Normalized Gradient Vector Diffusion and Image Segmentation

Abstract. In this paper, we present an approach for image segmentation, based on the existing Active Snake Model and Watershed-based Region Merging. Our algorithm includes initial segmentation using Normalized Gradient Vector Diffusion (NGVD) and region merging based on Region Adjacency Graph (RAG). We use a set of heat diffusion equations to generate a vector field over the image domain, which provides us with a natural way to define seeds as well as an external force to attract the active snakes. Then an initial segmentation of the original image can be obtained by a similar idea as seen in active snake model. Finally an RAG-based region merging technique is used to find the true segmentation as desired. The experimental results show that our NGVD-based region merging algorithm overcomes some problems as seen in classic active snake model. We will also see that our NGVD has several advantages over the traditional gradient vector diffusion. Keywords. Image segmentation, Gradient vecto...

• Type: Conference
• Year: 2002
• Where: ECCV
• Authors: Zeyun Yu, Chandrajit L. Bajaj
• Keywords: Active Snake Model, Computer Vision, ECCV 2002, Gradient Vector Diffusion, Normalized Gradient Vector, Region Merging Algorithm, Region Merging Technique