Fuzzy homogeneity measures for path-based colour image segmentation. (2nd June 2006)

• Record Type: Journal Article
• Authors: Chamorro-Martinez, J.; Sanchez, D.; Prados-Suarez, B.; Galan-Perales, E.
• Is Part Of: International journal of intelligent systems technologies and applications. Volume 1:Number 3/4(2006)
• Page Start: 301
• Page End: 318
• Publication Date: 2006-06-02
• Subjects: image segmentation -- fuzzy segmentation -- path-based segmentation -- fuzzy connectivity -- fuzzy colour homogeneity -- colour images -- image processing -- uncertainty; Artificial intelligence -- Periodicals; Intelligent control systems -- Periodicals; 006.3
• Languages: English
• ISSNs: 1740-8865

Abstract

In this paper we propose a set of measures to model the concept of homogeneity in path-based image segmentation. We introduce the idea of path homogeneity as the aggregation of resemblances between consecutive pixels in the path. This resemblance is obtained from a measure of resemblance between neighbour pixels. In order to aggregate these resemblance values we propose the use of certain families of t-norms that verify a set of intuitive properties. We have studied the performance and behaviour of these functions through a set of experiments. Finally, we have applied these proposals to obtain fuzzy segmentations from real images.