Image segmentation is one of the fundamental problems in image processing and computer vision. Studies of high quality image segmentation methods have always gained a lot of attention in the field of image processing. However，so far the problem of image segmentation has not been well solved yet. Conventional methods cannot divide the images exactly because too much objectivity has been used. For complex objects, this paper proposed an efficient image segmentation algorithm based wavelet transform. This article presents the result of wavelet image segmentation and watershed algorithm image segmentation. The experimental result indicates that, the algorithm based on wavelet transform has fast convergence and good noise immunity.