Research Of Edge Detection Based On GVF Snake Model

Snakes are curves defined within an image domain that can move under the influence of internal forces coming from within the curve itself and external forces computed from the image data. The internal and external forces are defined so that the snake will conform to an object boundary or other desired features within an image. There are two key difficulties with Snakes. First, the initial contour must, in general, be close to the true boundary or else it will likely converge to the wrong result. The second problem is that active contours have difficulties progressing into boundary concavities. GVF Snake is one of several methods have been proposed to address this problems. it is specified directly from a force balance condition. Gradient vector flow (GVF) are a new class of external forces for active contour models, are dense vector fields derived from images by minimizing certain energy functional in a variational framework. The GVF snake has a large capture range.This paper proposes a method of edge detection based on GVF Snake and Contourlet transform. Contourlet transform is a kind of image representations. The first stage of the transform is Laplcian pyramid provides multiresolution decomposition to receive singular points. The second stage is a directional filter bank which produces angular decomposition at the same directions. Using the characteristics of Contourlet transform finds the object contour, as the initial contour on edge detection through iterative calculation. Experimental results show that the method of the contour setting is effective and reasonable, improves the effect and precision of edge detection.This paper combines the background subtraction method with symmetric differential method to segment the motion human image, and then extracts the contour of motion human with modified GVF Snake model. GVF Snake can evidently increase the detection effect of boundary concavities. However, due to the process of isotropic diffusion easily lead to the effect is not fairly good. The method can stop the spread of GVF on the boundary although the anisotropic characteristics, and enforce the spread on the non-boundary to improve the competency of detection into slender area. Experimental demonstrate the effective and correct of the anisotropic GVF Snake method for gait recognition on edge detection.