Mode Detection by Relaxation

  • Authors:
  • A. Touzani;J. G. Postaire

  • Affiliations:
  • Univ. des Sciences et Techniques de Lille Flandres-Artois, France;Univ. des Sciences et Tech. de Lille Flandres-Artois, France

  • Venue:
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Year:
  • 1988

Quantified Score

Hi-index 0.14

Visualization

Abstract

A relaxation process is described and applied to the detection of the modes of the underlying probability density function for clustering multidimensional data. When the process is iterated, the label probabilities become very high in the modal region and very low in the valleys, so that mode detection becomes trivial.