Journal of University of Science and Technology of China ›› 2012, Vol. 42 ›› Issue (1): 52-59.DOI: 10.3969/j.issn.0253-2778.2012.01.009

Previous Articles     Next Articles

A SAR image segmentation algorithm based on local median fitting C-V model

ZHANG Qian   

  1. Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230027, China
  • Received:2011-05-25 Revised:2011-07-06 Online:2012-01-31 Published:2012-01-31

Abstract: A novel SAR image segmentation algorithm LMFCV-SIS based on local median fitting (LMF) C-V model was proposed according to the characteristics of SAR images. The main idea of the algorithm is to use the LMF of the pixel and its neighbors to form an energy and the final evolution of the curve was given by the minimization of the energy. The performance of the approach was verified by plenty of real airborne SAR images and the experimental results from the real data show its efficiency and accuracy.

Key words: SAR images, image segmentation, active contour model, level set method, local median fitting (LMF)