Recycling coins from scrap

• US 10,625,304 B2
• Filed: 03/19/2019
• Issued: 04/21/2020
• Est. Priority Date: 04/26/2017
• Status: Active Grant

• Current Assignee: Sortera Technologies Incorporated
• Original Assignee: UHV Technologies Incorporated
• Inventors: Kumar, Nalin, Garcia, Jr., Manuel Gerardo, Lowe, Ronnie Kip
• Primary Examiner(s): Fox, Charles A
• Assistant Examiner(s): Kumar, Kalyanavenkateshware
• Application Number:
  US16/358,374
• Publication Number:
  US 20190210067A1
• Time in Patent Office: 399 Days
• CPC Class Codes: B07B 13/003 Separation of articles by differences in their geometrical form or by difference in their physical properties, e.g. elasticity, compressibility, hardness
• CPC Class Codes: B07B 13/18 Control
• CPC Class Codes: B07C 5/342 according to optical properties, e.g. colour according to radiation transmittivity B07C5/3416
• CPC Class Codes: G06F 18/2413 based on distances to training or reference patterns
• CPC Class Codes: G06T 2207/30136 Metal
• CPC Class Codes: G06T 2207/30141 Printed circuit board [PCB]
• CPC Class Codes: G06T 7/0006 using a design-rule based approach
• CPC Class Codes: G06V 10/46 Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features colour feature extraction G06V10/56
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/82 using neural networks
• CPC Class Codes: G06V 20/66 Trinkets, e.g. shirt buttons or jewellery items recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 2201/06 Recognition of objects for industrial automation

Abstract

A material sorting system sorts materials utilizing a vision system that implements a machine learning system in order to identify or classify each of the materials, which are then sorted into separate groups based on such an identification or classification determining that the materials have a specified geometric shape. Such a system can sort monetary coins or other valuable metals from other forms of scrap.

Claims

1. A method comprising:

capturing, by a camera, image data of each piece of a heterogeneous mixture of materials moving in a stream past the camera, wherein the materials in the heterogeneous mixture of materials have various different shapes including one or more different geometric shapes;

classifying the materials that have one or more specified geometric shapes into a first classification;

classifying the materials that do not have the one or more specified geometric shapes into a second classification; and

sorting by an automated sorting device the materials classified into the first classification from the materials classified into the second classification, wherein the materials having the specified geometric shape include monetary coins, wherein the classifying of the materials is performed with a machine learning system implementing one or more machine learning algorithms that have been previously trained to recognize one or more physical characteristics of one or more denominations of the monetary coins.

2. The method as recited in claim 1, wherein materials having a circular shape and also having a hole formed therein are not classified as monetary coins.

3. The method as recited in claim 1, wherein the classifying the materials that have one or more specified geometric shapes into the first classification includes classifying the monetary coins into different denominations.

4. The method as recited in claim 1, wherein the second classification includes materials that are not monetary coins.

5. The method as recited in claim 1, wherein the one or more machine learning algorithms perform the classifying of the materials as a function of a knowledge base of parameters configured during a training stage to visually recognize the one or more physical characteristics of the one or more denominations of the 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 machine learning system 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. A method comprising:

capturing, by a camera, image data of each piece of a heterogeneous mixture of materials moving in a stream past the camera, wherein the materials in the heterogeneous mixture of materials have various different shapes including one or more different geometric shapes;

classifying the materials that have one or more specified geometric shapes into a first classification;

classifying the materials that do not have the one or more specified geometric shapes into a second classification; and

sorting by an automated sorting device the materials classified into the first classification from the materials classified into the second classification, wherein the first classification is monetary coins and specified jewelry.

9. The method as recited in claim 8, wherein the classifying of the materials is performed with a machine learning system implementing one or more machine learning algorithms that have been previously trained during a training stage to visually recognize one or more physical characteristics of the monetary coins and specified jewelry, wherein the training stage comprises processing a control sample of a plurality of monetary coins and specified jewelry through the machine learning system.

10. A system comprising:

a machine learning system implementing one or more machine learning algorithms that have been previously trained to recognize one or more physical characteristics of one or more denominations of monetary coins;

a camera configured to capture image data of each piece of a heterogeneous mixture of materials that includes the one or more denominations of monetary coins and pieces that are not monetary coins;

the machine learning system configured to classify certain pieces of the heterogeneous mixture of materials as the one or more denominations of monetary coins as a function of a processing by the one or more machine learning algorithms of the captured image data; and

an automatic sorting device configured to sort the certain pieces of the heterogeneous mixture of materials classified as the one or more denominations of monetary coins from a remainder of the heterogeneous mixture of materials.

11. The system as recited in claim 10, further comprising a sieve for separating the heterogeneous mixture of materials having a size less than a predetermined size before the capturing of the image data.

12. The system as recited in claim 10, wherein the machine learning system is configured to classify certain pieces of the heterogeneous mixture of materials as monetary coins of a first denomination and certain pieces of the heterogeneous mixture of materials 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, and wherein the automatic sorting device is configured to sort the monetary coins of the first denomination from the monetary coins of the second denomination.

13. The system as recited in claim 10, wherein the one or more machine learning algorithms perform the classifying of the materials as a function of a knowledge base of parameters configured during a training stage to visually recognize the one or more physical characteristics of the one or more denominations of monetary coins, wherein the training stage comprises processing a control sample of a plurality of one or more denominations of monetary coins through the machine learning system in order to create the knowledge base, wherein the control sample only includes monetary coins of the one or more denominations.

14. A computer program product stored on a computer readable storage medium, which when executed, performs a method for classifying materials for sorting, comprising:

receiving image data of each piece of a heterogeneous mixture of materials moving in a stream past a vision system camera, wherein the materials in the heterogeneous mixture of materials have various different shapes including one or more different closed geometric shapes;

classifying the materials that have a specified closed geometric shape into a first classification designated as monetary coins;

classifying the materials that do not have the specified closed geometric shape into a second classification, wherein materials composed of electrical box knockouts are classified into the second classification; and

sending to an automated sorting device information regarding the classifications so that the automated sorting device can sort the materials classified into the first classification from the materials classified into the second classification, wherein the one or more different closed geometric shapes are selected from a group consisting of circles and polygons.

15. The computer program product as recited in claim 14, wherein materials having a circular shape and also having a hole formed therein are classified into the second classification.