US20040151364A1 - Automated part sorting system - Google Patents
Automated part sorting system Download PDFInfo
- Publication number
- US20040151364A1 US20040151364A1 US10/749,642 US74964203A US2004151364A1 US 20040151364 A1 US20040151364 A1 US 20040151364A1 US 74964203 A US74964203 A US 74964203A US 2004151364 A1 US2004151364 A1 US 2004151364A1
- Authority
- US
- United States
- Prior art keywords
- parts
- uninspected
- processor
- sorting
- defective
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
- B07C5/3422—Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/363—Sorting apparatus characterised by the means used for distribution by means of air
- B07C5/365—Sorting apparatus characterised by the means used for distribution by means of air using a single separation means
- B07C5/366—Sorting apparatus characterised by the means used for distribution by means of air using a single separation means during free fall of the articles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30128—Food products
Definitions
- the present invention is directed to a part sorting system and, more particularly, to a part sorting system for automatically inspecting a plurality of uninspected parts.
- Machine vision systems have been applied in a variety of applications, which include food processing, metal recycling, mineral processing and paper recycling, among others.
- vision systems are based on non-contact measurements of electromagnetic radiation (e.g., visible light, infrared light and x-rays), which are typically facilitated by a camera.
- electromagnetic radiation e.g., visible light, infrared light and x-rays
- it is common to optically inspect and sort individual articles with automatic inspection systems.
- Many of the inspection systems have determined properties (e.g., color, size and shape) of the articles such that defective articles could be separated from good articles.
- Machine vision systems have been utilized, for example, to inspect fruit, vegetables and nuts.
- Machine vision systems have also been utilized in other areas that require a similar sorting of products and/or articles.
- such systems have been utilized to sort wood chips, aggregates and manufactured products, such as, fasteners and formed parts, in addition to meat products, such as quartered or cubed poultry or beef products.
- Inspection systems have also been designed to inspect various circular parts by dimension and to detect surface defects in the parts. Some of these systems have determined an inside diameter (I.D.), an outside diameter (O.D.) and detected surface defects, such as nicks, fractures, etc.
- I.D. inside diameter
- O.D. outside diameter
- detected surface defects such as nicks, fractures, etc.
- a wide variety of cameras which include line scan cameras, area scan cameras and CMOS cameras, have been utilized or proposed for utilization in various inspection systems. Images captured by the cameras are automatically processed and evaluated such that image dependent decisions can be implemented.
- prior art systems have performed image capturing on a conveyor belt. Unfortunately, such systems must contend with accumulation of trash on the conveyor belt, thus complicating captured image analysis.
- Most prior art inspection systems have singulated objects for inspection, which has required additional tooling and has added additional costs to the system.
- the present invention is directed to a part sorting system for automatically inspecting a plurality of uninspected parts.
- the system sorts acceptable parts from defective parts and includes a feed conveyor, a sorting camera, at least one rejection valve and a computer system that includes a processor.
- the feed conveyor receives a plurality of uninspected parts and distributes and moves the uninspected parts through an inspection area.
- the sorting camera captures an image of each of the plurality of inspected parts as the plurality of uninspected parts move through the inspection area.
- the rejection valve functions to redirect a defective part such that the defective part is separated from inspected acceptable parts.
- the processor is coupled to the feed conveyor, the sorting camera, and the at least one rejection valve.
- the processor controls the speed of the conveyor, the scanning rate of the sorting camera and the at least one rejection valve.
- the processor executing the inspection routine, also compares at least one edge of a captured image to at least one stored template image to determine whether an inspected part is defective.
- a vibratory conveyor distributes the plurality of uninspected parts in a substantially even manner across a top surface of a platform of the vibratory conveyor and provides the plurality of uninspected parts to the feed conveyor.
- the top surface of the platform is made of a metal that is substantially covered with a material. The material serves to increase the energy absorption and surface friction of the top surface of the platform such that the plurality of uninspected parts are retained on the vibratory conveyor.
- the vibratory conveyor includes a plurality of resilient fiberglass legs and an air cylinder. The plurality of resilient fiberglass legs are mechanically coupled to and support a bottom surface of the platform. The air cylinder is mechanically coupled to the bottom surface of the platform and is capable of varying the magnitude and frequency of the vibration of the vibratory conveyor responsive to the processor.
- FIG. 1 is a simplified diagram of a part sorting system, according to an embodiment of the present invention.
- FIG. 2 is a block diagram of the major components of the part sorting system of FIG. 1;
- FIG. 3 illustrates a part training routine, according to an embodiment of the present invention
- FIG. 4 is a diagram illustrating the capturing and comparison of an image of a part at a non-zero degree orientation whose edge pixels are compared to the templates of FIG. 3;
- FIG. 5 is a flowchart of an image processing routine that determines whether a given part is defective.
- the present invention is directed to a part sorting system that is capable of sorting objects of various shapes (e.g., round and non-round parts).
- the part sorting system is capable of separating foreign material, mixed parts, damaged parts and any other non-conforming parts from the product stream.
- the part sorting system can measure the outside diameter (O.D.) and inside diameter (I.D.) of a round washer (e.g., one-half inch I.D.).
- the part sorting system is capable of performing one-hundred percent size inspection at a rate of approximately 1.2 million washers per ten hours (two thousand pieces per minute).
- the part sorting system uses a template image matching technique to sort defective parts by size and shape.
- the template image matching technique compares captured part images of a plurality of uninspected parts that may be at random orientations, with at least one trained stored image template of a good part. Out-of-tolerance parts are indicated by size and shape deviation.
- the present technique is applicable to round and non-round objects of virtually any shape.
- One of ordinary skill in the art will readily appreciate that the system can be scaled to handle parts of virtually any size.
- a line scan camera is utilized to capture a one-dimensional array of pixels of multiple sections of each of the plurality of uninspected parts.
- a line scan camera to build an image with a line scan camera, either the camera or the object being inspected must move.
- An advantage of utilizing a line scan camera is that it advantageously allows for the image capturing of continuously moving objects on a production line.
- a typical line scan camera has a programmable scan rate, which allows for high precision inspection.
- the present invention advantageously performs off-belt inspection such that an object being inspected is backlit. Backlighting the object allows the line scan camera to capture a better image of the part. As such, the resolution (i.e., the number of gray scales that can be determined) is typically increased, which allows fractures in the part to be more readily detected. Further, image capture is enhanced as trash contamination of the captured image, associated with on-belt inspection, is avoided.
- a hopper provides parts at a controlled rate to a platform of a vibratory conveyor. The vibratory conveyor functions to distribute the parts evenly across a top surface of the platform, so as to typically provide a single layer of single profile parts.
- a system provides flexibility in that the parts that can be inspected, by the system, can vary in size and shape. Additionally, the automated part sorter, described herein, can advantageously handle parts at random orientations.
- the vibratory conveyor provides the plurality of uninspected parts to a feed conveyor that provides part separation and moves the parts through an inspection area, where the line scan camera (or cameras) scan the parts to grab images of the parts. Those part images are analyzed by processor controlled template image matching to sort defective parts by size and shape.
- the processor makes decision-based inspections and typically saves the inspection data such that it can be further evaluated, when off-line analysis is desired. Acceptable parts continue in the product stream while unacceptable parts are removed from the product stream.
- a standard personal computer system executing a Windows NT® operating system, is utilized.
- the system is expandable in that other cameras (e.g., line scan, area scan or CMOS) and vision processing boards can be added to the system, to increase the resolution and through-put of the part sorting system, if desired.
- the system includes a modem, which enables remote access for technical training, trouble shooting and upgrading of the part sorting system.
- FIG. 1 a part sorting system 100 , according to an embodiment of the present invention, is shown.
- uninspected parts are supplied to the part sorting system 100 by loading the parts into a bin 104 of a hopper 102 .
- the parts are supplied to a vibratory conveyor 110 via a hopper conveyor 106 , which is driven by a hopper motor 108 that is under processor 202 (FIG. 2) control.
- Vibratory conveyor 110 includes a platform 121 that has a top surface 120 and a bottom surface 114 .
- the top surface 120 of vibratory conveyor 110 includes a material 122 .
- the material 122 serves to increase the energy absorption and surface friction of the top surface 120 of the vibratory conveyor 110 .
- a suitable material 120 is manufactured and made commercially available by Great Lakes Belting (Part No. FNV100TG).
- the thickness of material 120 (preferably made of nitrile) is part dependent.
- Attached to the bottom surface 114 , of platform 121 is one end of each of a plurality of legs (e.g., fiberglass) 112 that support platform 121 and are mechanically coupled to the bottom surface 114 , of platform 121 .
- An opposite end of the plurality of legs 112 is coupled to a support structure 123 .
- One end of an air cylinder 116 is mechanically coupled to the bottom surface 114 of platform 121 .
- An opposite end of the air cylinder 116 is coupled to the support structure 123 .
- a suitable air cylinder 116 is manufactured and made commercially available by Martin Engineering (Part No. 32505). Air cylinder 116 , under processor 202 control, varies the magnitude and frequency of the vibration of the vibratory conveyor 110 such that the parts are normally separated into a single layer. The vibration of the vibratory conveyor 110 causes the parts to move across the top surface 120 of the platform 121 in the direction of feed conveyor 130 . Processor 202 , of system 100 , optimally controls the vibration of vibratory conveyor 122 such that parts of different size and weight can be sorted with part sorting system 100 . Commercially available vibratory conveyors have not allowed the frequency and amplitude of the vibration to be part optimized and thus, cannot be utilized for a wide variety of parts.
- Feed conveyor 130 includes a feed conveyor motor 132 for driving a conveyor belt (not shown), of feed conveyor 130 .
- Feed conveyor motor 132 includes an encoder (not shown) that provides signals to processor 202 such that processor 202 can determine the speed of the belt and, in turn, the speed of the parts across the feed conveyor 130 .
- Feed conveyor 130 delivers the plurality of uninspected parts to an inspection area defined by camera 140 and rejection valve 144 . As conveyor 130 moves the plurality of uninspected parts into the inspection area, camera 140 , under processor 202 control, captures images of the individual uninspected parts. The capturing of images is facilitated by a backlight 142 .
- the illumination provided by backlight 142 can be derived, for example, from a light emitting diode (LED) or a fluorescent light source.
- the backlight 142 allows camera 140 to capture images with sharper contrast, which enables systems 100 to detect, for example, fractures in the face of a part.
- an air stream is provided across backlight 142 such that backlight 142 remains free of various trash (e.g., dirt, oil, etc.) that typically comes off the conveyor belt.
- a clean-in-place (CIP) air knife is applied to the belt of feed conveyor 132 such that trash is removed.
- CIP clean-in-place
- backlight 142 includes a plurality of optical fibers that provide backlighting, of the uninspected parts, for camera 140 .
- a suitable camera is manufactured and made commercially available by Basler (Part No. L1GD).
- a suitable backlight is manufactured and made commercially available by Illumination Technology (Part No. 3900).
- processor 202 Upon capturing an image of each part, the image is analyzed by processor 202 .
- Processor 202 executes image processing software which compares the captured image to at least one template image to determine whether a part is defective. As will be further described below, when a defective part is detected, processor 202 causes one or more air valves located within rejection valve 144 to be actuated. Utilizing multiple air valves within rejection valve 144 allows multiple parts that are side-by-side to be inspected at the same time and allows a good part that is adjacent to a defective part to remain in the product stream when a defective part is removed from the product stream. A suitable rejection valve is manufactured and made commercially available by MAC (Part No. 52).
- a processing thread of the inspection software causes system 100 to continuously grab and process images of parts, while system 100 is active. This is facilitated through the use of multiple buffers, which allow processing of one image while live grabbing of a second image.
- the software calculates the time at which a given defective part can be acted upon by an appropriate air valve, within rejection valve 144 , and activates the appropriate air valve or valves at that time.
- the time is dependent upon the speed of the belt of the feed conveyor 130 and the positioning of the rejection valve 144 with respect to the inspection end of feed conveyor 130 .
- the appropriate air valve, of rejection valve 144 is typically determined by the location of the part on the conveyor belt. Actuating an appropriate air valve, of rejection valve 144 , causes the defective part to be deflected into a reject chute 146 . Good parts pass from feed conveyor 130 to take-away conveyor 150 undisturbed by rejection valve 144 .
- Take-away conveyor 150 provides inspected good parts through a part counting area, defined by part counting camera 160 .
- a part counting backlight 162 provides backlight illumination to the parts for easier detection by part counting camera 160 .
- Part counting camera 160 is also coupled to processor 202 such that processor 202 can determine when a packaging box 184 A, 184 B or 184 C, located on packaging box conveyor 180 , contains a desired number of parts. At that point, processor 202 causes a top gate actuator 166 and a bottom gate 168 to move a top gate 167 and a bottom gate 169 to a closed position.
- packaging valve 164 deflects the good parts into a bottom chute 172 .
- Processor 202 then actuates a packaging box conveyor motor 182 such that a new empty packaging box 184 B is delivered beneath bottom chute 172 and top chute 170 such that it can receive good parts.
- processor 202 opens top gate 166 and bottom gate 172 such that the held good parts are delivered into the packaging box 184 B. In this manner, good parts are retained in bottom chute 172 while the new packaging box 184 B is moved into position. This process is repeated when the new packaging box 184 B receives the desired number of parts.
- a part sorting system has been described, which allows a wide variety of parts to be automatically inspected, sorted and packaged.
- FIG. 2 illustrates a block diagram of most of the major electrical/electro-mechanical components of the part sorting system 100 of FIG. 1.
- processor 202 is coupled to a top gate actuator 166 and a bottom actuator 168 such that it controls the opening and closing of the top gate 167 and bottom gate 169 .
- Processor 202 is also coupled to a hopper motor 108 , a vibratory conveyor air cylinder 116 , a feed conveyor motor 132 , a take-away conveyor motor 152 and a packaging box conveyor 182 .
- Processor 202 provides control signals to motors 108 , 132 , 152 and 192 and receives signals from encoders located within motors 108 , 132 , 152 and 192 that allow processor 202 to determine if the motors 108 , 132 , 152 and 182 have responded appropriately. For example, processor 202 receives signals from the encoder of feed conveyor motor 132 , which allow processor 202 to synchronize the operation of the part sorting camera 140 with the speed of the feed conveyor motor 132 .
- Processor 202 is also coupled to and controls rejection valve 144 and packaging valve 164 .
- An air source 208 provides pressurized air to the top gate actuator 166 , bottom gate actuator 168 , rejection valve 144 and the packaging valve 164 .
- Processor 202 is also coupled to a display 206 , which is preferably a touch screen display, and to a memory subsystem 204 .
- Memory subsystem 204 includes an application appropriate amount of volatile and non-volatile memory.
- Processor 202 is coupled to part sorting backlight 142 and part counting backlight 162 and desirably controls the illumination provided by the backlights 142 and 162 so as to optimize the image capturing of part sorting camera 140 and part counting camera 160 .
- Processor 202 is also coupled to a height sensor 135 , which provides a rough indication of the height of a given individual part.
- Height sensor 135 allows system 100 to determine when multiple parts are stuck together and is preferably a laser through beam sensor manufactured and made commercially available by SUNX (Part No. LAS11).
- SUNX Part No. LAS11
- An overhead image of two parts that are stuck together may not cause the parts to be rejected, as a defective part, without a rough height indicator.
- another camera e.g., line scan
- processor 202 can be positioned and coupled to processor 202 to determine the height of the parts more precisely.
- FIG. 3 illustrates a part training routine that allows system 100 to develop template images of good parts.
- a number of good parts 302 e.g., four to six parts
- templates 304 A, 304 B, 304 C and 304 D are generated.
- one, two, or four templates may be required.
- a round part only requires one template since it is symmetrical.
- four templates 304 A, 304 B, 304 C and 304 D are required for part 302 .
- the software utilized by system 100 preferably rotates a captured part image to zero degrees and then utilizes the pixels on the edge of the part to determine whether the part is defective.
- an image of a part 302 A, at a non-zero degree orientation is captured.
- the edge pixels of part 302 A are rotated to a zero degree orientation and compared with each of the templates 304 A, 304 B, 304 C and 304 D, as required.
- the edge pixels of image 302 A match template 304 A.
- the image of the part is compared to one or more of the templates and the number of the pixels outside each template are counted. If a given part matches at least one template within defined limits, it is a good part. Otherwise, if a given part does not match any template within the defined limits, it is a defective part. It is advantageous to only compare the edge pixels in that the amount of time required for processing the edge pixels is typically appreciably lower (part dependent) than that of processing all part pixels.
- FIG. 5 shows a flowchart of an image processing routine 500 , executed by processor 202 , that determines whether a given part is defective.
- routine 500 is initiated.
- step 504 a part image that has been buffered is retrieved from a memory buffer.
- step 506 the part image is oriented.
- step 508 the retrieved part image is compared to at least one stored template of a known good part.
- decision step 510 processor 202 determines whether the part is good. If so, control transfers to step 514 . Otherwise, control transfers to step 512 .
- processor 202 allows the part to remain in the product stream and control returns to step 504 .
- processor 202 causes the defective part to be removed from the product stream at which point control transfers to step 504 .
- processor 202 causes a defective part to be removed from the product stream by actuating an appropriate portion of rejection valve 144 at an appropriate time.
Abstract
A part sorting system for automatically inspecting a plurality of uninspected parts includes a feed conveyor, a sorting camera, at least one rejection valve and a computer system that includes a processor. The feed conveyor receives a plurality of uninspected parts and moves the uninspected parts through an inspection area. The sorting camera captures an image of each of the plurality of inspected parts as the plurality of uninspected parts moves through the inspection area. The rejection value functions to direct a defective part such that the defective part is separated from inspected acceptable parts. The processor is coupled to the feed conveyor, the sorting camera and the at least one rejection valve. The processor controls the conveyor, the sorting camera and the at least one rejection valve and compares only edge pixels of the captured image to determine whether an inspected part is defective.
Description
- This application is a continuation of U.S. patent application Ser. No. 09/597,946, entitled “AUTOMATED PART SORTING SYSTEM,” by Ernest K. Kenneway et al., filed on Jun. 20, 2000, the disclosure of which is hereby incorporated by reference herein in its entirety.
- The present invention is directed to a part sorting system and, more particularly, to a part sorting system for automatically inspecting a plurality of uninspected parts.
- Machine vision systems have been applied in a variety of applications, which include food processing, metal recycling, mineral processing and paper recycling, among others. As is well known to one of ordinary skill in the art, vision systems are based on non-contact measurements of electromagnetic radiation (e.g., visible light, infrared light and x-rays), which are typically facilitated by a camera. In the manufacturing and processing environments, it is common to optically inspect and sort individual articles with automatic inspection systems. Many of the inspection systems have determined properties (e.g., color, size and shape) of the articles such that defective articles could be separated from good articles.
- Machine vision systems have been utilized, for example, to inspect fruit, vegetables and nuts. Machine vision systems have also been utilized in other areas that require a similar sorting of products and/or articles. For example, such systems have been utilized to sort wood chips, aggregates and manufactured products, such as, fasteners and formed parts, in addition to meat products, such as quartered or cubed poultry or beef products.
- In a typical system, video images of the products and/or articles are captured, with a camera and a frame grabber, to extract color, shape and/or size related information. Typically, bulk articles are stabilized, using centrifugal force, and conveyed individually past an optical inspection station. In a typical prior art system that implements air deflectors, the center of a defective product is computed such that an air stream is aimed at the center of the product to remove the defective product from a product stream.
- Inspection systems have also been designed to inspect various circular parts by dimension and to detect surface defects in the parts. Some of these systems have determined an inside diameter (I.D.), an outside diameter (O.D.) and detected surface defects, such as nicks, fractures, etc. A wide variety of cameras, which include line scan cameras, area scan cameras and CMOS cameras, have been utilized or proposed for utilization in various inspection systems. Images captured by the cameras are automatically processed and evaluated such that image dependent decisions can be implemented. Typically, prior art systems have performed image capturing on a conveyor belt. Unfortunately, such systems must contend with accumulation of trash on the conveyor belt, thus complicating captured image analysis. Most prior art inspection systems have singulated objects for inspection, which has required additional tooling and has added additional costs to the system.
- Thus, an inspection system that performs off-belt inspection and does not require article singulation is desirable.
- The present invention is directed to a part sorting system for automatically inspecting a plurality of uninspected parts. The system sorts acceptable parts from defective parts and includes a feed conveyor, a sorting camera, at least one rejection valve and a computer system that includes a processor. The feed conveyor receives a plurality of uninspected parts and distributes and moves the uninspected parts through an inspection area. The sorting camera captures an image of each of the plurality of inspected parts as the plurality of uninspected parts move through the inspection area. The rejection valve functions to redirect a defective part such that the defective part is separated from inspected acceptable parts. The processor is coupled to the feed conveyor, the sorting camera, and the at least one rejection valve. The processor, executing an inspection routine, controls the speed of the conveyor, the scanning rate of the sorting camera and the at least one rejection valve. The processor, executing the inspection routine, also compares at least one edge of a captured image to at least one stored template image to determine whether an inspected part is defective.
- In another embodiment of the present invention, a vibratory conveyor distributes the plurality of uninspected parts in a substantially even manner across a top surface of a platform of the vibratory conveyor and provides the plurality of uninspected parts to the feed conveyor. In yet another embodiment, the top surface of the platform is made of a metal that is substantially covered with a material. The material serves to increase the energy absorption and surface friction of the top surface of the platform such that the plurality of uninspected parts are retained on the vibratory conveyor. In still another embodiment of the present invention, the vibratory conveyor includes a plurality of resilient fiberglass legs and an air cylinder. The plurality of resilient fiberglass legs are mechanically coupled to and support a bottom surface of the platform. The air cylinder is mechanically coupled to the bottom surface of the platform and is capable of varying the magnitude and frequency of the vibration of the vibratory conveyor responsive to the processor.
- These and other features, advantages and objects of the present invention will be further understood and appreciated by those skilled in the art by reference to the following specification, claims, and appended drawings.
- In the drawings:
- FIG. 1 is a simplified diagram of a part sorting system, according to an embodiment of the present invention;
- FIG. 2 is a block diagram of the major components of the part sorting system of FIG. 1;
- FIG. 3 illustrates a part training routine, according to an embodiment of the present invention;
- FIG. 4 is a diagram illustrating the capturing and comparison of an image of a part at a non-zero degree orientation whose edge pixels are compared to the templates of FIG. 3; and
- FIG. 5 is a flowchart of an image processing routine that determines whether a given part is defective.
- The present invention is directed to a part sorting system that is capable of sorting objects of various shapes (e.g., round and non-round parts). The part sorting system is capable of separating foreign material, mixed parts, damaged parts and any other non-conforming parts from the product stream. For example, the part sorting system can measure the outside diameter (O.D.) and inside diameter (I.D.) of a round washer (e.g., one-half inch I.D.). In addition, the part sorting system is capable of performing one-hundred percent size inspection at a rate of approximately 1.2 million washers per ten hours (two thousand pieces per minute). The part sorting system uses a template image matching technique to sort defective parts by size and shape. The template image matching technique compares captured part images of a plurality of uninspected parts that may be at random orientations, with at least one trained stored image template of a good part. Out-of-tolerance parts are indicated by size and shape deviation. The present technique is applicable to round and non-round objects of virtually any shape. One of ordinary skill in the art will readily appreciate that the system can be scaled to handle parts of virtually any size.
- Preferably, a line scan camera is utilized to capture a one-dimensional array of pixels of multiple sections of each of the plurality of uninspected parts. As is well known to one of ordinary skill in the art, to build an image with a line scan camera, either the camera or the object being inspected must move. An advantage of utilizing a line scan camera is that it advantageously allows for the image capturing of continuously moving objects on a production line. A typical line scan camera has a programmable scan rate, which allows for high precision inspection.
- The present invention advantageously performs off-belt inspection such that an object being inspected is backlit. Backlighting the object allows the line scan camera to capture a better image of the part. As such, the resolution (i.e., the number of gray scales that can be determined) is typically increased, which allows fractures in the part to be more readily detected. Further, image capture is enhanced as trash contamination of the captured image, associated with on-belt inspection, is avoided. In a typical system, a hopper provides parts at a controlled rate to a platform of a vibratory conveyor. The vibratory conveyor functions to distribute the parts evenly across a top surface of the platform, so as to typically provide a single layer of single profile parts. Utilizing the system, described herein, is advantageous in that there is no need for special tooling to align the parts in single file. A system, according to the present invention, provides flexibility in that the parts that can be inspected, by the system, can vary in size and shape. Additionally, the automated part sorter, described herein, can advantageously handle parts at random orientations.
- The vibratory conveyor provides the plurality of uninspected parts to a feed conveyor that provides part separation and moves the parts through an inspection area, where the line scan camera (or cameras) scan the parts to grab images of the parts. Those part images are analyzed by processor controlled template image matching to sort defective parts by size and shape. The processor makes decision-based inspections and typically saves the inspection data such that it can be further evaluated, when off-line analysis is desired. Acceptable parts continue in the product stream while unacceptable parts are removed from the product stream. In a preferred embodiment, a standard personal computer system, executing a Windows NT® operating system, is utilized. The system is expandable in that other cameras (e.g., line scan, area scan or CMOS) and vision processing boards can be added to the system, to increase the resolution and through-put of the part sorting system, if desired. Preferably, the system includes a modem, which enables remote access for technical training, trouble shooting and upgrading of the part sorting system.
- Turning to FIG. 1, a
part sorting system 100, according to an embodiment of the present invention, is shown. Initially, uninspected parts are supplied to thepart sorting system 100 by loading the parts into abin 104 of ahopper 102. The parts are supplied to avibratory conveyor 110 via ahopper conveyor 106, which is driven by ahopper motor 108 that is under processor 202 (FIG. 2) control.Vibratory conveyor 110 includes aplatform 121 that has atop surface 120 and abottom surface 114. In a preferred embodiment, thetop surface 120 ofvibratory conveyor 110 includes amaterial 122. Thematerial 122 serves to increase the energy absorption and surface friction of thetop surface 120 of thevibratory conveyor 110. Asuitable material 120 is manufactured and made commercially available by Great Lakes Belting (Part No. FNV100TG). The thickness of material 120 (preferably made of nitrile) is part dependent. - Attached to the
bottom surface 114, ofplatform 121, is one end of each of a plurality of legs (e.g., fiberglass) 112 that supportplatform 121 and are mechanically coupled to thebottom surface 114, ofplatform 121. An opposite end of the plurality oflegs 112 is coupled to asupport structure 123. One end of anair cylinder 116 is mechanically coupled to thebottom surface 114 ofplatform 121. An opposite end of theair cylinder 116 is coupled to thesupport structure 123. - A
suitable air cylinder 116 is manufactured and made commercially available by Martin Engineering (Part No. 32505).Air cylinder 116, underprocessor 202 control, varies the magnitude and frequency of the vibration of thevibratory conveyor 110 such that the parts are normally separated into a single layer. The vibration of thevibratory conveyor 110 causes the parts to move across thetop surface 120 of theplatform 121 in the direction offeed conveyor 130.Processor 202, ofsystem 100, optimally controls the vibration ofvibratory conveyor 122 such that parts of different size and weight can be sorted withpart sorting system 100. Commercially available vibratory conveyors have not allowed the frequency and amplitude of the vibration to be part optimized and thus, cannot be utilized for a wide variety of parts. -
Feed conveyor 130 includes afeed conveyor motor 132 for driving a conveyor belt (not shown), offeed conveyor 130.Feed conveyor motor 132 includes an encoder (not shown) that provides signals toprocessor 202 such thatprocessor 202 can determine the speed of the belt and, in turn, the speed of the parts across thefeed conveyor 130.Feed conveyor 130 delivers the plurality of uninspected parts to an inspection area defined bycamera 140 andrejection valve 144. Asconveyor 130 moves the plurality of uninspected parts into the inspection area,camera 140, underprocessor 202 control, captures images of the individual uninspected parts. The capturing of images is facilitated by abacklight 142. The illumination provided bybacklight 142 can be derived, for example, from a light emitting diode (LED) or a fluorescent light source. Thebacklight 142 allowscamera 140 to capture images with sharper contrast, which enablessystems 100 to detect, for example, fractures in the face of a part. - Preferably, an air stream is provided across
backlight 142 such thatbacklight 142 remains free of various trash (e.g., dirt, oil, etc.) that typically comes off the conveyor belt. Preferably, a clean-in-place (CIP) air knife is applied to the belt offeed conveyor 132 such that trash is removed. As previously stated, aligning parts on a track or on multiple tracks limits the ability of a given part sorting system to handle a wide variety of parts. In a preferred embodiment,backlight 142 includes a plurality of optical fibers that provide backlighting, of the uninspected parts, forcamera 140. A suitable camera is manufactured and made commercially available by Basler (Part No. L1GD). A suitable backlight is manufactured and made commercially available by Illumination Technology (Part No. 3900). - Upon capturing an image of each part, the image is analyzed by
processor 202.Processor 202 executes image processing software which compares the captured image to at least one template image to determine whether a part is defective. As will be further described below, when a defective part is detected,processor 202 causes one or more air valves located withinrejection valve 144 to be actuated. Utilizing multiple air valves withinrejection valve 144 allows multiple parts that are side-by-side to be inspected at the same time and allows a good part that is adjacent to a defective part to remain in the product stream when a defective part is removed from the product stream. A suitable rejection valve is manufactured and made commercially available by MAC (Part No. 52). - Preferably, a processing thread of the inspection software causes
system 100 to continuously grab and process images of parts, whilesystem 100 is active. This is facilitated through the use of multiple buffers, which allow processing of one image while live grabbing of a second image. The software calculates the time at which a given defective part can be acted upon by an appropriate air valve, withinrejection valve 144, and activates the appropriate air valve or valves at that time. One of ordinary skill in the art will appreciate that, the time is dependent upon the speed of the belt of thefeed conveyor 130 and the positioning of therejection valve 144 with respect to the inspection end offeed conveyor 130. One of ordinary skill in the art will also appreciate that the appropriate air valve, ofrejection valve 144, is typically determined by the location of the part on the conveyor belt. Actuating an appropriate air valve, ofrejection valve 144, causes the defective part to be deflected into areject chute 146. Good parts pass fromfeed conveyor 130 to take-awayconveyor 150 undisturbed byrejection valve 144. - Take-away
conveyor 150 provides inspected good parts through a part counting area, defined bypart counting camera 160. Apart counting backlight 162 provides backlight illumination to the parts for easier detection bypart counting camera 160.Part counting camera 160 is also coupled toprocessor 202 such thatprocessor 202 can determine when apackaging box packaging box conveyor 180, contains a desired number of parts. At that point,processor 202 causes atop gate actuator 166 and abottom gate 168 to move atop gate 167 and abottom gate 169 to a closed position. - Under
processor 202 control,packaging valve 164 deflects the good parts into abottom chute 172.Processor 202 then actuates a packagingbox conveyor motor 182 such that a newempty packaging box 184B is delivered beneathbottom chute 172 andtop chute 170 such that it can receive good parts. Upon positioning anew box 184B to receive parts from thebottom chute 172 and thetop chute 170,processor 202 openstop gate 166 andbottom gate 172 such that the held good parts are delivered into thepackaging box 184B. In this manner, good parts are retained inbottom chute 172 while thenew packaging box 184B is moved into position. This process is repeated when thenew packaging box 184B receives the desired number of parts. Thus, a part sorting system has been described, which allows a wide variety of parts to be automatically inspected, sorted and packaged. - FIG. 2 illustrates a block diagram of most of the major electrical/electro-mechanical components of the
part sorting system 100 of FIG. 1. As previously discussed,processor 202 is coupled to atop gate actuator 166 and abottom actuator 168 such that it controls the opening and closing of thetop gate 167 andbottom gate 169.Processor 202 is also coupled to ahopper motor 108, a vibratoryconveyor air cylinder 116, afeed conveyor motor 132, a take-awayconveyor motor 152 and apackaging box conveyor 182.Processor 202 provides control signals tomotors motors processor 202 to determine if themotors processor 202 receives signals from the encoder offeed conveyor motor 132, which allowprocessor 202 to synchronize the operation of thepart sorting camera 140 with the speed of thefeed conveyor motor 132. -
Processor 202 is also coupled to andcontrols rejection valve 144 andpackaging valve 164. Anair source 208 provides pressurized air to thetop gate actuator 166,bottom gate actuator 168,rejection valve 144 and thepackaging valve 164.Processor 202 is also coupled to adisplay 206, which is preferably a touch screen display, and to amemory subsystem 204.Memory subsystem 204 includes an application appropriate amount of volatile and non-volatile memory.Processor 202 is coupled topart sorting backlight 142 andpart counting backlight 162 and desirably controls the illumination provided by thebacklights part sorting camera 140 andpart counting camera 160. -
Processor 202 is also coupled to aheight sensor 135, which provides a rough indication of the height of a given individual part.Height sensor 135 allowssystem 100 to determine when multiple parts are stuck together and is preferably a laser through beam sensor manufactured and made commercially available by SUNX (Part No. LAS11). One of ordinary skill in the art will appreciate that an overhead image of two parts that are stuck together may not cause the parts to be rejected, as a defective part, without a rough height indicator. Thus, by making a rough height determination, such an anomaly can be detected. One of ordinary skill in the art will also appreciate that, if desired, another camera (e.g., line scan) can be positioned and coupled toprocessor 202 to determine the height of the parts more precisely. - FIG. 3 illustrates a part training routine that allows
system 100 to develop template images of good parts. A number of good parts 302 (e.g., four to six parts) are run through thepart sorting system 100 such thattemplates templates part 302. One of ordinary skill in the art will appreciate that the number of templates required is dependent upon how the software orients a given part. The software utilized bysystem 100 preferably rotates a captured part image to zero degrees and then utilizes the pixels on the edge of the part to determine whether the part is defective. - As illustrated in FIG. 4, an image of a
part 302A, at a non-zero degree orientation, is captured. To facilitate comparison, the edge pixels ofpart 302A are rotated to a zero degree orientation and compared with each of thetemplates image 302Amatch template 304A. In determining whether a given part is defective, the image of the part is compared to one or more of the templates and the number of the pixels outside each template are counted. If a given part matches at least one template within defined limits, it is a good part. Otherwise, if a given part does not match any template within the defined limits, it is a defective part. It is advantageous to only compare the edge pixels in that the amount of time required for processing the edge pixels is typically appreciably lower (part dependent) than that of processing all part pixels. - FIG. 5 shows a flowchart of an
image processing routine 500, executed byprocessor 202, that determines whether a given part is defective. Instep 502, routine 500 is initiated. Next, instep 504, a part image that has been buffered is retrieved from a memory buffer. Then, instep 506, the part image is oriented. Next, instep 508, the retrieved part image is compared to at least one stored template of a known good part. Then, indecision step 510,processor 202 determines whether the part is good. If so, control transfers to step 514. Otherwise, control transfers to step 512. Instep 514,processor 202 allows the part to remain in the product stream and control returns to step 504. Instep 512,processor 202 causes the defective part to be removed from the product stream at which point control transfers to step 504. As mentioned above,processor 202 causes a defective part to be removed from the product stream by actuating an appropriate portion ofrejection valve 144 at an appropriate time. - The above description is considered that of the preferred embodiments only. Modification of the invention will occur to those skilled in the art and to those who make or use the invention. Therefore, it is understood that the embodiments shown in the drawings and described above are merely for illustrative purposes and not intended to limit the scope of the invention, which is defined by the following claims as interpreted according to the principles of patent law, including the Doctrine of Equivalents.
Claims (20)
1. A part sorting system for automatically inspecting a plurality of uninspected parts, the system sorting acceptable parts from defective parts, the system comprising:
a feed conveyer for receiving a plurality of uninspected parts, the feed conveyor moving the uninspected parts through an inspection area;
a sorting camera for capturing an image of each of the plurality of uninspected parts as the plurality of uninspected parts move through the inspection area;
at least one rejection valve, the rejection valve functioning to direct a defective part such that the defective part is separated from inspected acceptable parts; and
a computer system, including:
a processor coupled to the feed conveyer, the sorting camera and the at least one rejection valve, wherein the processor executes an inspection routine that controls the speed of the feed conveyer, the scanning rate of the sorting camera and the at least one rejection valve, and wherein the processor executing the inspection routine compares only edge pixels of the captured image to at least one stored template image to determine whether each of the uninspected parts is defective.
2. The system of claim 1 , further including:
a vibratory conveyor including a platform having a top surface and a bottom surface, the vibratory conveyor distributing the plurality of uninspected parts in a substantially even manner across the top surface of the platform and providing the plurality of uninspected parts to the feed conveyer.
3. The system of claim 2 , wherein the top surface of the platform is made of a metal that is substantially covered with a material, the material serving to increase the energy absorption and surface friction of the top surface of the platform.
4. The system of claim 3 , wherein the vibratory conveyor further includes:
a plurality of resilient fiberglass legs mechanically coupled to and supporting the bottom surface of the platform; and
an air cylinder mechanically coupled to the bottom surface of the platform, the air cylinder varying the magnitude and frequency of the vibration of the platform in response to the processor.
5. The system of claim 1 , further including:
a height sensor coupled to the processor and positioned adjacent the inspection area, the height sensor providing an indication of the height of each of the plurality of uninspected parts to the processor.
6. The system of claim 1 , further including:
a light source for backlighting the plurality of uninspected parts as the plurality of uninspected parts move through the inspection area, the backlighting enhancing the ability of the sorting camera to capture gray scale images of each of the plurality of uninspected parts.
7. The system of claim 6 , wherein the light source is provided via a plurality of optical fibers.
8. The system of claim 1 , further including:
a hopper for receiving the plurality of uninspected parts, the hopper providing the uninspected parts to the vibratory conveyor responsive to the processor.
9. The system of claim 1 , wherein the sorting camera is a line scan charge coupled device (CCD) camera.
10. The system of claim 1 , wherein the sorting camera is a line scan complementary metal-oxide semiconductor (CMOS) camera.
11. The system of claim 1 , further including:
an electric motor coupled to the processor, the electric motor driving the feed conveyer responsive to the processor; and
an encoder coupled to the processor, the encoder providing an indication of the speed of the motor and hence the associated speed of the feed conveyor, wherein the processor sets a scan rate for the sorting camera responsive to the speed of the feed conveyor.
12. A method for automatically inspecting a plurality of uninspected parts and sorting acceptable parts from defective parts, the method comprising the steps of:
moving a plurality of uninspected parts through an inspection area;
capturing an image of each of the plurality of uninspected parts as the plurality of uninspected parts move through the inspection area;
comparing only edge pixels of the captured image of each of the plurality of uninspected parts to at least one stored template image to determine whether each of the uninspected parts is defective; and
directing a defective part such that the defective part is separated from inspected acceptable parts.
13. The method of claim 12 , wherein the plurality of uninspected parts are distributed in a substantially even manner across a top surface of a platform of a vibratory conveyor which provides the plurality of uninspected parts to a feed conveyer.
14. The method of claim 13 , wherein the top surface of the platform is made of a metal that is substantially covered with a material, the material serving to increase the energy absorption and surface friction of the top surface of the platform.
15. The method of claim 14 , wherein the vibratory conveyor further includes a plurality of resilient fiberglass legs mechanically coupled to and supporting a bottom surface of the platform and an air cylinder mechanically coupled to the bottom surface of the platform, the air cylinder varying the magnitude and frequency of the vibration of the vibratory conveyor in response to the processor.
16. The method of claim 12 , further including the step of:
determining the height of each of the plurality of uninspected parts.
17. The method of claim 12 , further including the step of:
backlighting the plurality of uninspected parts as the plurality of uninspected parts move through the inspection area, the backlighting enhancing the ability of a sorting camera to capture gray scale images of each of the plurality of uninspected parts.
18. The method of claim 12 , further including:
setting a scan rate for a sorting camera responsive to the speed of a feed conveyor, wherein the sorting camera captures an image of each of the plurality of uninspected parts and the feed conveyor distributes and moves the uninspected parts through an inspection area.
19. A sorting system for automatically inspecting a plurality of uninspected objects, the system sorting acceptable objects from defective objects, the system comprising:
a feed conveyer for receiving a plurality of uninspected objects, the feed conveyor moving the uninspected objects through an inspection area;
a sorting camera positioned adjacent the inspection area, the sorting camera for capturing an image of each of the plurality of uninspected objects as the plurality of uninspected objects move through the inspection area;
at least one rejection valve positioned for directing a defective object such that the defective object is separated from inspected acceptable objects;
a light source positioned for backlighting the plurality of uninspected objects as the plurality of uninspected objects move through the inspection area, wherein the inspection area is not located on a belt of the feed conveyor; and
a computer system, including:
a processor coupled to the feed conveyer, the sorting camera, the at least one rejection valve and the light source, wherein the processor executes an inspection routine that controls the speed of the feed conveyer, the scanning rate of the sorting camera, the at least one rejection valve and the light provide by the light source, and wherein the processor executing the inspection routine compares the captured image to at least one stored template image to determine whether each of the uninspected objects is defective.
20. The system of claim 20 , wherein the processor only compares edge pixels of the captured image to the at least one stored template image to determine whether each of the uninspected objects is defective.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/749,642 US20040151364A1 (en) | 2000-06-20 | 2003-12-31 | Automated part sorting system |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/597,946 US6701001B1 (en) | 2000-06-20 | 2000-06-20 | Automated part sorting system |
US10/749,642 US20040151364A1 (en) | 2000-06-20 | 2003-12-31 | Automated part sorting system |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/597,946 Continuation US6701001B1 (en) | 2000-06-20 | 2000-06-20 | Automated part sorting system |
Publications (1)
Publication Number | Publication Date |
---|---|
US20040151364A1 true US20040151364A1 (en) | 2004-08-05 |
Family
ID=31716136
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/597,946 Expired - Lifetime US6701001B1 (en) | 2000-06-20 | 2000-06-20 | Automated part sorting system |
US10/749,642 Abandoned US20040151364A1 (en) | 2000-06-20 | 2003-12-31 | Automated part sorting system |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/597,946 Expired - Lifetime US6701001B1 (en) | 2000-06-20 | 2000-06-20 | Automated part sorting system |
Country Status (1)
Country | Link |
---|---|
US (2) | US6701001B1 (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020076096A1 (en) * | 2000-12-15 | 2002-06-20 | Mitutoyo Corporation | System and methods for determining the settings of multiple light sources in a vision system |
US20060088196A1 (en) * | 2004-10-25 | 2006-04-27 | Popovich Joseph Jr | Embedded imaging and control system |
EP1743713A1 (en) * | 2005-07-13 | 2007-01-17 | Radix Systems Limited | Fluid jet sorter |
US20100172573A1 (en) * | 2009-01-07 | 2010-07-08 | Michael Bailey | Distinguishing Colors of Illuminated Objects Using Machine Vision |
US20110026804A1 (en) * | 2009-08-03 | 2011-02-03 | Sina Jahanbin | Detection of Textural Defects Using a One Class Support Vector Machine |
US20140054132A1 (en) * | 2012-08-24 | 2014-02-27 | Ho Chi WONG | Vibration feeding apparatus and method |
AU2012201855B2 (en) * | 2011-04-01 | 2015-03-05 | Joy Global Underground Mining Llc | Imaging-based interface sensor and control device for mining machines |
US20170059391A1 (en) * | 2015-08-26 | 2017-03-02 | R.J. Reynolds Tobacco Company | Capsule object inspection system and associated method |
WO2018200866A1 (en) * | 2017-04-26 | 2018-11-01 | UHV Technologies, Inc. | Material sorting using a vision system |
CN108734710A (en) * | 2018-06-14 | 2018-11-02 | 厦门理工学院 | A kind of intelligence fruits and vegetables selection method |
US10302598B2 (en) | 2016-10-24 | 2019-05-28 | General Electric Company | Corrosion and crack detection for fastener nuts |
US10625304B2 (en) | 2017-04-26 | 2020-04-21 | UHV Technologies, Inc. | Recycling coins from scrap |
CN111167731A (en) * | 2019-10-23 | 2020-05-19 | 武汉库柏特科技有限公司 | Product sorting method, product sorting system and intelligent sorting robot |
US10722922B2 (en) | 2015-07-16 | 2020-07-28 | UHV Technologies, Inc. | Sorting cast and wrought aluminum |
CN113333321A (en) * | 2021-05-11 | 2021-09-03 | 北京若贝特智能机器人科技有限公司 | Automatic identification and classification conveying method, system and device and storage medium |
US11278937B2 (en) | 2015-07-16 | 2022-03-22 | Sortera Alloys, Inc. | Multiple stage sorting |
WO2023055425A1 (en) * | 2021-09-28 | 2023-04-06 | Sortera Alloys, Inc. | Sorting based on chemical composition |
WO2024035963A3 (en) * | 2022-08-12 | 2024-03-21 | Marble, Inc. | Product classification, sorting, and packing systems and methods |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6701001B1 (en) * | 2000-06-20 | 2004-03-02 | Dunkley International, Inc. | Automated part sorting system |
US20050226489A1 (en) * | 2004-03-04 | 2005-10-13 | Glenn Beach | Machine vision system for identifying and sorting projectiles and other objects |
US9424634B2 (en) * | 2004-03-04 | 2016-08-23 | Cybernet Systems Corporation | Machine vision system for identifying and sorting projectiles and other objects |
US7313270B2 (en) * | 2004-05-19 | 2007-12-25 | Applied Vision Company, Llc | Vision system and method for process monitoring |
US7394937B2 (en) | 2004-05-19 | 2008-07-01 | Applied Vision Company, Llc | Vision system and method for process monitoring |
US20060083419A1 (en) * | 2004-10-18 | 2006-04-20 | Michael Carbaugh | Systems and methods for isolating parts |
DE102005026419B4 (en) * | 2005-06-08 | 2011-01-05 | Mühlbauer Ag | Method and device for geometric measurement of flat bodies |
US7669707B2 (en) * | 2006-06-29 | 2010-03-02 | Dunkley International, Inc. | Material handling apparatus with integrated part sorter |
EP2030895A1 (en) * | 2007-08-31 | 2009-03-04 | Uhlmann VisioTec GmbH | Device for monitored tablet filling |
WO2009074708A1 (en) * | 2007-10-11 | 2009-06-18 | Euroelektro International Oy | Use of a smart camera for controlling an industrial ac drive |
NL2009980C2 (en) * | 2012-12-13 | 2014-06-16 | Ct Voor Tech Informatica B V | A method of producing glass products from glass product material and an assembly for performing said method. |
US9478030B1 (en) * | 2014-03-19 | 2016-10-25 | Amazon Technologies, Inc. | Automatic visual fact extraction |
US9731328B2 (en) * | 2015-08-03 | 2017-08-15 | Linear Group Services, LLC | Inspection and sorting machine |
TWI606870B (en) * | 2015-11-04 | 2017-12-01 | 澧達科技股份有限公司 | Electronic product sorting system and sorting method |
US10526124B2 (en) | 2016-05-25 | 2020-01-07 | International Business Machines Corporation | Surface distortion detector for packaging |
WO2019079867A1 (en) * | 2017-10-27 | 2019-05-02 | Vettorazzi Leandro | Automation system and method for sorting returnable racks |
US11461887B2 (en) | 2020-02-14 | 2022-10-04 | Pratt & Whitney Canada Corp. | System and method for inspecting workpieces |
Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4281933A (en) * | 1980-01-21 | 1981-08-04 | Fmc Corporation | Apparatus for sorting fruit according to color |
US4414566A (en) * | 1981-04-03 | 1983-11-08 | Industrial Automation Corporation | Sorting and inspection apparatus and method |
US4581762A (en) * | 1984-01-19 | 1986-04-08 | Itran Corporation | Vision inspection system |
US4696047A (en) * | 1985-02-28 | 1987-09-22 | Texas Instruments Incorporated | Apparatus for automatically inspecting electrical connecting pins |
US4876728A (en) * | 1985-06-04 | 1989-10-24 | Adept Technology, Inc. | Vision system for distinguishing touching parts |
US5353356A (en) * | 1989-02-09 | 1994-10-04 | Waugh Richard M | Product gauge methods and apparatus for use in the optical determination of the acceptability of products |
US5638657A (en) * | 1994-05-09 | 1997-06-17 | Merck & Co., Inc. | System and method for automatically feeding, inspecting and diverting tablets for continuous filling of tablet containers |
US5887073A (en) * | 1995-09-01 | 1999-03-23 | Key Technology, Inc. | High speed mass flow food sorting apparatus for optically inspecting and sorting bulk food products |
US5893465A (en) * | 1998-06-26 | 1999-04-13 | Welliver Metal Products Corporation | Food product sorter |
US5917726A (en) * | 1993-11-18 | 1999-06-29 | Sensor Adaptive Machines, Inc. | Intelligent machining and manufacturing |
US5960098A (en) * | 1995-06-07 | 1999-09-28 | Agri-Tech, Inc. | Defective object inspection and removal systems and methods for identifying and removing defective objects |
US5966457A (en) * | 1955-06-14 | 1999-10-12 | Lemelson; Jerome H. | Method for inspecting, coding and sorting objects |
US5978502A (en) * | 1996-04-01 | 1999-11-02 | Cognex Corporation | Machine vision methods for determining characteristics of three-dimensional objects |
US6005959A (en) * | 1995-02-17 | 1999-12-21 | International Business Machines Corporation | Produce size recognition system |
US6031931A (en) * | 1996-03-15 | 2000-02-29 | Sony Corporation | Automated visual inspection apparatus |
US6049379A (en) * | 1997-12-30 | 2000-04-11 | Coors Brewing Company | Method for inspecting translucent objects using imaging techniques |
US6064759A (en) * | 1996-11-08 | 2000-05-16 | Buckley; B. Shawn | Computer aided inspection machine |
US6701001B1 (en) * | 2000-06-20 | 2004-03-02 | Dunkley International, Inc. | Automated part sorting system |
-
2000
- 2000-06-20 US US09/597,946 patent/US6701001B1/en not_active Expired - Lifetime
-
2003
- 2003-12-31 US US10/749,642 patent/US20040151364A1/en not_active Abandoned
Patent Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5966457A (en) * | 1955-06-14 | 1999-10-12 | Lemelson; Jerome H. | Method for inspecting, coding and sorting objects |
US4281933A (en) * | 1980-01-21 | 1981-08-04 | Fmc Corporation | Apparatus for sorting fruit according to color |
US4414566A (en) * | 1981-04-03 | 1983-11-08 | Industrial Automation Corporation | Sorting and inspection apparatus and method |
US4581762A (en) * | 1984-01-19 | 1986-04-08 | Itran Corporation | Vision inspection system |
US4696047A (en) * | 1985-02-28 | 1987-09-22 | Texas Instruments Incorporated | Apparatus for automatically inspecting electrical connecting pins |
US4876728A (en) * | 1985-06-04 | 1989-10-24 | Adept Technology, Inc. | Vision system for distinguishing touching parts |
US5353356A (en) * | 1989-02-09 | 1994-10-04 | Waugh Richard M | Product gauge methods and apparatus for use in the optical determination of the acceptability of products |
US5917726A (en) * | 1993-11-18 | 1999-06-29 | Sensor Adaptive Machines, Inc. | Intelligent machining and manufacturing |
US5638657A (en) * | 1994-05-09 | 1997-06-17 | Merck & Co., Inc. | System and method for automatically feeding, inspecting and diverting tablets for continuous filling of tablet containers |
US6005959A (en) * | 1995-02-17 | 1999-12-21 | International Business Machines Corporation | Produce size recognition system |
US5960098A (en) * | 1995-06-07 | 1999-09-28 | Agri-Tech, Inc. | Defective object inspection and removal systems and methods for identifying and removing defective objects |
US5887073A (en) * | 1995-09-01 | 1999-03-23 | Key Technology, Inc. | High speed mass flow food sorting apparatus for optically inspecting and sorting bulk food products |
US6031931A (en) * | 1996-03-15 | 2000-02-29 | Sony Corporation | Automated visual inspection apparatus |
US5978502A (en) * | 1996-04-01 | 1999-11-02 | Cognex Corporation | Machine vision methods for determining characteristics of three-dimensional objects |
US6064759A (en) * | 1996-11-08 | 2000-05-16 | Buckley; B. Shawn | Computer aided inspection machine |
US6049379A (en) * | 1997-12-30 | 2000-04-11 | Coors Brewing Company | Method for inspecting translucent objects using imaging techniques |
US5893465A (en) * | 1998-06-26 | 1999-04-13 | Welliver Metal Products Corporation | Food product sorter |
US6701001B1 (en) * | 2000-06-20 | 2004-03-02 | Dunkley International, Inc. | Automated part sorting system |
Cited By (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6987876B2 (en) * | 2000-12-15 | 2006-01-17 | Mitutoyo Corporation | System and methods for determining the settings of multiple light sources in a vision system |
US20020076096A1 (en) * | 2000-12-15 | 2002-06-20 | Mitutoyo Corporation | System and methods for determining the settings of multiple light sources in a vision system |
AU2010200298B2 (en) * | 2004-10-25 | 2012-02-02 | Parata Systems, Llc | Embedded imaging and control system |
US20060088196A1 (en) * | 2004-10-25 | 2006-04-27 | Popovich Joseph Jr | Embedded imaging and control system |
WO2006047508A1 (en) | 2004-10-25 | 2006-05-04 | Mckesson Automation Systems, Inc. | Embedded imaging and control system |
US8121392B2 (en) | 2004-10-25 | 2012-02-21 | Parata Systems, Llc | Embedded imaging and control system |
EP1743713A1 (en) * | 2005-07-13 | 2007-01-17 | Radix Systems Limited | Fluid jet sorter |
US20100172573A1 (en) * | 2009-01-07 | 2010-07-08 | Michael Bailey | Distinguishing Colors of Illuminated Objects Using Machine Vision |
US8320662B2 (en) * | 2009-01-07 | 2012-11-27 | National Instruments Corporation | Distinguishing colors of illuminated objects using machine vision |
US20110026804A1 (en) * | 2009-08-03 | 2011-02-03 | Sina Jahanbin | Detection of Textural Defects Using a One Class Support Vector Machine |
US8457414B2 (en) * | 2009-08-03 | 2013-06-04 | National Instruments Corporation | Detection of textural defects using a one class support vector machine |
AU2012201855B2 (en) * | 2011-04-01 | 2015-03-05 | Joy Global Underground Mining Llc | Imaging-based interface sensor and control device for mining machines |
US9650893B2 (en) | 2011-04-01 | 2017-05-16 | Joy Mm Delaware, Inc. | Imaging-based interface sensor and control device for mining machines |
US9965864B2 (en) | 2011-04-01 | 2018-05-08 | Joy Mm Delaware, Inc. | Imaging-based interface sensor and control device for mining machines |
US20140054132A1 (en) * | 2012-08-24 | 2014-02-27 | Ho Chi WONG | Vibration feeding apparatus and method |
US8985305B2 (en) * | 2012-08-24 | 2015-03-24 | Asm Technology Singapore Pte Ltd | Vibration feeding apparatus and method |
US10722922B2 (en) | 2015-07-16 | 2020-07-28 | UHV Technologies, Inc. | Sorting cast and wrought aluminum |
US11471916B2 (en) | 2015-07-16 | 2022-10-18 | Sortera Alloys, Inc. | Metal sorter |
US11278937B2 (en) | 2015-07-16 | 2022-03-22 | Sortera Alloys, Inc. | Multiple stage sorting |
US20170059391A1 (en) * | 2015-08-26 | 2017-03-02 | R.J. Reynolds Tobacco Company | Capsule object inspection system and associated method |
US9766114B2 (en) * | 2015-08-26 | 2017-09-19 | R.J. Reynolds Tobacco Company | Capsule object inspection system and associated method |
US10710119B2 (en) | 2016-07-18 | 2020-07-14 | UHV Technologies, Inc. | Material sorting using a vision system |
US10302598B2 (en) | 2016-10-24 | 2019-05-28 | General Electric Company | Corrosion and crack detection for fastener nuts |
US10625304B2 (en) | 2017-04-26 | 2020-04-21 | UHV Technologies, Inc. | Recycling coins from scrap |
US11260426B2 (en) | 2017-04-26 | 2022-03-01 | Sortera Alloys, hic. | Identifying coins from scrap |
WO2018200866A1 (en) * | 2017-04-26 | 2018-11-01 | UHV Technologies, Inc. | Material sorting using a vision system |
CN108734710A (en) * | 2018-06-14 | 2018-11-02 | 厦门理工学院 | A kind of intelligence fruits and vegetables selection method |
CN111167731A (en) * | 2019-10-23 | 2020-05-19 | 武汉库柏特科技有限公司 | Product sorting method, product sorting system and intelligent sorting robot |
CN113333321A (en) * | 2021-05-11 | 2021-09-03 | 北京若贝特智能机器人科技有限公司 | Automatic identification and classification conveying method, system and device and storage medium |
WO2023055425A1 (en) * | 2021-09-28 | 2023-04-06 | Sortera Alloys, Inc. | Sorting based on chemical composition |
WO2024035963A3 (en) * | 2022-08-12 | 2024-03-21 | Marble, Inc. | Product classification, sorting, and packing systems and methods |
Also Published As
Publication number | Publication date |
---|---|
US6701001B1 (en) | 2004-03-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6701001B1 (en) | Automated part sorting system | |
US6805245B2 (en) | Object sorting system | |
US6265683B1 (en) | Semiconductor material classification device | |
US5405015A (en) | System and method for seeking and presenting an area for reading with a vision system | |
US7364043B2 (en) | Fastener inspection system | |
US4726898A (en) | Apparatus for spinning fruit for sorting thereof | |
KR100301976B1 (en) | Non-contact surface defect detection method and apparatus | |
EP3110569B1 (en) | An improved machine for grading small sized irregular objects and a process thereof | |
EP0833701B1 (en) | Defective object inspection and separation system | |
US6059117A (en) | Method for sorting product | |
US4969746A (en) | Component inspection apparatus and method | |
US7173692B2 (en) | Device and method for optically inspecting operating holes formed in heads of screws | |
US10189055B2 (en) | Color based optical grading system with multi reflectance and multi-angle views | |
JPH01249181A (en) | Parts sorting method for automatic appearance screening machine for chip parts | |
GB1152407A (en) | Photometric Sorting Apparatus | |
EP0413522A2 (en) | Detection of opaque foreign articles from among transparent bodies | |
WO2021161341A1 (en) | System for modular multi-grade sorting and a method thereof | |
US5311977A (en) | High resolution parts handling system | |
EP4162256A1 (en) | Apparatus for detecting matter | |
US4819783A (en) | Automated inspection system and method | |
EP0105114A2 (en) | Apparatus for spinning fruit for sorting thereof | |
CA2738368C (en) | Multiple vision system and method | |
JPH09178430A (en) | Camera-operated goods screening device | |
SU1036383A1 (en) | Method of photometric separation of lumpy materials | |
Morade | Application of Image Processing for Automatic Cleaning of Rice |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |