Image analysis – Pattern recognition – Feature extraction
Reexamination Certificate
2000-12-15
2002-10-08
Lee, Thomas D (Department: 2624)
Image analysis
Pattern recognition
Feature extraction
C382S266000
Reexamination Certificate
active
06463175
ABSTRACT:
U.S. PATENT REFERENCES
1. U.S. Pat. No. 5,315,700 entitled, “Method and Apparatus for Rapidly Processing Data Sequences”, by Johnston et. al., May 24, 1994
2. U.S. Pat. No. 6,130,967 entitled, “Method and Apparatus for a Reduced Instruction Set Architecture for Multidimensional Image Processing”, by Shih-Jong J. Lee, et. al., Oct. 10, 2000
3. Pending application Ser. No. 08/888,116 entitled, “Method and Apparatus for Semiconductor Wafer and LCD Inspection Using Multidimensional Image Decomposition and Synthesis”, by Shih-Jong J. Lee, et. al., filed Jul. 3, 1997
4. U.S. Pat. No. 6,122,397 entitled, “Method and Apparatus for Maskless Semiconductor and Liquid Crystal Display Inspection”, by Shih-Jong J. Lee, et. al., Sep. 19, 2000
5. U.S. Pat. No. 6,148,099 entitled, “Method and Apparatus for Incremental Concurrent Learning in Automatic Semiconductor Wafer and Liquid Crystal Display Defect Classification”, by Shih-Jong J. Lee et. al., Nov. 14, 2000
CO-PENDING U.S. PATENT APPLICATIONS
1. U.S. patent application Ser. No. 09/693,723, “Image Processing System with Enhanced Processing and Memory Management”, by Shih-Jong J. Lee et. al, filed Oct. 20, 2000
2. U.S. patent application Ser. No. 09/693,378, “Image Processing Apparatus Using a Cascade of Poly-Point Operations”, by Shih-Jong J. Lee, filed Oct. 20, 2000
3. U.S. patent application Ser. No. 09/692,948, “High Speed Image Processing Apparatus Using a Cascade of Elongated Filters Programmed in a Computer”, by Shih-Jong J. Lee et. al., filed Oct. 20, 2000
4. U.S. patent application Ser. No. 09/703,018, “Automatic Referencing for Computer Vision Applications”, by Shih-Jong J. Lee et. al, filed Oct. 31, 2000
5. U.S. patent application Ser. No. 09/702,629, “Run-Length Based Image Processing Programmed in a Computer”, by Shih-Jong J. Lee, filed Oct. 31, 2000
6. U.S. Patent Application entitled, “Structure-guided Image Measurement Method” by Shih-Jong J. Lee et. al., filed Dec. 15, 2000.
REFERENCES
1. Lee, J S J, Haralick, R M and Shapiro, L G, “Morphologic Edge Detection,” IEEE Journal of Robotics and Automation RA-3 No.2:142-56, April, 1987.
2. Haralick R M and Shapiro, L G, “Survey Image Segmentation Techniques,” Comput. Vision, Graphics, and Image Processing, vol. 29 No. 1: 100-132, January 1985.
3. Otsu N, “A Threshold Selection Method from Gray-level Histograms,” IEEE Trans. System Man and Cybernetics, vol. SMC-9, No. 1, January 1979, PP 62-66.
4. Serra, J, “Image Analysis and Mathematical Morphology,” London: Academic Press, pp 319-321, 1982.
5. Sternberg, S R, “Grayscale Morphology,” Comput. Vision, Graphics, and Image Processing, vol. 35 No. 3: 333-355, September 1986.
TECHNICAL FIELD
This invention relates to image processing methods that incorporate knowledge of object structure derived from the image itself or from a-priori knowledge of an object's structural relationships from its design data (such as CAD drawings) to enhance object features and/or guide image measurement estimation and object detection.
BACKGROUND OF THE INVENTION
Common tasks in computer vision applications include enhancement and detection of objects of interest, refinement of detected object masks, and measurement, alignment or classification of the refined object. Other applications include enhancement for image compression or image highlighting for display. Many computer vision applications require the enhancement and measurement of image features for objects of interest characterization or detection. Application domain knowledge is available in most computer vision applications. The application domain knowledge can often be expressed as structures of image features such as shaped color, edges, lines and regions, or changes with time such as object motion on a prescribed path. The structures include spatial relationships of object features such as shape, size, intensity distribution, parallelism, co-linearity, adjacency, position, etc. The structure information can be particularly well defined in industrial applications such as semiconductor, electronic or machine part inspections. In machine part inspections, most of the work-pieces have available Computer Aided Design (CAD) data that specifies CAD components as entities (e.g. LINE, POINT, 3DFACE, 3DPOLYINE, 3DVERTEX, LINE, POINT, 3DFACE, 3DPOLYLINE, 3DVERTEX, etc.) and blocks (properties that are associated) of entities. Semiconductor applications frequently have step and repeat type processes that form lines, patterns, and mosaic structures. In biomedical or scientific applications, structure information may also be loosely defined. For example, a cell nucleus is generally round, frequently stains dark, and different but known approximate shapes can differentiate different types of blood cells or chromosomes.
The capability of a computer vision system is often characterized by its detection/measurement accuracy, repeatability and throughput. It is desirable to achieve sub-pixel measurement accuracy and repeatability for many computer vision applications. Application domain knowledge used according to this invention can significantly improve the capability of a computer vision system to make accurate and repeatable measurements. However, it is non-trivial to efficiently use the application domain knowledge in high precision applications.
PRIOR ART
Prior art uses an image segmentation approach for image feature detection or measurement (Haralick R M and Shapiro, L G, “Survey Image Segmentation Techniques”, Comput. Vision, Graphics, and Image Processing, vol. 29 No. 1: 100-132, January 1985). The image segmentation approach converts a grayscale image into a binary image that contains object of interest masks. Binary thresholding is a common technique used in the image segmentation approach to create masks.
Because edges or features of an image are imaged by the optical and imaging system as continuously varying gray levels, there exists no single gray level that represents edge pixels. For this reason, any system that depends on taking a binary threshold of the image before critical dimensions are determined must necessarily introduce quantization errors into the measurement. Binary thresholding also exacerbates the resolution limiting effect of system noise.
Prior art applies application domain structure information through a projection/dispersion approach. The projection/dispersion approach integrates image pixel values in a pre-defined direction in the image. This can be done using a binary image (projection) or grayscale image (dispersion) and results in a one-dimensional plot of summed pixel values. The application domain structure information defines the projection directions, however misalignments, variations in illumination, and image noise limit the resolving capability of these projections. The prior art approach is sensitive to system variations such as rotation, object illumination, changes in object surface texture (which affects gray levels), etc. Rotation errors result in the integration of pixel values along a wrong direction that is destructive to accuracy. Furthermore, the projection-based approach cannot effectively combine multiple two-dimensional structure information (such as anti-parallelism, orthogonality, intersection, curvaceous qualities) where features of interest may be along different directions or complex. Another difficulty in the prior art is that two-dimensional processing is needed for reliable sub-pixel accuracy due to the utility of using as many pixels as possible for the measurement. Use of all possible pixels minimizes spatial quantization errors and also aids reconstruction and interpolation between sample values. Herein there are two difficulties, the prior art does not take advantage of all pixels whose position is related, the prior art confuses image surface information and image edge information through the use of projection, and the projections cannot be used effectively with complex structures. Where the prior art could have employed two dimensions to achieve a better result (but not a projection result), such grayscale processing is in the prior a
Brinich Stephen
Lee Thomas D
LandOfFree
Structure-guided image processing and image feature enhancement does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Structure-guided image processing and image feature enhancement, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Structure-guided image processing and image feature enhancement will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2940732