Remote Sensing Image Segmentation Based on Modified Information Cut in Wavelet Domain

To solve the mis-clusters caused by the traditional information cut (IC) algorithm when it is applied to segment images with gray changes, a modified information cut in wavelet domain (W-MIC) algorithm is proposed. First, it modifies IC using a new Parzen windowing which combines the gray relevance and space relevance between image pixels in order to reduce the effect of gray changes to image segmentation. Further, considering the difficulties of selecting the optimal parameter in the above modified information cut (MIC), MIC is introduced to wavelet domain to reduce the complexity of parameter selection via the smoothing role of wavelet. Remote sensing image segmentation results demonstrate that it effectively decreases the influence of parameters selection, and it can not only avoid the mis\|clusters caused by gray changes, but also keep image edges.