본문 바로가기
  • Home

Environment-Adaptive Image Segmentation Using Color Invariants

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2010, 15(10), pp.71-78
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

Jang Seok-Woo 1

1안양대학교

Accredited

ABSTRACT

Even though various types of image segmentation methods have been extensively introduced, robustly segmenting images to environmental conditions such as illumination changes, shading, highlight, etc, has been known to be a very difficult task. To resolve the problem in some degree, we propose in this paper an environment-adaptive image segmentation approach using color invariants. The suggested method first introduces several color invariants like W, C, U, N, and H, and automatically measures environmental conditions in which images are captured. It then chooses the most adequate color invariant to environmental factors, and effectively extracts edges using the selected invariant. Experimental results show that the proposed method can robustly perform edge-based segmentation rather than existing methods. We expect that our method will be useful in many real applications which require edge-based image segmentation.

Citation status

* References for papers published after 2023 are currently being built.