Multi-scale Edge Detection of Wood Defect Images Based on the Dyadic Wavelet Transform

摘要

Multi-scale feature of wavelet and the theory of wavelet transform modulus maxima were researched. A method about multi-scale edge detection based on dyadic wavelet transform was proposed in order to solve the contradiction between noise suppression and edge continuity when wood defect image detected edge. A fast multi-scale edge detection algorithm was constructed when the image and filter do convolution and applied to the wood defect image edge detection. The method was verified by computer simulation. The experimental results show that the method can detect image edge continuously and clearly and can suppress noise effectively. The method is better than the traditional edge detection algorithms and is suitable for wood defect image edge extraction.