Share Email Print

Proceedings Paper

Wavelet-based improved Chan-Vese model for image segmentation
Author(s): Xiaoli Zhao; Pucheng Zhou; Mogen Xue
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper, a kind of image segmentation approach which based on improved Chan-Vese (CV) model and wavelet transform was proposed. Firstly, one-level wavelet decomposition was adopted to get the low frequency approximation image. And then, the improved CV model, which contains the global term, local term and the regularization term, was utilized to segment the low frequency approximation image, so as to obtain the coarse image segmentation result. Finally, the coarse segmentation result was interpolated into the fine scale as an initial contour, and the improved CV model was utilized again to get the fine scale segmentation result. Experimental results show that our method can segment low contrast images and/or inhomogeneous intensity images more effectively than traditional level set methods.

Paper Details

Date Published: 25 October 2016
PDF: 7 pages
Proc. SPIE 10157, Infrared Technology and Applications, and Robot Sensing and Advanced Control, 101570O (25 October 2016); doi: 10.1117/12.2244592
Show Author Affiliations
Xiaoli Zhao, Army Official Academy (China)
Pucheng Zhou, Army Official Academy (China)
Mogen Xue, Army Official Academy (China)

Published in SPIE Proceedings Vol. 10157:
Infrared Technology and Applications, and Robot Sensing and Advanced Control

© SPIE. Terms of Use
Back to Top