Saliency-directed color image segmentation using modified particle swarm optimization

  • Authors:
  • Chi-Yu Lee;Jin-Jang Leou;Han-Hui Hsiao

  • Affiliations:
  • Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi 621, Taiwan;Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi 621, Taiwan;Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi 621, Taiwan

  • Venue:
  • Signal Processing
  • Year:
  • 2012

Quantified Score

Hi-index 0.08

Visualization

Abstract

Color image segmentation, an ill-posed problem, can be treated as a process of dividing a color image into some constituent regions and each region is homogeneous. In this study, a saliency-directed color image segmentation approach using ''simple'' modified particle swarm optimization (PSO) is proposed, in which both low-level features and high-level image semantics extracted from each color image are employed. To extract high-level image semantics from each color image, the visual attention saliency map for each color image is generated by three (color, intensity, and orientation) feature maps, which is used to guide region merging using ''simple'' modified PSO and a hybrid fitness function for color image segmentation. The proposed approach contains four stages, namely, color quantization, feature extraction, small region elimination, and region merging using ''simple'' modified PSO. Based on the experimental results obtained in this study, as compared with four comparison approaches, the proposed approach usually provides the better color image segmentation results.