parameters configured during a training stage to recognize the visual characteristics unique to monetary coins.

6. The method as recited in claim 5 , wherein the training stage comprises processing a control sample of a plurality of one or more denominations of monetary coins through the neural network in order to create the knowledge base.

7. The method as recited in claim 6 , wherein the control sample includes a damaged denomination of monetary coin that possesses a geometric shape that is altered relative to an undamaged version of the denomination of monetary coin.

8. The method as recited in claim 1 , wherein the visual characteristics unique to monetary coins include features other than geometric shapes and dimensions particular to monetary coins.

9. A computer program product stored on a computer readable storage medium, which when executed by a data processing system, performs a process for classifying materials, comprising:

receiving visual image data of each piece of a collection of materials comprising pieces that are monetary coins and pieces that are not monetary coins;

classifying certain pieces of the collection of materials as monetary coins as a function of visual characteristics captured from the visual image data, wherein the visual characteristics are unique to monetary coins; and

classifying a remainder of the pieces of the collection of materials as not monetary coins, wherein the classifying of the collection of materials is performed with a neural network implementing one or more machine learning algorithms previously trained to recognize the visual characteristics unique to monetary coins.

10. The computer program product as recited in claim 9 , wherein the computer readable storage medium, which when executed, comprises sending to an automated sorting device information regarding the classifications used by the automated sorting device to sort the certain pieces classified as monetary coins from the remainder of pieces classified as not monetary coins.

11. The computer program product as recited in claim 9 , wherein the computer readable storage medium, which when executed, comprises classifying a piece of the collection of materials having a circular shape and size similar to monetary coins as not monetary coins when the piece does not possess other visual characteristics unique to monetary coins.

12. The computer program product as recited in claim 9 , wherein the one or more machine learning algorithms are configured to perform the classifying of the collection of materials as a function of a knowledge base of parameters configured during a training stage to recognize the visual characteristics unique to monetary coins, wherein the training stage comprises processing a control sample of a plurality of one or more denominations of monetary coins in order to create the knowledge base.

13. The computer program product as recited in claim 12 , wherein the control sample includes a damaged denomination of monetary coin that possesses a geometric shape that is altered relative to an undamaged version of the denomination of monetary coin.

14. The computer program product as recited in claim 9 , wherein the visual characteristics unique to monetary coins include features other than geometric shapes and dimensions particular to monetary coins.

15. A system comprising:

a camera suitable for capturing image data of each piece of a collection of shredded end-of-life vehicle scrap pieces comprising pieces having irregular shapes and sizes that includes monetary coins and scrap pieces that are not monetary coins; and

a machine learning system implementing one or more machine learning algorithms configured to utilize the captured image data to classify each of the pieces as either a monetary coin or a scrap piece that is not a monetary coin.

16. The system as recited in claim 15 , wherein the one or more machine learning algorithms are configured to classify each of the pieces as either a monetary coin or a scrap piece that is not a monetary coin as a function of a knowledge base previously generated during a training stage, wherein the knowledge base represents visual characteristics unique to monetary coins.

17. The system as recited in claim 16 , wherein during the training stage, the machine learning system is configured to process image data captured from a control sample of a plurality of monetary coins in order to create the knowledge base.

18. The system as recited in claim 17 , wherein the control sample includes a damaged denomination of monetary coin that possesses a geometric shape that is altered relative to an undamaged version of the denomination of monetary coin.

19. The system as recited in claim 15 , wherein the one or more machine learning algorithms are configured to classify a scrap piece as not a monetary coin even when the piece has a geometric shape substantially similar to that of a monetary coin.

20. The system as recited in claim 15 , further comprising an automated sorting device suitable for physically separating the pieces classified as a monetary coin from the pieces classified as not a monetary coin.

21. The system as recited in claim 15 , further comprising a conveyor system suitable for moving the collection of end-of-life vehicle scrap pieces past the camera.

22. The system as recited in claim 15 , wherein the one or more machine learning algorithms are configured to classify certain pieces of the collection of end-of-life vehicle scrap pieces as monetary coins of a first denomination and certain pieces of the collection of end-of-life vehicle scrap pieces as monetary coins of a second denomination, wherein the classifications are performed as a function of the processing by the one or more machine learning algorithms of the captured image data.

23. The system as recited in claim 15 , wherein the visual characteristics unique to monetary coins include features other than geometric shapes and dimensions particular to monetary coins.

24. A method comprising:

capturing, by a camera, visual image data of each piece of a collection of materials comprising monetary coins and pieces that are not monetary coins;

classifying certain pieces of the collection of materials as monetary coins as a function of visual characteristics obtained from the captured visual image data, wherein the visual characteristics are unique to monetary coins; and

classifying a remainder of the pieces of the collection of materials as not monetary coins, wherein the classifying certain pieces of the collection of materials as monetary coins as a function of visual characteristics obtained from the captured visual image data further comprises classifying a certain piece of the collection of materials as a monetary coin as a function of visual characteristics obtained from the captured visual image data when the certain piece possesses a geometric shape that is altered relative to an undamaged version of a monetary coin.

25. A method comprising:

capturing, by a camera, visual image data of each piece of a collection of materials comprising monetary coins and pieces that are not monetary coins;

classifying certain pieces of the collection of materials as monetary coins as a function of visual characteristics obtained from the captured visual image data, wherein the visual characteristics are unique to monetary coins; and

classifying a remainder of the pieces of the collection of materials as not monetary coins, wherein the remainder of the pieces of the collection of materials classified as not monetary coins comprise shredded end-of-life vehicle scrap pieces having irregular shapes and sizes.

26. A computer program product stored on a computer readable storage medium, which when executed by a data processing system, performs a process for classifying materials, comprising:

receiving visual image data of each piece of a collection of materials comprising pieces that are monetary coins and pieces that are not monetary coins;

classifying certain pieces of the collection of materials as monetary coins as a function of visual characteristics captured from the visual image data, wherein the visual characteristics are unique to monetary coins; and

classifying a remainder of the pieces of the collection of materials as not monetary coins, wherein the remainder of the pieces of the collection of materials classified as not monetary coins comprise shredded end-of-life vehicle scrap pieces having irregular shapes and sizes.