Image analysis – Applications – Manufacturing or product inspection
Reexamination Certificate
2000-09-27
2004-06-29
Mehta, Bhavesh M. (Department: 2625)
Image analysis
Applications
Manufacturing or product inspection
C382S141000, C382S197000, C438S016000, C348S126000
Reexamination Certificate
active
06757421
ABSTRACT:
RESERVATION OF COPYRIGHT
The disclosure of this patent document contains material, which is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the U.S. Patent and Trademark Office patent files or records, but otherwise reserves all copyright rights whatsoever.
BACKGROUND OF THE INVENTION
1. Field of the Invention
Aspects of the invention relate to a machine vision method and an apparatus for the detection of defects.
2. Description of Background Information
Machine vision involves the extraction of vision-related information by obtaining information representing an image, and then processing that information. Machine vision techniques are used in applications including character recognition, industrial inspection of manufactured objects, robot guidance systems, radiology, remote sensing and detecting and others.
In industrial inspections, machine vision is used to sort out products that are blemished, marred or otherwise defective. Golden Template Comparison (GTC) is one type of industrial inspection method that uses image intensity information to detect flaws or defects in two-dimensional scenes of inspected objects. Generally, GTC involves the comparison of a run-time (i.e., test) image to a template image which comprises statistical information obtained from known good scenes, obtained during train-time. More specifically, pixel intensity values of the run-time image are subtracted from those of a template image, and the differences between the two images are observed to determine whether a flaw or defect is present within the inspected object. GTC thus comprises two main phases: training and inspection. During training, the template image is constructed by sampling a plurality of images, each of which represents a scene of an object absent defects. During inspection, the run-time image, which represents the scene of the object to be tested (the inspected object), is then compared to the template image.
Recently, there have been increasing demands for an improved method and apparatus for detecting breaks and short circuits in patterns on printed circuit boards and corresponding exposure film. The use of the GTC method requires a considerable amount of memory to register a number of images as templates since a vast region must be divided into numerous sub-regions at high magnification to detect small defects. A more flexible method of detecting short circuits or breaks in patterns on printed circuit boards and corresponding exposure film is needed.
REFERENCES:
patent: 3909602 (1975-09-01), Micka
patent: 5150423 (1992-09-01), Hoki
patent: 5394481 (1995-02-01), Kumagai et al.
patent: 5404163 (1995-04-01), Kubo
patent: 5430548 (1995-07-01), Hiroi et al.
patent: 5471407 (1995-11-01), Akasaka et al.
patent: 5608816 (1997-03-01), Kawahara et al.
patent: 5694481 (1997-12-01), Lam et al.
patent: 6292582 (2001-09-01), Lin et al.
patent: 6363167 (2002-03-01), Miyano et al.
Carter Aaron
Cognex Corporation
Mehta Bhavesh M.
LandOfFree
Method and apparatus for detecting defects does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for detecting defects, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for detecting defects will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3340880