Estimation of Initial Contour Based on Edge Background Subtraction for Self-affine Mapping System

  • Authors:

  • Haruki Kawanaka;Hirofumi Kato;Fuminori Matsubara;Yuji Iwahori;Robert J. Woodham

  • Affiliations:

  • Faculty of Information Science and Technology, Aichi Prefectural University, Nagakute-cho, Aichi-gun 480-1198, Japan;Faculty of Engineering, Chubu University, Matsumoto-cho 1200, Kasugai 487-8501, Japan;Faculty of Engineering, Chubu University, Matsumoto-cho 1200, Kasugai 487-8501, Japan;Faculty of Engineering, Chubu University, Matsumoto-cho 1200, Kasugai 487-8501, Japan;Department of Computer Science and Technology, University of British Columbia, Vancouver, B.C., Canada V6T 1Z4

  • Venue:
  • KES '07 Knowledge-Based Intelligent Information and Engineering Systems and the XVII Italian Workshop on Neural Networks on Proceedings of the 11th International Conference
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Self-affine mapping system is a technique that can extract the contour on the basis of rough form. A self-similarity at the block unit in square is utilized. The initial contour of this technique is given as a simple form by hand, the result of background subtraction or frame subtraction and the selection from candidates of the plural outline form with degree of separation. However, there are some problems in case that the cost of manual operation is large, or the self-similarity does not hold when the object has the similar brightness as the background. So, in this paper, we propose a new method to extract the contour with self-affine mapping system from the rough form of the object obtained by using edge background subtraction and interpolation.