Image Edge Detection Using Nonsubsampled Contourlet Transform

An algorithm for image edge detection based on nonsubsampled contourlet transform (NSCT) is proposed. NSCT is multiresolutional, localized, multidirectional and anisotropic, so it can more effectively capture high dimensional singularity. Firstly, the coefficients at different scales and in different directions are obtained by image decomposition using the NSCT, then with these coefficients thresholds are adaptively set and the generalized nonlinear gain function is used to enhance the edge features with low contrast while protecting the strong contrast features from over enhancing in the NSCT domain. The experiment results show that the algorithm achieve a good effect than other algorithms.