This paper presents a new thresholding method based on isoperimetric theory for image segmentation. The proposed method uses isoperimetric ratio as a criterion in selecting optimal segmenting threshold, that is, segmenting image with the gray value of minimal isoperimetric ratio as optimal threshold. Experiments show that this method outperforms normalized cut thresholding method in terms of segmentation quality, speed and noise immunity.
Published in:
Cybernetics and Intelligent Systems, 2008 IEEE Conference on
Date of Conference: 21-24 Sept. 2008