Translator Disclaimer
30 April 1987 Recognition Methodology: Algorithms & Architecture
Author Affiliations +
Computer recognition and inspection of objects is, in general , a complex procedure requiring a variety of kinds of steps which successively transform the iconic data to recognition information. We hypothesize that the difficulty of today's computer vision and recognition technology to be able to handle unconstrained environments is due to the fact that the existing algorithms are specialized and do not develop one or more of the necessary steps to a high enough degree. Our thesis is that there are no shortcuts. A recognition methodology must pay substantial attention to each of the following five steps: conditioning, labeling, grouping, extracting, and matching.
© (1987) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Robert M. Haralick "Recognition Methodology: Algorithms & Architecture", Proc. SPIE 0755, Image Pattern Recognition: Algorithm Implementations, Techniques, and Technology, (30 April 1987);


Point set pattern matching using the Procrustean metric
Proceedings of SPIE (July 08 1994)
Connection Machine Vision Applications
Proceedings of SPIE (June 06 1987)
Locally linear embedding based on local correlation
Proceedings of SPIE (January 13 2012)
Parallel Processing For Computer Vision
Proceedings of SPIE (November 22 1982)

Back to Top