Segmentation processes in the visions system

  • Authors:

  • John Prager;Paul Nagin;Ralf Kohler;Allen Hanson;Edward Riseman

  • Affiliations:

  • Computer and Information Science Department, University of Massachusetts, Amherst, Massachusetts;Computer and Information Science Department, University of Massachusetts, Amherst, Massachusetts;Computer and Information Science Department, University of Massachusetts, Amherst, Massachusetts;Computer and Information Science Department, University of Massachusetts, Amherst, Massachusetts and Hampshire College, Amherst, Massachusetts;Computer and Information Science Department, University of Massachusetts, Amherst, Massachusetts

  • Venue:
  • IJCAI'77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 2
  • Year:
  • 1977

Quantified Score

Hi-index 0.00

Visualization

Abstract

In VISIONS the segmentation algorithms receive input from a digitized color image as an array of pixel values, and generate output as a layered graph of symbolically named regions, boundaries, and endpoints -- each with their descriptive attributes. This processed sensory data provides the initial input to the model-building system of VISIONS.