Abstract:
A fuzzy multiscale edge detection algorithm of image based on wavelet multiresolution analysis is presented in this paper. The dyadic wavelet transform is employed to produce the multiscale representation of image, and fuzzy decision method is applied in wavelet domain of different scales. The information of images with different scales can be synthesized effectively, and an optimal result of edge detection can be acquired. The paper compares the performances of the new algorithm with the Canny algorithm and Mallat's algori thm according to the concrete image signals. The results prove the feasibility and effectiveness of our algorithm over these other methods.