Projection-based geometrical feature extraction for computer vision: Algorithms in pipeline architectures

Journal Article · Thu Jan 01 00:00:00 EST 1987 · IEEE Trans. Pattern Anal. Mach. Intell.; (United States)

DOI:https://doi.org/10.1109/TPAMI.1987.4767883· OSTI ID:6314962

Sanz, J L; Dinstein, I

In this paper, some image transforms and features such as projections along linear patterns, convex hull approximations, Hough transform for line detection, diameter, moments, and principal components will be considered. Specifically, we present algorithms for computing these features which are suitable for implementation in image analysis pipeline architectures. In particular, random access memories and other dedicated hardware components which may be found in the implementation of classical techniques are not longer needed in our algorithms. The effectiveness of our approach is demonstrated by running some of the new algorithms in conventional short-pipelines for image analysis.

• Research Organization: Dept. of Computer Science, IBM Almaden Research Center, 650 Harry Road, San Jose, CA 95120
• OSTI ID: 6314962
• Journal Information: IEEE Trans. Pattern Anal. Mach. Intell.; (United States), Vol. PAMI-9:1
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
ARRAY PROCESSORS
COMPUTER ARCHITECTURE
DATA-FLOW PROCESSING
IMAGE PROCESSING
ALGORITHMS
PATTERN RECOGNITION
PERFORMANCE
TRANSFORMATIONS
VISION
MATHEMATICAL LOGIC
PROCESSING
PROGRAMMING
990210* - Supercomputers- (1987-1989)