본문 바로가기
  • Home

Comparison of Edge Detection using Linear Rank Tests in Images

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2005, 10(6), pp.17-26
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

Lim Dong Hoon 1

1경상대학교

Candidate

ABSTRACT

In this paper we propose three nonparametric tests such as Wilcoxon test, Median test and Van der Waerden test, based on linear rank statistics for detecting edges in images. The methods used herein are based on detecting changes in gray-levels obtained using an edge-height parameter between two sub-regions in a window. We compare and analysis the performance of three statistical edge detectors in terms of qualitative measures with the edge maps and objective, quantitative measures.

Citation status

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