Segmentation using Wavelet and GVF Snake

F.D. Way, M. Rajeswari, and D. Ramachandram (Malaysia)

Keywords

Gradient vector flow, wavelet, multi scale edge, andsegmentation

Abstract

The Gradient Vector Flow (GVF) snake is a popular technique to segment object in image processing. Its advantages are insensitivity to contour initialization and its ability to deform into highly concave part of the object compared to other deformable contour models. However, the performance of a GVF snake to model any arbitrary shape is heavily dependent upon objects with the highest intensity changes in the edge map and does not take into consideration objects with secondary gradient magnitude. To alleviate this problem, we propose a multi-scale method to obtain a suitable edge map to aid the GVF determination problem. The GVF are thus calculated from the enhanced edge map which focuses on the secondary structures of interest. This paper presents the approach and preliminary results which are encouraging.

Important Links:



Go Back