An Edge Detection Method Based on Lifting Wavelet and Mathematical Morphology

Abstract

An edge detection method based on lifting wavelet and mathematical morphology is proposed in this paper. Firstly, the original image is decomposed by lifting wavelet transformation; secondly, the edge pixels in low-frequency sub-image are detected by morphological gradient and edge pixels in high-frequency sub-images are detected by the largest value of the module of wavelet coefficients; the two edge images obtained respectively by the morphology and wavelet are fused according to some rules at last. The experimental results show that the performance obtained by the method proposed in this paper is better than the one obtained by either of morphology method and wavelet method.