Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published April 1989 | Published
Book Section - Chapter Open

Low level image segmentation with high level "emergent properties": color based segmentation

Abstract

The presented method incorporates a discontinuity detection process into a multigrid relaxation algorithm, with the goal of recovering "significant" discontinuities at different scales. Line processes are activated in a deterministic way, depending on local properties of both neighboring line processes (at different scales) and neighboring continuous variables. Computational complexity is O(n) for an image with n pixels and convergence time is a small multiple of that required by one relaxation step at the finest grid. The suggested scheme is applied to the problem of image segmentation based on color differences. These dissimilarities are detected by considering changes in the relative intensity of the red, green and blue components of the pixels adjacent to a given discontinuity. A final relaxation step restricted within the detected boundaries is then suggested as a way of "coloring" the delineated regions in a uniform way. The algorithm has been implemented with high efficiency on a MIMD parallel computer with distributed memory. A coarse grain decomposition is found to be useful for this and other multiscale problems.

Additional Information

© 1989 IEEE. This work was done in the Caltech Concurrent Computation and Neural Networks Program and benefited in many ways from the advice of Geoffrey Fox. I am also pleased to acknowledge useful suggestions and discussions from Paul Messina, Wojtek Furmanski, Christof Koch and Demetri Terzopulos. Work supported in part by DOE grant DE-FG-03-85ER25009, the National Science Foundation with grant IST-8700064 and by IBM.

Attached Files

Published - 00040537.pdf

Files

00040537.pdf
Files (670.6 kB)
Name Size Download all
md5:4f3a9fa8844c0fd8a9d850cacd88d3b5
670.6 kB Preview Download

Additional details

Created:
August 19, 2023
Modified:
October 26, 2023