%0 Journal Article
%T Medical Image Segmentation with Improved Gradient Vector Flow
%A Jinyong Cheng
%A Xiaoyun Sun
%J Research Journal of Applied Sciences, Engineering and Technology
%D 2012
%I Maxwell Science Publication
%X In this study, we discover some deficiencies of GVF and GGVF Snake such as it can not capture boundaries like ¡°U¡± and ¡°¦¸¡± completely because of the counteraction of some external forces and the influence of the local minimum external forces. Based on analyzing force distribution rules of gradient vector flow, a standard is introduced to distinguish every control point is true or false. An additional control force is added to GVF Snake model. The direction of control force is gained by tracking the force field and the motion of snake control points. Experimentation proves that the new GVF Snake model can solve the problem that GVF and GGVF Snake model can not detect the boundaries like ¡°U¡± and ¡°¦¸¡± and the new algorithm can improve GVF snake model¡¯s ability to capture thin boundary indentation like the boundary of brain image.
%K Active contour models
%K edge detection
%K gradient vector flow
%K medical image segmentation
%U http://maxwellsci.com/jp/abstract.php?jid=RJASET&no=224&abs=14