关键词: 边缘检测, 双阈值, 数学形态学, 图像融合

Abstract: The key to image edge detection is to suppress noises more effectively while detecting as much as possible the edges of image. For this purpose, this paper proposes a fusion dual-threshold and mathematical morphology edge detection method. First of all, the source image is decomposed by wavelet decomposition, it uses dual-threshold method for high frequency components of treatment, and uses multi-structure element algorithm for multi-scale mathematical morphology frequency components for low frequency component. And then the level of sub-subtraction method is used for image fusion edge. The experimental results show that the algorithm is superior to wavelet modulus maxima algorithm or mathematical morphological method and can more effectively suppress noise. The edges are consecutive and clear.

Key words: edge detection, double threshold, mathematical morphology, image fusion