International Journal of Computer Vision

, Volume 2, Issue 3, pp 311–347

Segmenting images using localized histograms and region merging

  • J. Ross Beveridge
  • Joey Griffith
  • Ralf R. Kohler
  • Allen R. Hanson
  • Edward M. Riseman
Article

DOI: 10.1007/BF00158168

Cite this article as:
Beveridge, J.R., Griffith, J., Kohler, R.R. et al. Int J Comput Vision (1989) 2: 311. doi:10.1007/BF00158168

Abstract

A working system for segmenting images of complex scenes is presented. The system integrates techniques that have evolved out of many years of research in low-level image segmentation at the University of Massachusetts and elsewhere. This paper documents the result of this historical evolution. Segmentations produced by the system are used extensively in related image interpretation research.

The system first produces segmentations based upon an analysis of spatially localized feature histograms. These initial segmentations are then simplified using a region merging algorithm. Parameter selection for the local histogram segmentation algorithm is facilitated by mapping the multidimensional parameter space to a one-dimensional parameter which regulates region fragmentation. An extension of this algorithm to multiple features is also presented. Experience with roughly 100 images from different domains has shown the system to be robust and effective. Samples of these results are included.

Copyright information

© Kluwer Academic Publishers 1989

Authors and Affiliations

  • J. Ross Beveridge
    • 1
  • Joey Griffith
    • 1
  • Ralf R. Kohler
    • 1
  • Allen R. Hanson
    • 1
  • Edward M. Riseman
    • 1
  1. 1.Computer and Information ScienceUniversity of MassachusettsAmherstUSA