An improved ant colony algorithm for fuzzy clustering in image segmentation

  • Authors:
  • Yanfang Han;Pengfei Shi

  • Affiliations:
  • Institute of Image Processing & Pattern Recognition, Shanghai Jiaotong University, Shanghai 200030, PR China;Institute of Image Processing & Pattern Recognition, Shanghai Jiaotong University, Shanghai 200030, PR China

  • Venue:
  • Neurocomputing
  • Year:
  • 2007

Quantified Score

Hi-index 0.01

Visualization

Abstract

Ant colony algorithm (ACA), inspired by the food-searching behavior of ants, is an evolutionary algorithm and performs well in discrete optimization. In this paper, it is used for fuzzy clustering in image segmentation. Three features such as gray value, gradient and neighborhood of the pixels, are extracted for the searching and clustering process. Unexpectedly, tests show that it is time consuming when dealing with the vast image data. In view of this drawback, improvements have been made by initializing the clustering centers and enhancing the heuristic function to accelerate the searching process. Experiments and comparisons are done to show that the improved ACA-based image segmentation is an efficient and effective approach.