Publication

Contour detection using multi-scale active shape models (1997)

Author(s): S. Mahmoodi;B.S. Sharif;E.G. Chester

  • : Contour detection using multi-scale active shape models

Abstract: A robust contour detection algorithm is presented for noisy images characterized by close objects. The proposed approach uses an adaptive multi-scale edge tracking scheme based on Active Shape Models and the wavelet transform. This adaptive method effectively adjusts the appropriate Gaussian function bandwidth according to the noise level so that close object edges can be detected before they are merged by excessive smoothing. This gives improved performance over a single scale approach, where an incorrect Gaussian function bandwidth can lead to erroneous edge detection. The results obtained show an adaptive multi-scale scheme is robust regardless of the image signal to noise ratio.

Notes: TY - CONF U1 - 97123946648 Compilation and indexing terms, Copyright 2004 Elsevier Engineering Information, Inc. U2 - Active shape models Gaussian function

  • Short Title: Contour detection using multi-scale active shape models
  • Conference Name: Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3), Oct 26-29 1997
  • Volume: 2
  • Pages: 708-711
  • Publisher: IEEE Comp Soc, Los Alamitos, CA, USA
  • Publication type: Conference Proceedings (inc. abstract)
  • Bibliographic status: Published

Keywords: Algorithms Spurious signal noise Signal to noise ratio Wavelet transforms Mathematical models Bandwidth Edge detection

Staff

Dr Graeme Chester
Senior Lecturer

Professor Bayan Sharif
Senior Research Investigator