Anisotropic Diffusion for Preservation of Line-edges

Abstract

In existing approaches, diffusion is diffusion is processed based on directions of line-edge. performed in four directions (North, South, East, West) We first analyzed the anisotropic diffusion of Perona without specific conditions. Therefore, these methods have and Malik [2] and GHAD(Gradient Histogram-Based shortcomings of distorted with the existence of impulse Anisotropic Diffusion)[8] in Section 2. Section 3 noises. presents the proposed anisotropic diffusion method In this paper, a new anisotropic diffusion based on prsents th opos anisotropicdion metho directions ofline-edges is proposed to enhance preservation based on directions of line-edge. Section 4 shows the of line-edges together with removal of noises. In the experimental results and conclusions are given in proposed method, an edge detection mask is used tofind the Section 5. direction of a line-edge. As a result, when the magnitude of edge detection is large enough, there exists a line-edge. In the case of a line-edge, the weight of diffusion is selected II. ANISOTROPIC DIFFUSION adaptively according to the direction of the line-edge. The Anisotropic diffusion algorithms remove noise from diffusion is based on 8-directions diffusion with emphasis an image by modifying the image via a partial on the line-edge direction. Experimental results show that the proposed method differential equation. Perona and Malik [2] replaced can eliminate noise while preserving contour ofline-edges. the classical isotropic diffusion equation with