Adaptive clustering for segmentation and classification

Date

2000-05

Journal Title

Journal ISSN

Volume Title

Publisher

Texas Tech University

Abstract

The purpose of image segmentation is to extract different objects embedded in an image. Clustering algorithms have been used for image segmentation for many years now. In recent years, many sophisticated image segmentation techniques have been developed; some of them being those employing fuzzy self- supervised neural networks based clustering algorithms.

This work reviews neuro- fuzzy clustering techniques, basic image segmentation techniques and demonstrates the application of the adaptive clustering technique in segmentation. The Integrated Adaptive Fuzzy Clustering (lAFC) algorithm, which combines neural networks with fuzzy optimization constraints, is discussed in detail. The application of lAFC in image segmentation is explored.

Description

Keywords

Neural networks, Cluster analysis, Fuzzy algorithms, Image processing

Citation