Share Email Print
cover

Proceedings Paper

Segmentation engine: a real-time image segmentation subsystem
Author(s): Byron E. Dom; Wolf-Ekkehard Blanz; Charles Cox; David Ashby Steele; Alan D. Dorundo
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper describes a system developed for segmenting multiband grayscale images into n-class labeled images at high-throughput rates. This system, which we refer to as the segmentation engine, performs supervised image segmentation using algorithms based on the statistical pattern recognition paradigm. So-called 'features' are computed for each pixel and the feature vector thus formed is presented to a statistical classifier, which uses feature information to determine the most probable class of the pixel. Algorithms are described for the following: features, automatic feature selection, classification and classifier training. While this paper describes the entire system, the algorithmic approach will be emphasized.

Paper Details

Date Published: 11 March 1994
PDF: 16 pages
Proc. SPIE 2183, Machine Vision Applications in Industrial Inspection II, (11 March 1994); doi: 10.1117/12.171223
Show Author Affiliations
Byron E. Dom, IBM Almaden Research Ctr. (United States)
Wolf-Ekkehard Blanz, IBM Almaden Research Ctr. (United States)
Charles Cox, IBM Almaden Research Ctr. (United States)
David Ashby Steele, IBM Almaden Research Ctr. (United States)
Alan D. Dorundo, IBM Almaden Research Ctr. (United States)


Published in SPIE Proceedings Vol. 2183:
Machine Vision Applications in Industrial Inspection II
Benjamin M. Dawson; Stephen S. Wilson; Frederick Y. Wu, Editor(s)

© SPIE. Terms of Use
Back to Top