Image segmentation plays a basic and important role in image processing, and its results are directly related to the ones of image analysis and understanding. Aiming at solving the problem of choosing the optimal threshold-weighted threshold of commonly used thread segmentation methods, this paper proposed the method of integrating genetic algorithm with OTSU method for image segmentation, and adopted watershed method to close and enhance the segmented image edges. The experimental results show that the image segmentation method proposed is not only more accurate than traditional methods in visual comparison and digital performance indices, but also is robust against noises and geometric attacks.