Image analysis – Color image processing – Pattern recognition or classification using color
Reexamination Certificate
1999-06-01
2003-08-05
Au, Amelia M. (Department: 2623)
Image analysis
Color image processing
Pattern recognition or classification using color
C382S205000, C382S224000, C382S100000
Reexamination Certificate
active
06603877
ABSTRACT:
FIELD
The present invention relates to the optical imaging and scanning inspection of objects (where the term “object” is used herein generically to connote any sample, surface or article-to-be-inspected) for identification of predetermined patterns therein, as for detecting manufacturing defects or other variations in such objects as, for example, electronic circuit boards or wafers or the like, and for determining different material regions of such objects more generally.
BACKGROUND
In connection with such electronic circuit boards, wafers, and similar objects, prior automatic optical image scanning inspection techniques have been successfully employed to detect such defects or variations, with differentiation between, for example, images of conductor and insulator materials, aided by brightness, color and other differences in the light reflected from the different materials, as described in U.S. Pat. No. 5,524,152 of common assignee herewith, and in U. S. Pat. No. 5,119,434.
As wafers and other composites become more complex and involve multilayers of varied material patterns, a greater degree of material discrimination has become essential. The present invention, accordingly, carries such different material categories in optical image inspection to a higher and more sophisticated and accurate level, involving using also local neighborhood comparisons about the various material regions that provide a high degree of likelihood of the correctness and lack of ambiguity of the material identification and characterization.
As before intimated, the optical image scanning inspection of objects requires determination of material regions therein; that is, for example, regions of metal conductor must be defined as different from regions of insulator, and unique types of each must be differentiated. In this way, each region can be processed correctly based on its material. A smooth metal surface can be checked for high-texture regions of contamination; but a textured metal will not necessarily be labeled contaminated. In accordance with the present invention, an imaged object comprising varied materials is categorized into given materials by discriminating several different image characteristics, such as color, texture, brightness, and average brightness (in a highly textured area), and also by observing how a small region compares to the local neighborhood around it.
OBJECTS OF INVENTION
A primary object of the present invention, thus, is to provide a new and improved method of and apparatus for optically imaging and scanning objects constituted of different materials, and for differentiating such materials through a novel material characterization technique that imbues likelihood values for the correct identification and distinguishment of the different materials.
Other and further objects will be explained hereinafter and are more particularly delineated in the appended claims.
SUMMARY
In summary, however, from one of its view points, the invention embraces a method of categorizing different material regions of an object-to-be-inspected, that comprises, optically scanning the object to produce a pixel image thereof; discriminating different pixel regions of the image corresponding to possibly different materials on the basis of color and brightness measurements of the pixel regions and assigning preliminary likelihoods to such discrimination though with ambiguities; comparing the pixel regions with their local neighborhood surroundings in the image, and preferably also with a reference image, to compare likelihoods and ambiguities of the pixel and its local neighborhood with the reference image, thereby to assist in resolving said ambiguities and to determine the materials categorization of the pixels with high likelihoods.
Preferred and best mode design and implementations will be detailed hereinafter.
REFERENCES:
patent: 4650333 (1987-03-01), Crabb et al.
patent: 4764969 (1988-08-01), Ohtombe et al.
patent: 5524152 (1996-06-01), Bishop et al.
patent: 5544256 (1996-08-01), Brecher et al.
patent: 5546475 (1996-08-01), Bolle et al.
patent: 5680476 (1997-10-01), Schmidt et al.
patent: 5801965 (1998-09-01), Takagi et al.
patent: 5818964 (1998-10-01), Itoh
patent: 5969753 (1999-10-01), Robinson
patent: 6075880 (2000-06-01), Kollhof et al.
patent: 6075891 (2000-06-01), Burman
patent: 6122042 (2000-09-01), Wunderman et al.
Au Amelia M.
Beltronics Inc.
Bhatnagar Anand
Rines and Rines
LandOfFree
Method of and apparatus for optical imaging inspection of... 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 of and apparatus for optical imaging inspection of..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of and apparatus for optical imaging inspection of... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3098169