A model for perception of structural image feature

  • Authors:

  • Hajime Enomoto;Naoki Yonezaki;Katsumi Nitta

  • Affiliations:

  • Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan;Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan;Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan

  • Venue:
  • IJCAI'79 Proceedings of the 6th international joint conference on Artificial intelligence - Volume 1
  • Year:
  • 1979

Quantified Score

Hi-index 0.00

Visualization

Abstract

A model to extract a structure feature of images belonging to one category is proposed, implemented and studied. This model consists of two parts i.e. an extraction of partial geometrical features and an extraction of structure feature by using them under the positional constraints. First, necessary conditions which geometrical features should satisfy is stated and a statistical method to select a key feature is described. Then the algorithm to extract structure feature as the maximal set of common subimages which satisfy the positional constraint is introduced. The structure feature is regarded as a intrinsic feature which is used when an animal perceives an image at a glance. The experiment was carried out about image of human faces and had a fairly good results.