CaltechAUTHORS
  A Caltech Library Service

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

Battiti, Roberto (1989) Low level image segmentation with high level "emergent properties": color based segmentation. In: International Workshop on Industrial Applications of Machine Intelligence and Vision. IEEE , Piscataway, NJ, pp. 128-132. http://resolver.caltech.edu/CaltechAUTHORS:20170711-155115544

[img] PDF - Published Version
See Usage Policy.

654Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20170711-155115544

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.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/MIV.1989.40537DOIArticle
http://ieeexplore.ieee.org/document/40537/PublisherArticle
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.
Funders:
Funding AgencyGrant Number
Department of Energy (DOE)DE-FG03-85ER25009
NSFIST-8700064
IBMUNSPECIFIED
Record Number:CaltechAUTHORS:20170711-155115544
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20170711-155115544
Official Citation:R. Battiti, "Low level image segmentation with high level `emergent properties': color based segmentation," International Workshop on Industrial Applications of Machine Intelligence and Vision,, Tokyo, 1989, pp. 128-132. doi: 10.1109/MIV.1989.40537
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:78970
Collection:CaltechAUTHORS
Deposited By: Kristin Buxton
Deposited On:11 Jul 2017 23:45
Last Modified:11 Jul 2017 23:45

Repository Staff Only: item control page