본문 바로가기
  • Home

An Improved Object Detection Methodusing Hausdorff Distance based on Elastic Deformation Energy

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2007, 12(2), pp.71-76
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

원보환 1 KOO JA YOUNG 1

1단국대학교

Accredited

ABSTRACT

Object detection process which makes decision on the existence of meaningful objects in a given image is a crucial part of image recognition in computer vision system. Hausdorff distance metric has been used in object detection and shows good results in applications such as face recognition. It defines the dissimilarity between two sets of points and is used to find the object that is most similar to the given model. This paper proposes a Hausdorff distance based detection method that uses directional information of points to improve detection accuracy when the sets of points are derived from edge extraction as is in usual cases. In this method, elastic energy needed to make two directional points coincident is used as a measure of similarity.

Citation status

* References for papers published after 2022 are currently being built.