New geometric active contours for imaging segmentation

Fei Yao-ping · Journal of Computer Applications · 2007

It is known well enough that the traditional geometric active contours are susceptible to weak edges and noise in imaging processing. To solve these problems, the paper proposed a new geometric active contour model based on the region gradient flow forces. The region force comes from image region segmentation, which can give the model a global view of the boundary information and expand the curves' capture scope by introduce an equation of diffusion. Experiments prove the new model can help curve detect fuzzy boundaries and overcome noisy regions in imaging segmentation.

Read the paper · More papers on PaperTik