CN112543680A

CN112543680A - Recovery of coins from waste

Info

Publication number: CN112543680A
Application number: CN201980043725.XA
Authority: CN
Inventors: N·库马; 小曼纽尔·G·加西亚; R·K·劳
Original assignee: Sotra Alloy Co Ltd
Current assignee: Sotra Alloy Co Ltd
Priority date: 2018-04-26
Filing date: 2019-03-19
Publication date: 2021-03-23
Also published as: WO2019209428A1; JP2021522070A; EP3784419A1; EP3784419A4

Abstract

A material sorting system that sorts materials using a vision system implementing a machine learning system to identify or classify each of the materials, then sorts the materials into separate groups based on such identification or classification that the materials are determined to have a specified geometry. Such a system can sort currency coins or other valuable metals from other forms of waste.

Description

Recovery of coins from waste

This application is a continuation-in-part application of U.S. patent application serial No. 15/963,755, which claims the benefit of U.S. provisional patent application serial No. 62/490,219, both of which are incorporated herein by reference.

Government licensing rights

This disclosure was made with U.S. government support under grant number DE-AR0000422 granted by the U.S. department of energy. The united states government may have certain rights in this disclosure.

Technical Field

The present disclosure relates generally to sorting of materials, and more particularly, to sorting certain values from waste materials.

Background

This section is intended to introduce various aspects of the art, which may be associated with exemplary embodiments of the present disclosure. This discussion is believed to be helpful in providing a framework to facilitate a better understanding of particular aspects of the present disclosure. Therefore, it should be understood that this section should be taken in this light, and not necessarily as an admission of prior art.

Recycling is the process of collecting and processing materials that would otherwise be discarded as waste and converting them into new products. Recycling is beneficial to the community and environment because it reduces the amount of waste sent to landfills and incineration plants, conserves natural resources, increases economic safety by developing domestic material sources, prevents pollution by reducing the need to collect new raw materials, and conserves energy. After collection, the recyclable item is typically sent to a material recovery facility to be sorted, cleaned, and processed into materials that are available for manufacturing.

It has been found that many motor vehicles designated for shredding and subsequent recycling processes have a relatively large number of currency coins located therein (such as between seats, under floor mats, etc.). At least one study estimates that there may be coins between approximately $ 10 and $ 15 per vehicle. Likewise, such vehicles may contain lost jewelry.

In addition, the motor vehicle includes a printed circuit board ("PCB") that contains recyclable valuable metals (e.g., copper, gold, silver, etc.).

Given the large number of vehicles recovered each year, there is a need in the recycling industry for a technique for recovering such valuable scrap pieces as a profitable byproduct of the normal vehicle recycling process. Furthermore, recently passed federal laws mandate that for certain coins, even if they are damaged, the U.S. government will pay for their face value.

Drawings

Fig. 1 illustrates a schematic diagram of a sorting system configured in accordance with an embodiment of the present disclosure.

Fig. 2 illustrates a flow chart of the operation of a sorting apparatus configured according to an embodiment of the present disclosure.

Fig. 3A shows visual images of various exemplary monetary coins.

Fig. 3B shows a visual image of an exemplary monetary coin intermixed with other scrap pieces.

Fig. 3C illustrates visual images of various exemplary jewelry pieces.

Fig. 3D shows a visual image of an exemplary jewelry piece mixed with other scrap pieces.

Fig. 4 illustrates a flow diagram configured in accordance with an embodiment of the disclosure.

FIG. 5 shows a block diagram of a data processing system configured in accordance with an embodiment of the present disclosure.

Fig. 6 shows a flow diagram of an exemplary configuration for a machine learning system, according to an embodiment of the present disclosure.

Detailed Description

Various detailed embodiments of the present disclosure are disclosed herein. However, it is to be understood that the disclosed embodiments are merely exemplary of the disclosure that may be embodied in various and alternative forms. The drawings are not necessarily to scale; some features may be exaggerated or minimized to show details of particular components. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a representative basis for teaching one skilled in the art to employ various embodiments of the present disclosure.

Embodiments of the present disclosure efficiently recover specified valuable pieces of waste (e.g., currency coins, jewelry, PCBs, copper, brass, etc.) from shredded waste (e.g., automotive (motor vehicle) waste) by using a machine learning based vision system as described herein.

As used herein, "material" may include any physical object, including but not limited to scrap pieces. Classes or types of materials may include: metals (ferrous and non-ferrous), metal alloys, currency coins, jewelry (e.g., rings, earrings, necklaces, bracelets, etc.), gold or silver flakes, buttons, electrical box knock-outs (knock-out), gaskets, plastics (including but not limited to PCB, HDPE, UHMWPE, and various colored plastics), rubber, foam, glass (including but not limited to borosilicate or soda-lime glass, and various colored glasses), ceramic, paper, cardboard, Teflon (Teflon), PE, bundling wires, coated insulated wires, rare earth elements, and the like. As used herein, the terms "scrap" and "scrap pieces" refer to pieces of material that are in a solid state. In the present disclosure, the terms "scrap," "scrap sheet," "material," and "sheet of material" may be used interchangeably.

As used herein, a heterogeneous mixture of materials refers to a collection of different individual classes or types of materials. As used herein, a homogeneous set of materials refers to a collection of individual materials of the same or substantially similar class or type.

The term "Zorba (Zorba)" is a generic term for shredded nonferrous metals, including but not limited to those derived from end-Of-life vehicles ("ELVs") or waste electronic and electrical equipment ("WEEE"), according to the definition in the nonferrous waste guide, issued by the Institute Of Scrap Recycling Industries, Inc. The waste recovery industry association ("ISRI") in the united states established the gaoba specification. In zoba, each scrap piece may be composed of a combination of non-ferrous metals (e.g., aluminum, copper, lead, magnesium, stainless steel, nickel, tin, zinc, in elemental or alloy (solid) form). Furthermore, the term "twist" shall refer to fragmented aluminum scrap. The twists may be produced by a float process whereby the aluminum scrap floats to the top as the heavier sheet of metal scrap sinks (e.g., in some processes, sand may be mixed in to change the density of the water in which the scrap is submerged).

As used herein, the terms "identify" and "classify" and the terms "identify" and "classify" may be used interchangeably. For example, according to certain embodiments of the present disclosure, a vision system (as further described herein) may be configured (e.g., with a machine learning system) to collect any type of information described below: this information may be used in a sorting system to selectively sort a material (e.g., scrap pieces) according to a set of one or more (user-defined) physical characteristics including, but not limited to, color, size, shape, texture, physical appearance, uniformity, hue, and/or manufacturing type of the material.

It should be noted that at least some of the materials to be sorted may have irregular sizes and shapes (see, e.g., fig. 3B and 3D). For example, such material (e.g., kibbles and/or twists) may have been previously run through some sort of shredder mechanism that chops the material into such irregularly shaped and sized pieces (production scrap pieces) that can then be fed onto a conveyor system.

Embodiments of the present disclosure will be described herein as sorting materials (e.g., scrap pieces) into such separate groups by physically depositing (e.g., ejecting) the materials (e.g., scrap pieces) into separate containers or bins according to a user-defined classification. As an example, in certain embodiments of the present disclosure, materials (e.g., scrap pieces) may be sorted into separate bins in order to separate designated valuable scrap pieces from other scrap materials. Such a piece of valuable scrap material designated (by a user of system 100) may be a coin of currency, jewelry (e.g., a ring, earring, necklace, bracelet, etc.), precious metal (gold, silver, platinum, copper, brass, etc.), or PCB (which may contain valuable metal (e.g., gold, silver, copper)).

Fig. 1 illustrates an example of an automated material sorting system 100 configured in accordance with various embodiments of the present disclosure, the automated material sorting system 100 for automatically (i.e., without human manual intervention) sorting materials. In the following, embodiments of the present disclosure will be described as sorting scrap pieces, although such embodiments are applicable to sorting any type of material. The conveyor system 103 may be implemented to convey one or more streams of individual scrap pieces 101 through the sorting system 100 such that each of the individual scrap pieces 101 may be tracked, sorted, and sorted into predetermined desired groups. Such a conveyor system 103 may be implemented with one or more conveyor belts on which the slug 101 typically travels at a predetermined constant speed. However, certain embodiments of the present disclosure may be implemented using other types of conveyor systems (including vibratory conveyors and mechanical conveyors) and a system in which pieces of scrap are free-dropped past various components of a sorting system. Hereinafter, the conveyor system 103 will be referred to simply as the conveyor belt 103.

Further, while the illustration in fig. 1 depicts a single flow of scrap pieces 101 on a conveyor belt 103, embodiments of the present disclosure may be implemented as: where a plurality of such streams of scrap pieces pass through various components of sortation system 100 in parallel with one another, or a collection of scrap pieces deposited onto conveyor 103 in a random manner passes through various components of sortation system 100. Thus, certain embodiments of the present disclosure are capable of simultaneously tracking, sorting, and sorting a plurality of such streams of concurrently traveling scrap pieces or scrap pieces randomly deposited onto a conveyor belt. In accordance with embodiments of the present disclosure, the vision system tracks, sorts, and sorts the scrap pieces without requiring separation of the scrap pieces 101.

According to certain embodiments of the present disclosure, the slug 101 may be fed onto the conveyor belt 103 using some suitable feeding mechanism, whereby the conveyor belt 103 conveys the slug 101 through various components within the sortation system 100. In certain embodiments of the present disclosure, the conveyor belt 103 is operated by a conveyor belt motor 104 to travel at a predetermined speed. The predetermined speed may be programmable and/or may be adjustable by an operator in any well-known manner. Monitoring of the predetermined speed of the conveyor belt 103 may alternatively be performed with the belt speed detector 105. In certain embodiments of the present disclosure, control of the conveyor motor 104 and/or the belt speed detector 105 may be performed by an automated control system 108. Such an automatic control system 108 may operate under the control of the computer system 107 and/or may implement the functionality for performing automatic control in software within the computer system 107.

The conveyor belt 103 may be a conventional endless belt conveyor employing a conventional drive motor 104 adapted to move the conveyor belt 103 at a predetermined speed. A belt speed detector 105, which may be a conventional encoder, may be operatively coupled to the conveyor belt 103 and the automated control system 108 to provide information corresponding to the movement (e.g., speed) of the conveyor belt 103. Thus, by utilizing control of the conveyor drive motor 104 and/or the automated control system 108 (and alternatively including the belt speed detector 105), as will be described further herein, each of the scrap pieces 101 traveling on the conveyor belt 103 may be tracked by position and time (relative to the various components of the system 100) as they are identified, such that each scrap piece 101 may be activated/deactivated as it passes in proximity to the various components of the sortation system 100. As a result, the automated control system 108 is able to track the position of each of the scrap pieces 101 as the scrap pieces 101 travel along the conveyor belt 103.

According to certain embodiments of the present disclosure, after the slug 101 is received by the conveyor belt 103, a roller (tub) and/or a vibrator (not shown) may be used to separate individual slugs from the collection of slugs. According to alternative embodiments of the present disclosure, the scrap pieces may be positioned into one or more separate (i.e., single file) streams, which may be performed by an optional active or passive separator 106. As previously discussed, no separator need be incorporated or used. Rather, the conveyor system (e.g., conveyor belt 103) may simply convey the collection of scrap pieces that have been positioned on conveyor belt 103 in a random manner.

Referring again to fig. 1, embodiments of the present disclosure may use a vision system or optical recognition system 110 as a means to begin tracking each of the scrap pieces 101 as the scrap pieces 101 travel on the conveyor belt 103. The vision system 110 may use one or more stationary or real-time motion cameras 109 (which may include one or more three-dimensional cameras) to record the location (i.e., position and timing) of each of the scrap pieces 101 on the moving conveyor belt 103. The vision system 110 may be further configured to perform certain types of identification (e.g., sorting) of all or a portion of the scrap pieces 101. For example, such a vision system 110 may be used to obtain information about each of the scrap pieces 101. For example, the vision system 110 may be configured (e.g., with a machine learning system) to collect any type of information as described below: this information may be used in the system 100 to selectively sort the scrap pieces 101 according to a set of one or more (user-defined) physical characteristics including, but not limited to, color, size, shape, texture, overall physical appearance, uniformity, make-up, and/or type of manufacture of the scrap pieces 101. The vision system 110 captures images of each of the scrap pieces 101, for example, by using optical sensors, such as those used in typical digital cameras and video equipment. Such images captured by the optical sensor may then be stored as image data in a memory device. According to embodiments of the present disclosure, such image data represents an image captured within the light wavelength of the light (i.e., the wavelength of the light observable by the typical human eye). However, alternative embodiments of the present disclosure may use optical sensors configured to capture images of materials composed of wavelengths of light outside the visual wavelengths of the typical human eye.

Additionally, such a vision system 110 may be configured to determine which of the scrap pieces 101 are not of the sort to be sorted by the sorting system 100 (e.g., scrap pieces classified as a type other than the designated valuable scrap piece) and signal rejection of such scrap pieces. Such identified waste sheets 101 may be ejected using one of the mechanisms for physically moving the sorted waste sheets into the various bins as described herein.

Referring next to fig. 2, a system and process 200 for activating each of the automated sorting apparatus (e.g., sorting

apparatus

126, 127, 128, 129) for ejecting sorted waste pieces into sorting bins is shown. Such systems and processes 200 may be implemented in the automated control system 108 previously described with reference to fig. 1 or in an overall computer system (e.g., computer system 107) that controls the sorting system. In process block 201, a signal is received from the automated control system 108 that the designated and tracked scrap pieces are in position for sorting. In process block 202, it is determined whether the timing associated with the signal is equal to the current time. The system and process 200 determines whether the timing associated with the sorted waste pieces corresponds to an expected time at which the sorted waste pieces pass near a particular sorting apparatus (e.g., air jet, pneumatic plunger, paint brush plunger, etc.) associated with the sort associated with the sorted waste pieces. If the timing signals do not correspond, then a determination is made in process block 203 whether the signal is greater than the current time. If so, the system may return an error signal 204. In such a case, the system may not be able to eject the sheet into the appropriate bin. Once the system and process 200 determines that a sorted waste sheet is passing near the sorting equipment associated with the sort, it will activate the sorting equipment in process block 205 to eject the sorted waste sheet into the bin associated with the sort. This may be performed by activating a pneumatic plunger, a paint brush plunger, an air jet, etc. In process block 206, the selected sorting equipment is then deactivated.

As previously mentioned, the sorting apparatus may include any well-known mechanism for redirecting selected waste sheets to a desired location, including but not limited to ejecting waste sheets from a conveyor system into a plurality of sorting bins. For example, the sorting apparatus may use air jets, where each of the air jets is assigned to one or more of the categories. When one of the air jets (e.g., 127) receives a signal from the automatic control system 108, the air jet emits an air flow that causes the scrap pieces 101 to be ejected from the conveyor belt 103 into a sorting bin (e.g., 137) corresponding to the air jet. For example, a high-speed air valve (e.g., available from the Mark industry (Mac Industries)) may be used to provide an appropriate air pressure for the air jets that is configured to eject the scrap pieces 101 from the conveyor belt 103.

Although the example shown in fig. 1 uses air jets to eject the slug, other mechanisms may be used to eject the slug, such as: removing the scrap pieces from the conveyor by a robot; pushing the scrap pieces away from the conveyor (e.g., using a paint brush plunger); the presence of an opening (e.g. a trap door) in the conveyor belt, through which the scrap pieces can fall; separating the waste pieces into separate bins using one or more air jets as they fall from the edge of the conveyor belt; or use a robotic arm and gripping device to pick a designated scrap piece from the conveyor belt 103.

In addition to the

N sorting bins

136, 137, 138, 139 into which the scrap pieces 101 are ejected, the system 100 may also include a receptacle or bin 140 that receives scrap pieces 101 that are not ejected from the conveyor belt 103 into any of the

aforementioned sorting bins

136, 137, 138, 139. For example, when the sorting of the scrap pieces 101 is not determined (or simply because the sorting equipment fails to adequately eject one piece), the scrap pieces 101 may not be ejected from the conveyor belt 103 into one of the

N sorting bins

136, 137, 138, 139. Thus, bin 140 may serve as a default container into which unsorted waste pieces are dumped. Alternatively, bin 140 may be used to receive one or more sorted scrap pieces that are intentionally unassigned to any of the

N sorting bins

136, 137, 138, 139. For example, scrap pieces that are not classified as designated valuable scrap pieces may be allowed to pass into bin 140 in accordance with embodiments of the present disclosure.

According to certain embodiments of the present disclosure, a set of one or more air jets may be configured to direct scrap pieces classified as designated valuable scrap pieces into a first receptacle as they fall off the edge of the conveyor belt 103, while those scrap pieces not classified as designated valuable scrap pieces are allowed to fall only from the edge of the conveyor belt 103 into a separate second receptacle (e.g., bin 140). Alternatively, the reverse operation may be performed, in which scrap pieces classified as designated valuable scrap pieces are allowed to fall off only from the edges of the conveyor belt 103.

According to certain embodiments of the present disclosure, currency coins may be sorted separately based on their different denominations and thus sorted into separate bins accordingly.

Depending on the type of sorting desired for the scrap pieces, multiple sorts (e.g., certain different denominations of currency coins) may be mapped to a single sorting apparatus and associated sorting bin. In other words, there need not be a one-to-one correlation between sorting and sorting bins. For example, a user may desire to sort certain types or sorts of materials (e.g., one or more different denominations of currency coins, or both currency coins and copper and/or brass, etc.) into the same sorting bin. To accomplish this sorting, the same sorting apparatus may be activated to sort the scrap pieces 101 into the same sorting bin when the scrap pieces 101 are sorted to fall into a predetermined sort group (e.g., one or more different denominations of currency coins, or both currency coins and copper and/or brass, etc.). Such combinatorial sorting may be applied to produce any desired combination of sorted waste pieces. The mapping of the classifications may be programmed by a user (e.g., using a sorting algorithm operated by the computer system 107 (see, e.g., fig. 4)) to produce such desired combinations. In addition, the sorting of scrap pieces is user definable and is not limited to any particular known scrap piece sorting.

As non-limiting examples of the foregoing, the machine learning system of the present disclosure may be configured to sort two or more currency coin denominations separately for sorting into the same bin (e.g., one or more of

bins

136, 137, 138, 139), or to sort certain denominations (e.g., american coins) for sorting into the same bin with scrap pieces that are not sorted into currency coins.

In another non-limiting example of the foregoing, the machine learning system of the present disclosure may be configured to sort monetary coins and another denomination or type of value into a common bin. The other category(s) or type(s) of value(s) may be jewelry (e.g., a ring, earring, necklace component, bracelet component, etc., such as shown in fig. 3C), pieces of a specified category or type of metal (e.g., gold, silver, copper, brass, etc.), and/or any scrap pieces (e.g., PCBs that may contain copper, gold, or silver) that are identified by the machine learning system as containing certain specified metals. Such scrap pieces collected into a common bin may then be passed through system 100 again (or such scrap pieces may be conveyed to a second similar system similar to system 100, such as further disclosed herein) in order to sort out the collected valuable scrap pieces (e.g., between currency coins and copper and/or brass).

The conveyor system 103 may include an endless conveyor (not shown) such that unsorted scrap pieces (or scrap pieces of two or more types or types of materials for re-sorting) are returned to the beginning of the sorting system 100 to again run through the system 100. Further, because the system 100 is able to specifically track each slug 101 as it travels on the conveyor system 103, some sort device (e.g., sort device 129) may be implemented to eject slugs 101 (e.g., such as currency coins, jewelry, PCBs, and jewelry, etc.) that the system 100 has not yet recognized after a predetermined number of passes through the sort system 100.

In certain embodiments of the present disclosure, the conveyor belt 103 may be divided into a plurality of belts arranged in series, such as, for example, two belts, where a first belt conveys the scrap pieces through the vision system and a second belt conveys the scrap pieces from the vision system to the sorting apparatus. Further, such a second conveyor may be at a lower elevation than the first conveyor, such that the scrap pieces fall from the first conveyor onto the second conveyor.

As previously described, embodiments of the present disclosure may implement one or more vision systems (e.g., vision system 110) to identify, track, and/or sort scrap pieces. Such vision systems may be configured with one or more devices for capturing or acquiring images of the pieces of waste as they pass over the conveyor system. The apparatus may be configured to capture or acquire any desired wavelength range reflected by the waste sheet, including but not limited to visible light, infrared ("IR") light, ultraviolet ("UV") light. For example, the vision system may be configured with one or more cameras (still and/or video cameras, any of which may be configured to capture two-dimensional, three-dimensional, and/or holographic images) positioned near (e.g., above) the conveyor system such that a visual image of the scrap piece is captured as it passes through the vision system(s).

Regardless of the type(s) of the captured image of the scrap pieces, the image may then be sent to a computer system (e.g., computer system 107) for processing by a machine learning system in order to identify and/or classify each of the scrap pieces for subsequent sorting of the scrap pieces in a desired manner. Such machine learning systems may implement one or more of any well-known machine learning algorithm, including one that implements: neural networks (e.g., artificial neural networks, deep neural networks, convolutional neural networks, recurrent neural networks, autoencoders, reinforcement learning, etc.), fuzzy logic, artificial intelligence ("AI"), deep learning algorithms, deep structure learning hierarchical learning algorithms, support vector machines ("SVMs") (e.g., linear SVMs, non-linear SVMs, SVM regression, etc.), decision tree learning (e.g., classification and regression trees ("CART")), ensemble learning (e.g., ensemble learning, Random forest(s), bootstrap aggregation and Pasting (Bagging and compiling), patch and subspace (books and Subspaces), Boosting (Stacking), Stacking (Stacking), etc.), dimensionality reduction (e.g., projection, manifold learning, principal component analysis, etc.), and/or deep machine learning algorithms, such as those described and publicly available on the deeplearning Publications and hyperlinks to available software), the contents of which are incorporated by reference herein. Non-limiting examples of publicly available machine learning algorithms, software, and libraries that may be used in embodiments of the present disclosure include: python, OpenCV, inclusion, Theano, Torch, PyTorch, Pylearn2, Numpy, Blocks, TensorFlow, MXNet, Caffe, Lasagne, Keras, Chainer, Matlab Deep Learning (Deep Learning), CNTK, MatConvNet (Matlab toolkit implementing a convolutional neural network for computer vision applications), Deep Learning toolkit (Deep Learning toolkit) (Matlab toolkit for Deep Learning (from Rasmus Berg Palm)), BigDL, Cuda-Convnet (fast C + +/CUDA implementation of a convolutional (or more generally, feedforward) neural network), Deep Belief network (Deep Belief network), RNM, RNNLIB-RNNLIB, matrbm, depletering 4j, eblean. lsh, depmat, MShadow, Matplotlib, SciPy, CXXNET, Nengo-Nengo, Eblearn, CUDAMat, Gnmpy, three-way decomposition RBM and mcRBM, mPoT (Pyron code for training a model of a natural image using CUDAMat and Gumpy), ConvNet, Elektronn, NN, Neraldsigner, Opano-promoted Hebbian Learning (the ano Generalized Hebbian Learning), Apache Singa, Light, and SimpleN.

Machine learning typically occurs in two phases or periods. For example, first, because the sortation system 100 is not being used to perform the actual sorting of scrap pieces, training is performed off-line. According to certain embodiments of the present disclosure, a portion of system 100 may be used to train a machine learning system in which one or more sets of homogeneous scrap pieces (i.e., one or more denominations of currency coins (e.g., see fig. 3A), an exemplary set of rings, bracelets, necklaces, and/or earrings, an exemplary PCB scrap piece, or an exemplary scrap piece of a particular type of precious metal (e.g., gold, silver, copper, brass, etc.) are passed through vision system 10 using conveyor system 103 (each set of homogeneous scrap pieces is unsorted, but may be collected in a common bin (e.g., bin 140)). Alternatively, training may be performed at another location remote from the system 100, including using some other mechanism for collecting images of a homogeneous set of specified valuable scrap pieces.

Note that according to certain embodiments of the present disclosure, a homogenous set of monetary coins may be a collection of monetary coins of the same denomination (and therefore of the same shape, size, color, hue, etc.), or may be a collection of monetary coins of different denominations (and therefore of different shapes, sizes, colors, hues, etc.), but sharing at least one same or substantially the same physical characteristic such as shape (e.g., circular, polygonal). Further, according to certain embodiments of the present disclosure, because most monetary coins are substantially circular, this may be a particular physical characteristic that may be used by a machine learning system to sort and sort materials. Because there are some foreign coins that are not circular (e.g., have a polygonal shape), such specific non-circular shapes (but still have a substantially polygonal (e.g., octagonal) shape) may also be used by machine learning systems to sort and sort materials. For the purposes of describing various embodiments of the present disclosure, it should be understood that most currency coins have a closed geometric shape (e.g., circular, polygonal).

During this training phase, the machine learning algorithm(s) use image processing techniques well known in the art to extract features from the captured images. Non-limiting examples of training algorithms include, but are not limited to, linear regression, gradient descent, feed forward, polynomial regression, learning curves, canonical learning models, and logistic regression. During this training phase, the machine learning algorithm(s) may be configured to learn relationships between specified valuable scrap pieces (e.g., currency coins (which may have different denominations), rings, bracelets, necklaces, earrings, PCBs, etc.) and their features (e.g., as captured by the images, such as color, texture, hue, shape (e.g., circles, polygons), brightness, etc.) to create a knowledge base for the classification of heterogeneous mixtures of scrap pieces that are later received by the sorting system 100 for sorting currency coins from the heterogeneous mixtures of scrap pieces. According to certain embodiments of the present disclosure, such a knowledge base may include a requirement that waste pieces having a substantially circular and/or polygonal shape (e.g., within a predetermined threshold of substantially circular and/or polygonal shape, as coins may have been damaged to some extent in a vehicle or by an automobile shredder, such as shown by some of the coins in fig. 3A) be identified as currency coins. Such a knowledge base may include rejecting round scrap pieces having holes formed therein so as not to identify the metal washer as a coin of currency. Such a knowledge base may further include rejecting round scrap pieces having a certain color or hue (e.g., so as not to sort U.S. coins with other currency coins).

Such a knowledge base may include one or more libraries, where each library includes parameters used by the vision system 110 to sort and sort scrap pieces during the second stage or period. For example, one particular library may include parameters configured by the training phase to identify and classify monetary coins of a particular denomination. According to certain embodiments of the present disclosure, such a library may be input into the vision system, and then a user of the system 100 may be able to adjust certain ones of the parameters in order to adjust the operation of the system 100 (e.g., adjust how well the vision system identifies a particular denomination of money coin from a heterogeneous mixture of materials (e.g., see fig. 3B) has a threshold validity).

For example, FIG. 3A shows a captured or acquired image of an exemplary homogenous set of money coins that may be used during the preceding training phase. During the training phase, a plurality of such monetary coins (e.g., a homogenous set of one or more exemplary monetary coins of a specified denomination) as control samples may be delivered (e.g., by the conveyor system 103) through the vision system such that the machine learning system detects, extracts, and learns what features are visually representative of such exemplary monetary coins. In other words, an image of a currency coin such as that shown in fig. 3A may first pass through a training phase such that the machine learning system "learns" how to detect, identify and classify currency coins in a heterogeneous mixture of scrap pieces (e.g., such as that shown in fig. 3B and 3D). This creates a library of parameters specific to a given monetary coin.

One point to mention here is that the detected/extracted features are not necessarily simple colors, or intensities, or circular or polygonal shapes; they may be abstract representations that can only be expressed mathematically or not at all; however, during the training phase, the machine learning system parses all data to find patterns that allow for the classification of control samples (e.g., actual currency coins). The machine learning system may take a sub-portion of the captured scrap piece image and attempt to find correlations between predefined classifications (e.g., one or more various currency coin denominations).

According to certain embodiments of the present disclosure, the machine learning system may be configured such that it classifies those scrap pieces that are near circular, but not perfectly circular, as currency coins. For example, when currency coins contained within a refuse dump vehicle are processed (e.g., run through a shredder), they may be damaged (e.g., bent slightly or notched therein). Fig. 3A shows an example of some such damaged coins. The machine learning system may adjust its tolerance parameters to classify such scrap pieces as currency coins. For example, a scrap piece is classified as a coin of currency even if it is not perfectly circular or does not have a completely closed circular shape, but its overall size (e.g., diameter) and/or color, hue, texture, etc. matches a certain denomination of coin of currency (e.g., 25 cents, 5 cents, 10 cents, etc. in the united states). Alternatively, the machine learning system may be trained to classify the slug into currency coins by including exemplary samples of damaged (e.g., notched, bent, etc.) coins in the aforementioned control samples (see fig. 3A)

Further, because there are non-U.S. currency coins that are not circular in shape but may have some other polygonal shape, the machine learning system of the present disclosure may be configured to classify such objects in the stream of scrap pieces as currency coins.

Because some of the waste material to be sorted may be produced from materials including metal electrical boxes, the piece of waste material may include a circular knockout that appears similar to a currency coin. However, a machine learning system configured according to embodiments of the present disclosure may be configured not to classify such knockout components as currency coins. This can be done by passing a homogenous set of such knockout parts through a machine learning system during a training phase. The machine learning system may "learn" not to classify such knockout parts as currency coins by how they have a different appearance from the currency coin, such as their texture, color, lack of stamped patterns on their faces, etc.

According to certain embodiments of the present disclosure, the machine learning system may be configured to not classify as currency coins any circularly shaped scrap pieces that do not have a diameter equivalent to one or more specified currency coins (e.g., 25 cents, 5 cents, 10 cents, etc.) including, but not limited to, any scrap pieces having a diameter greater than and/or less than a predetermined diameter. This may result, for example, in a garment button not being classified as a currency coin. Such diameter specifications may be used to sort currency coins by denomination.

According to certain embodiments of the present disclosure, training the machine learning system to identify currency coins for sorting using a homogenous set of exemplary coins (see, e.g., fig. 3A) enables the machine learning system 100 to sort specified currency coins from a heterogeneous mixture of waste sheets (see, e.g., fig. 3B).

According to certain embodiments of the present disclosure, the machine learning system may be trained to recognize a specified type of jewelry by passing an exemplary sample of jewelry pieces (see, e.g., fig. 3C) through the machine learning system as previously disclosed, so as to enable the machine learning system 100 to sort specified jewelry waste pieces from a heterogeneous mixture of waste pieces (see, e.g., fig. 3D). As previously disclosed, the machine learning system is capable of identifying and sorting jewelry scrap pieces from a heterogeneous mixture of such scrap pieces by learning specific physical characteristics of such designated jewelry scrap pieces. Fig. 3D provides a non-limiting example of how such pieces of jewelry waste may be visually distinguished from other pieces of waste.

Although not shown in the figures, exemplary PCB pieces may be run through the machine learning system as homogeneous groups to allow the machine learning system 100 to identify and sort such PCB scrap pieces from a heterogeneous mixture of scrap pieces. For example, a machine learning system may do so by looking for a scrap piece of green or green-looking plastic sheet.

Fig. 6 represents an example of various possible embodiments of the present disclosure at an abstract level. The one or more machine learning algorithms may embody one or more aspects of the system and process 600 in nature, although not necessarily as fully as outlined in the flowchart of fig. 6.

In block 601, the vision system 110 needs to acquire an image of the scrap pieces 101 as described herein. Block 602 abstractly represents that the machine learning system may be configured to identify certain specified valuable waste pieces (e.g., currency coins, whether they are round or have a polygonal shape) that are similar to those waste pieces. Other physical characteristics (e.g., color, coloration, hue, texture, stamped features, diameter, etc.) may be used to identify a specified feature (e.g., a feature associated with a coin) in the scrap piece 101.

Optional block 603 abstractly represents how a machine learning system may be configured to exclude from a currency coin classification those slug 101 that appear similar to (i.e., have physical characteristics similar to) an electrical box knockout component.

Optional block 604 abstractly represents how the machine learning system may be further configured to not classify those scrap pieces that do not have the desired denomination to be sorted (e.g., have the color of a U.S. cent, less than 10 cents, greater than 25 cents, etc.) as monetary coins. Block 604 also abstractly represents how the machine learning system may sort different denominations of currency coins separately.

After the machine learning algorithm has been established and the machine learning system has sufficiently learned the differences in material classifications, a library for different categories or types of material (e.g., one or more currency coin denominations, rings, bracelets, necklaces, earrings, PCBs, etc.) is then implemented into a material sorting system (e.g., system 100) for identifying and/or sorting and then sorting the designated scrap pieces from the heterogeneous mixture of scrap pieces.

Fig. 4 illustrates a flow chart depicting an exemplary embodiment of a process 400 for sorting scrap pieces using a vision system, in accordance with certain embodiments of the present disclosure. Aspects of process 400 may be configured to operate in any of the embodiments of the present disclosure described herein, including sorting system 100 of fig. 1. The operations of process 400 may be performed by hardware and/or software included within a computer system (e.g., computer system 3400 of fig. 5) that controls a sorting system (e.g., computer system 107 and/or vision system 110 of fig. 1). In optional process block 401, the scrap pieces may be passed through some well known screen (not shown) that may be configured to allow scrap pieces smaller than a predetermined size to pass through the screen. For example, the slots formed in the screen may be configured to pass objects having similar sizes as currency coins. However, any apparatus or even other sorting system as described herein may be used to first separate the smaller scrap pieces from the larger scrap pieces.

In process block 402, a scrap piece may be deposited onto a conveyor belt. Fig. 3B shows a digital photograph of an exemplary heterogeneous collection of such scrap pieces including various currency coins deposited onto a conveyor belt. Fig. 3A shows a digital photograph of an exemplary heterogeneous collection of scrap pieces, including various jewelry scrap pieces, deposited onto a conveyor belt. In a non-limiting example, the screen may be positioned such that the passing scrap pieces are deposited on the conveyor belt. For example, referring to fig. 1, such a screen may be positioned between a ramp or chute 102 and a conveyor belt 103. Sensing the position of each slug 101 on the conveyor belt 103 is used to track each slug as it travels through the sortation system. This may be performed by the vision system 110 (e.g., by distinguishing scrap pieces from underlying conveyor belt material while in communication with a conveyor belt speed detector (e.g., belt speed detector 105)), and this information is collected and monitored by the automated control system 108. Alternatively, a linear sheet-like (sheet) laser beam (or any system capable of generating light sources including, but not limited to, visible, UV, VIS, and IR and having detectors that can be used to position the sheet) can be used to position the sheet. In process block 403, one or more images of the scrap pieces are captured/acquired when the scrap pieces have traveled proximate to the vision system 110. In process block 404, a machine learning system (such as previously disclosed) may perform pre-processing of the images, which may be used to detect or identify (extract) each scrap piece from the background (e.g., conveyor belt 103). In other words, image pre-processing may be used to identify differences between the scrap piece and the background. Well-known image processing techniques such as dilation, thresholding, and contouring may be used to identify the scrap pieces as being different from the background. In process block 405, image segmentation may be performed. For example, one or more of the images captured by the camera of the vision system may include an image of one or more scrap pieces. Additionally, a particular scrap piece may be located on the seam of the conveyor belt when capturing an image of that scrap piece. Thus, in such cases it may be desirable to isolate the image of a single slug from the background of the image. In an exemplary technique for process block 405, the first step is to apply a high contrast of the image; in this way, the background pixels are reduced to substantially all black pixels, and at least some of the pixels belonging to the scrap piece are lightened to substantially all white pixels. The image pixels of the white scrap piece are then expanded to cover the entire size of the scrap piece. After this step, the position of the scrap pieces is a high contrast image of all white pixels on a black background. Subsequently, a contouring algorithm may be used to detect the boundaries of the scrap piece. This boundary information is saved and the boundary position is then transferred to the original image. Segmentation is then performed on a larger area of the original image than the previously defined boundaries. In this manner, each slug is identified and separated from the background. In process block 406, the size and shape of each scrap piece may be determined.

In process block 407, image post-processing may be performed. Image post-processing may involve resizing an image to prepare the image for use in a neural network. This may also include modifying certain image properties (e.g., enhancing image contrast, changing image background, or applying filters) in a manner that will yield an enhancement to the ability of the machine learning system to classify the scrap pieces. After image post-processing, normalization of the various images may be performed in process block 408 so that images of various different scrap pieces may be more easily compared to one another. In process block 409, the data representing each image may be resized. In some cases, the image may need to be resized to match the data input requirements of some machine learning systems (such as neural networks). Neural networks require image sizes that are much smaller than those captured by typical digital cameras (e.g., 225x225 pixels or 299x299 pixels). Further, the smaller the image size, the less processing time is required to perform classification. Thus, smaller image sizes may ultimately increase the throughput and value of the sorting system.

In process blocks 410 and 411, each slug is identified/sorted based on the detected features. For example, process block 410 may be configured with a neural network employing one or more machine learning algorithms that compares the extracted features (e.g., circular/polygonal shapes, no holes, colors, etc.) to those stored in a knowledge base generated during the training phase, and assigns each of the scrap pieces a classification with the highest match based on such comparison. The machine learning algorithm(s) may process the captured images in a hierarchical manner by using an automatically trained filter. The filter responses are then successfully combined in the next stage(s) of the algorithm(s) until probabilities are obtained in the final step. In process block 411, these probabilities may be used for each of the N (N ≧ 1) classifications to decide which of the N sorting bins the corresponding scrap piece should be sorted. For example, each of the N classifications may be assigned to a corresponding sorting bin, and the scrap pieces under consideration are sorted into the bin corresponding to the classification that returns the highest probability greater than a predefined threshold. In embodiments of the present disclosure, such predefined thresholds may be preset by a user. If none of the probabilities is greater than a predetermined threshold (e.g., the slug is not classified as a money coin), the particular slug may be sorted into an outlier bin (e.g., sorting bin 140).

In process block 412, sorting equipment corresponding to the one or more classifications of the waste sheet is activated (e.g., see fig. 2). Between the time the image of the scrap piece 101 is captured by the vision system 110 and the time the sorting apparatus is activated, the scrap piece 101 has moved from near the vision system 110 to a downstream position on the conveyor belt 103 at the conveyance rate of the conveyor belt 103. In embodiments of the present disclosure, activation of the sorting devices (e.g., 126, 127, 128, 129) is timed such that when a scrap piece 101 passes through a sorting device mapped to a classification of the scrap piece, the sorting device is activated and the scrap piece is directed to its associated sorting bin (e.g., 136, 137, 138, 139). In an embodiment of the present disclosure, activation of the sorting device may be timed by an automated control system in communication with a belt speed detector 105, the belt speed detector 105 detecting when a scrap piece has passed before the sorting device and sending a signal to enable activation of the sorting device. In process block 413, the sorting bin corresponding to the activated sorting apparatus receives the directed scrap piece.

According to certain embodiments of the present disclosure, a plurality of at least a portion of the system 100 may be serially linked together in order to perform a plurality of iterations or layers of sorting. For example, when two or more systems 100 are linked in this manner, a conveyor system having a single conveyor belt or multiple conveyor belts may be implemented that conveys waste pieces through a first vision system configured for sorting the waste pieces of the heterogeneous mixture of the first set of materials into a first set of one or more receptacles (e.g., sorting

bins

136, 137, 138, 139) by a sorter (e.g., first robotic control system 108 and associated one or

more sorting devices

126, 127, 128, 129), and then conveys the waste pieces through a second vision system configured for sorting the waste pieces of the heterogeneous mixture of the second set of materials into a second set of one or more sorting bins by a second sorter.

Such a series of systems 100 may include any number of such systems linked together in such a manner. According to certain embodiments of the present disclosure, each successive vision system may be configured to sort out different materials than the previous vision system(s) (e.g., first sorting coins and copper/brass from waste, then sorting between coins and copper/brass flakes).

As already described herein, embodiments of the present disclosure may be implemented to perform various functions described for identifying, tracking, sorting, and sorting materials (such as scrap pieces). Such functionality may be implemented within hardware and/or software, such as within one or more data processing systems (e.g., data processing system 3400 of fig. 5), such as computer system 107, vision system 110, and/or automation control system 108, as previously noted. However, the functionality described herein is not limited to implementation in any particular hardware/software platform.

As will be appreciated by one skilled in the art, aspects of the present disclosure may be embodied as systems, processes, methods, and/or program products. Accordingly, various aspects of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a "circuit," circuitry, "" module "or" system. Furthermore, aspects of the present disclosure may take the form of a program product embodied in one or more computer-readable storage media having computer-readable program code embodied therein. (however, any combination of one or more computer-readable media may be utilized

The computer readable storage medium may be, for example, but not limited to: an electronic, magnetic, optical, electromagnetic, infrared, biological, atomic or semiconductor system, apparatus, controller or device, or any suitable combination of the foregoing, wherein the computer readable storage medium is not the transitory signal itself. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory ("RAM") (e.g., RAM 3420 of fig. 5), a read-only memory ("ROM") (e.g., ROM 3435 of fig. 5), an erasable programmable read-only memory ("EPROM" or flash memory), an optical fiber, a portable compact disc read-only memory ("CD-ROM"), an optical storage device, a magnetic storage device (e.g., hard disk drive 3431 of fig. 5), or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, controller or device. Program code embodied on a computer readable signal medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein (e.g., in baseband or as part of a carrier wave). Such a propagated signal may take any of a variety of forms, including, but not limited to: electromagnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, controller, or device.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, processes and program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable program instructions for implementing the specified logical function(s). It should also be noted that, in some implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.

For example, a module implemented in software for execution by various types of processors (e.g., GPU 3401, CPU3415) may include, for example, one or more physical or logical blocks of computer instructions organized as objects, procedures, or functions. Nevertheless, the executables of an identified module need not be physically located together, but may comprise disparate instructions stored in different locations which, when joined logically together, comprise the module and achieve the stated purpose for the module. Indeed, a module of executable code may be a single instruction, or many instructions, and may even be distributed over several different code segments, among different programs, and across several memory devices. Similarly, operational data (e.g., a material classification library as described herein) may be identified and illustrated herein within modules, and may be embodied in any suitable form and organized within any suitable type of data structure. The operational data may be collected as a single data set, or may be distributed over different locations including over different storage devices. The data may provide electronic signals over a system or network.

These program instructions may be provided to one or more processors and/or controllers of a general purpose computer, special purpose computer, or other programmable data processing apparatus (e.g., a controller) to produce a machine, such that the instructions, which execute via the processor(s) (e.g., GPU 3401, CPU3415) of the computer or other programmable data processing apparatus, create a circuit system or means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, such as, for example, a system which may include one or more graphics processing units (e.g., GPUs 3401, CPUs 3415), or combinations of special purpose hardware and computer instructions. For example, a module may be implemented as a hardware circuit comprising custom VLSI circuits or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, controllers, or other discrete components. A module may also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices or the like.

Computer program code (i.e., instructions) for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, Python, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages, or any of the machine learning software disclosed herein. The program code may execute entirely on the user's computer system, partly on the user's computer system, as a stand-alone software package, partly on the user's computer system (e.g., a computer system for sorting) and partly on a remote computer system (e.g., a computer system for training a machine learning system), or entirely on the remote computer system or server. In the latter scenario, the remote computer system may be connected to the user's computer system through any type of network, including a local area network ("LAN") or a wide area network ("WAN"), or the connection may be made to an external computer system (for example, through the Internet using an Internet service provider). As an example of the foregoing, various aspects of the present disclosure may be configured to execute on one or more of the computer system 107, the automated control system 108, and the vision system 110.

These program instructions may also be stored in a computer-readable storage medium that can direct a computer system, other programmable data processing apparatus, a controller, and/or other devices to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The program instructions may also be loaded onto a computer, other programmable data processing apparatus, controller or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

One or more databases may be included in the host for storing and providing access to data for various implementations. Those skilled in the art will also appreciate that for security reasons, any of the databases, systems, or components of the present disclosure may include any combination of databases or components in a single location or multiple locations, wherein each database or system may include any of a variety of suitable security features, such as firewalls, access codes, encryption, decryption, and the like. The database may be any type of database, such as a relational database, a hierarchical database, an object-oriented database, and/or the like. Common database products that can be used to implement a database include: IBM's DB2, any of the database products available from Oracle Corporation, Microsoft Access of Microsoft Corporation, or any other database product. The database may be organized in any suitable manner, including as a data table or a lookup table.

The correlation of certain data (e.g., for each of the scrap pieces processed by the sorting system described herein) may be accomplished by any data correlation technique known and practiced in the art. For example, the association may be done manually or automatically. The automatic association techniques may include, for example, database searching, database merging, GREP, AGREP, SQL, and/or similar automatic association techniques. The associating step may be accomplished through a database consolidation function, such as using key fields in each of the manufacturer and retailer data tables. The key field partitions the database according to the high-level object class defined by the key field. For example, a category may be specified as a key field in both the first data table and the second data table, and the two data tables may then be merged based on the classification data in the key field. In these embodiments, the data corresponding to the key fields in each of the merged data tables is preferably the same. However, data tables with similar but not identical data in the key fields may also be merged by using, for example, AGREP.

Reference herein to a "configuring" device performing some function or a device "configured to" perform some function. It will be appreciated that this may include selecting predefined logic blocks and logically associating them such that they provide specific logic functions, including monitoring or control functions. It may further comprise: programming computer software based logic that modifies the control device, wiring discrete hardware components, or a combination of any or all of the foregoing. A device so configured is physically designed to perform a specified function.

In the description herein, numerous specific details are provided, such as examples of programming, software modules, user selections, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, controllers, etc., to provide a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the disclosure may be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, materials, or operations may not be shown or described in detail to avoid obscuring aspects of the disclosure.

With reference now to FIG. 5, a block diagram is depicted that illustrates a data processing ("computer") system 3400 in which aspects of embodiments of the present disclosure may be implemented. (the terms "computer," "system," "computer system," and "data processing system" may be used interchangeably herein.) the computer system 107, the automated control system 108, and/or the vision system 110 may be configured similarly to the computer system 3400. The computer system 3400 may employ a local bus 3405 (e.g., a peripheral component interconnect ("PCI") local bus architecture). Any suitable bus architecture may be used, such as accelerated graphics Port ("AGP") and industry Standard architecture ("ISA"), among others. The one or more processors 3415, volatile memory 3420, and non-volatile memory 3435 may be connected to the local bus 3405 (e.g., through a PCI bridge (not shown)). An integrated memory controller and cache memory may be coupled to the one or more processors 3415. The one or more processors 3415 may include one or more central processor units and/or one or more graphics processor units and/or one or more tensor processing units. In certain embodiments of the present disclosure, one or more GPUs 3401 (e.g., gpgpgpu or general purpose computing on a graphics processing unit) may be implemented within computer system 107 to operate any one or more of the machine learning systems disclosed herein. Additional connections to the local bus 3405 may be made through direct component interconnection or through add-in boards. In the depicted example, a communications (e.g., network (LAN)) adapter 3425, an I/O (e.g., small computer system interface ("SCSI") host bus) adapter 3430, and an expansion bus interface (not shown) may be connected to the local bus 3405 by direct component connection. An audio adapter (not shown), a graphics adapter (not shown), and a display adapter 3416 (coupled to display 3440) may be connected to local bus 3405 (e.g., by an add-in board inserted into an expansion slot).

The user interface adapter 3412 may provide a connection for a keyboard 3413 and a mouse 3414, a modem (not shown), and additional memory (not shown). I/O adapter 3430 may provide a connection for hard disk drive 3431, tape drive 3432, and a CD-ROM drive (not shown).

An operating system may run on the one or more processors 3415 and is used to coordinate and provide control of various components within the computer system 3400. In FIG. 5, the operating system may be a commercially available operating system. An object oriented programming system (e.g., Java, Python, etc.) can run in conjunction with the operating system and provide calls to the operating system from one or more programs (e.g., Java, Python, etc.) executing on the system 3400. Instructions for the operating system, the object-oriented operating system, and programs may be located on non-volatile storage 3435 storage devices, such as hard disk drive 3431, and may be loaded into volatile memory 3420 for execution by processor 3415.

Those of ordinary skill in the art will appreciate that the hardware in FIG. 5 may vary depending on the implementation. Other internal hardware or peripheral devices, such as flash ROM (or equivalent nonvolatile memory) or optical disk drives and the like, may be used in addition to or in place of the hardware depicted in FIG. 5. Also, any of the processes of the present disclosure may be applied to a multi-processor computer system or performed by a plurality of such systems 3400. For example, training of the vision system 110 can be performed by the first computer system 3400 while the operations of the vision system 110 for sorting can be performed by the second computer system 3400.

As another example, the computer system 3400 may be a stand-alone system configured to be bootable without relying on some type of network communication interface, whether or not the computer system 3400 comprises some type of network communication interface. By way of further example, the computer system 3400 may be an embedded controller configured with ROM and/or flash ROM that provides non-volatile memory for storing operating system files or user-generated data.

The depicted example in FIG. 5 and above-described examples are not meant to imply architectural limitations. Further, forms of computer programs forming aspects of the present disclosure may reside on any computer readable storage medium used by a computer system (i.e., floppy disks, compact disks, hard disks, magnetic tape, ROM, RAM, etc.).

Reference throughout this specification to "one embodiment" or "an embodiment" or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, appearances of the phrases "in one embodiment," "in an embodiment," "certain embodiments," "various embodiments," and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment. Furthermore, the described features, structures, aspects, and/or characteristics of the disclosure may be combined in any suitable manner in one or more embodiments. Accordingly, even though features may be initially claimed as acting in certain combinations, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.

Benefits, other advantages, and solutions to problems have been described above with regard to specific embodiments. However, the benefits, advantages, solutions to problems, and any element(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature or element of any or all the claims. Further, no element described herein is required for the practice of the present disclosure unless explicitly described as essential or critical.

Those skilled in the art having read this disclosure will recognize that changes and modifications may be made to the embodiments without departing from the scope of the disclosure. It should be understood that the particular implementations shown and described herein may illustrate the present disclosure and its best mode and may not be intended to otherwise limit the scope of the present disclosure in any way. Other variations may be within the scope of the following claims.

While this specification contains many specifics, these should not be construed as limitations on the scope of the disclosure or of what may be claimed, but rather as descriptions of features specific to particular implementations of the disclosure. The headings herein may not be intended to limit the disclosure, the embodiments of the disclosure, or other items disclosed under the heading.

Herein, the term "or" may be intended to be inclusive, wherein "a or B" includes a or B and also includes both a and B. As used herein, the term "and/or," when used in the context of a list of entities, refers to entities that exist alone or in combination. Thus, for example, the phrase "A, B, C and/or D" includes A, B, C and D individually, but also includes any and all combinations and subcombinations of A, B, C and D.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

The corresponding structures, materials, acts, and equivalents of all means-plus-function elements or step-plus-function elements in the claims below are intended to include any structure, material, or act for performing the function in combination with other claimed elements as specifically claimed.

As used herein with respect to an identified property or condition, "substantially" refers to a degree of deviation that is small enough to not measurably detract from the identified property or condition. In some cases, the exact allowable degree of deviation depends on the particular context.

As used herein, a plurality of items, structural elements, compositional elements, and/or materials may be presented in a common list for convenience. However, these lists should be construed as though each member of the list is individually identified as a separate and unique member. Thus, no single element on such list should be construed as a de facto equivalent of any other element on the same list solely based on the presentation in a common group of any single element on such list with any other element on the same list without indications to the contrary.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the presently disclosed subject matter belongs. Although any methods, devices, and materials similar or equivalent to those described herein can also be used in the practice or testing of the presently disclosed subject matter, representative methods, devices, and materials are now described.

Unless otherwise indicated, all numbers expressing quantities of ingredients, reaction conditions, and so forth used in the specification and claims are to be understood as being modified in all instances by the term "about". Accordingly, unless indicated to the contrary, the numerical parameters set forth in the specification and attached claims are approximations that may vary depending upon the desired properties sought to be obtained by the presently disclosed subject matter. As used herein, the term "about," when referring to a value or amount of mass, weight, time, volume, concentration, or percentage, is intended to encompass variations of ± 20% in some embodiments, 10% in some embodiments, 5% in some embodiments, 1% in some embodiments, 0.5% in some embodiments, and 0.1% in some embodiments, relative to the specified amount, where such variations are suitable for performing the methods of the present disclosure.

Claims

1. A method, comprising:

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

classifying material having one or more specified geometries into a first classification;

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

sorting, by automated sorting equipment, the material sorted into the first classification from the material sorted into the second classification.

2. The method of claim 1, wherein the one or more different geometric shapes comprise circles.

3. The method of claim 1, wherein the one or more different geometric shapes comprise polygons.

4. The method of claim 1, wherein materials having a circular shape and also having pores formed therein are classified into the second classification.

5. The method of claim 1, wherein the material having the specified geometry comprises a currency coin.

6. The method of claim 1, wherein the first category is monetary coins and designated jewelry.

7. The method of claim 1, further comprising, prior to said capturing said image data, passing a mass of material through a screen to produce a heterogeneous mixture of said material having a size less than a predetermined size.

8. A system, comprising:

a camera configured to capture image data of each sheet in a heterogeneous mixture of materials moving through the camera in a stream, wherein materials in the heterogeneous mixture of materials have various different shapes including one or more different closed geometric shapes;

circuitry configured to classify a material having a specified closed geometry into a first classification;

circuitry configured to classify material that does not have the specified closed geometry into a second classification; and

an automated sorting apparatus configured to sort the material classified into the first classification from the material classified into the second classification.

9. The system of claim 8, wherein the material having the specified closed geometric shape has a circular shape.

10. The system of claim 9, further comprising circuitry configured to classify material having a circular shape and a hole formed therein into the second classification.

11. The system of claim 8, further comprising a screen for separating a heterogeneous mixture of the material having a size less than a predetermined size prior to the capturing of the image data.

12. The system of claim 8, wherein the one or more different closed geometric shapes comprise circles.

13. The system of claim 8, wherein the one or more different closed geometric shapes comprise polygons.

14. The system of claim 9, wherein the first classification is a monetary coin.

15. The system of claim 8, wherein the heterogeneous mixture of materials comprises zoba.

16. The system of claim 8, wherein the heterogeneous mixture of materials comprises waste material from an end-of-life vehicle.

17. A computer program product stored on a computer-readable storage medium, which when executed performs a method for sorting material for sorting, the method comprising:

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

sorting material having a specified closed geometry into a first category specified as a money coin;

classifying materials that do not have the specified closed geometry into a second classification; and

sending information about the classification to an automated sorting apparatus, such that the automated sorting apparatus is capable of sorting material classified into the first classification from material classified into the second classification, wherein the one or more different closed geometries are selected from the group consisting of circles and polygons.

18. The computer program product of claim 17, wherein materials having a circular shape and also having pores formed therein are classified into the second classification.

19. The computer program product of claim 17, wherein a material consisting of an electrical box knockout component is classified into the second classification.

20. The computer program product of claim 17, wherein the heterogeneous mixture of materials comprises waste material from an end-of-life vehicle.