Fast and Robust Segmentation of Low Contrast Biomedical Images

J. Hubený and P. Matula (Czech Republic)


medical imaging, fast Chan–Vese active contour segmenta tion


This paper presents fast and robust algorithm for min imization of Chan–Vese energy functional. Proposed tech nique is based on recently published k-Means level set [1] and threshold dynamics [2] approximations of Chan– Vese functional. The approximation algorithms are com bined in order to preserve their individual advantages and avoid their limitations. Hence, the proposed hybrid algo rithm is robust and converges reasonably fast to steady state and is suitable for two-phase segmentation of low contrast biomedical data. A simple numerical scheme for threshold dynamics method is derived in the paper. Results of the hy brid algorithm that are better than results of both k-Means level set and threshold dynamics methods employed indi vidually are presented.

Important Links:

Go Back