Defective object inspection and removal systems and methods for identifying and removing defective objects

• US 5,960,098 A
• Filed: 11/14/1997
• Issued: 09/28/1999
• Est. Priority Date: 06/07/1995
• Status: Expired due to Fees

• Current Assignee: Grantway LLC
• Original Assignee: Agri-Tech, Inc.
• Inventors: Tao, Yang
• Primary Examiner(s): Johns, Andrew W.
• Application Number:
  US08/970,420
• Time in Patent Office: 683 Days
• Field of Search: 382/110, 382/154, 382/173, 382/203, 382/256, 382/257, 382/274, 382/276, 348/89, 348/91, 209/577, 209/576, 250/559.45, 250/559.46, 356/237.1, 356/376, 345/426, 345/427
• US Class Current: 382/110
• CPC Class Codes: B07C 5/3422 using video scanning devices, e.g. TV-cameras

Abstract

Image processing system using cameras and image processing techniques to identify undesirable objects on roller conveyor lines. The cameras above the conveyor capture images of the passing objects. The roller background information is removed and images of the objects remain. To analyze each individual object accurately, the adjacent objects are isolated and small noisy residue fragments are removed. A spherical optical transform and a defect preservation transform preserve any defect levels on objects even below the roller background and compensate for the non-lambertian gradient reflectance on spherical objects at their curvatures and dimensions. Defect segments are then extracted from the resulting transformed images. The size, level, and pattern of the defect segments indicate the degree of defects in the object. The extracted features are fed into a recognition process and a decision making system for grade rejection decisions. The locations in coordinates of the defects generated by a defect allocation function are combined with defect rejection decisions and user parameters to signal appropriate mechanical actions such as to separate objects with defects from those that are defect-free.

Claims

1. A defective object identification and removal system having a conveyor that transports a plurality of objects through an imaging chamber with a camera disposed within the imaging chamber to capture images of the transported objects, the system comprising:

an image processor for identifying, based on the images, defective objects from among the transported objects by performing a curvature transform on the images to correct the images for differences in gradation caused by differences in light reflectance of the objects and detecting defects in the objects using the corrected images, and for generating defect selection signals when the defective objects have been identified; and

an ejector controller for generating signals to remove the defective objects from the conveyor in response to the defect selection signals.

2. The system of claim 1 wherein the image processor generates plane images corresponding to the images captured by the camera.

3. The system of claim 1 wherein the image processor separates portions of the images corresponding to objects and portions corresponding to defects within ones of the objects.

4. The system of claim 2 wherein the image processor separates portions of the images corresponding to objects and portions corresponding to defects within ones of the objects.

5. The system of claim 1 wherein the image processor locates within the corrected image defect segments based on differences in gradation caused by differences in light reflectance of the defect segments.

6. The system of claim 5, wherein the image processor includes

means for assigning a grade to the objects based on characteristics of the defect segments.

7. The system of claim 6, wherein the image processor further includes

means for generating the defect selection signals based on the grade assigned to the objects.

8. A defective object removal system, comprising:

a conveyor that transports a plurality of objects;

an imaging unit disposed adjacent to the conveyor to capture images of the transported objects;

an image processor, coupled to receive the images from the imaging unit, that corrects the images to compensate for differences in light reflectance due to curvature of the objects, identifies defective objects from the corrected images, and generates ejector signals based on the identified defective objects; and

an ejector unit that removes the defective objects from the conveyor in response to the ejector signals.

9. A method, performed by an image processor, for identifying and separating a defective object from a plurality of objects, comprising the steps of:

receiving images of the objects;

identifying a contour of the objects from the received images;

correcting the received images to compensate for differences in light reflectance due to the contour of the objects;

identifying the defective object from the corrected images; and

generating signals to separate the defective object from the plurality of objects.

10. A system for identifying and separating a defective object from a plurality of objects, comprising:

means for acquiring an image for each of the objects, the acquired image including an object image and a background image;

means for separating the object image from the background image in the acquired image;

means for creating a contour image from the object image;

means for converting the contour image to a binary image;

means for forming an inverse image of the binary image;

means for identifying the defective object by adding the inverse image to the contour image; and

means for separating the defective object from other ones of the objects.

11. The system of claim 10, wherein the means for creating a contour image includes

means for forming a series of rings of the object image, each of the rings relating to a different intensity level of the object due to varying reflectance levels of the object.

12. The system of claim 11, wherein the means for forming an inverse image includes

means for setting the intensity levels for each of the rings to a different uniform level to eliminate any defect from the binary image, and

means for inverting the intensity level for each of the rings of the binary image.

13. A method for identifying and separating a defective object from a plurality of objects, comprising the steps of:

acquiring an image for each of the objects, the acquired image including an object image and a background image;

separating the object image from the background image in the acquired image;

creating a contour image from the object image;

converting the contour image to a binary image;

forming an inverse image of the binary image;

identifying the defective object by adding the inverse image to the contour image; and

separating the defective object from other ones of the objects.

14. The method of claim 13, wherein the creating a contour image step includes the substep of

forming a series of rings of the object image, each of the rings relating to a different intensity level of the object due to varying reflectance levels of the object.

15. The method of claim 14, wherein the forming an inverse image step includes the

setting the intensity levels for each of the rings to a different uniform level to eliminate any defect from the binary image, and

inverting the intensity level for each of the rings of the binary image.