Image Edge Detection Based on Lifting Wavelet

The current widely used edge detection algorithm have Sobel, Roberts, Laplacian etc. The core idea of these algorithms is that the edge points correspond to the local maximal points of original image´s gray-level gradient. However, when there are noises in images, these algorithms are very sensitive to noises, and may detect noise points as marginal points, and the real edge may not be detected because of the noises´ interference. Designing image edge detection systems with good nature is a goal which all researchers pursue. Method of lifting can best deal with based on MRA multi-resolution analysis method which is time and memory consuming which impedes its real-time application. The process of lifting method was introduced. Method of image edge detection based on lifting wavelet was introduced. The algorithm, traditional wavelet image edge detection algorithms and Canny operator are compared. Result of the experiment indicate, the quality of image have been improved. It is better than traditional wavelet and Canny operator image edge detection algorithms.