Multi-Phase Image Segmentation Based on Low-Rank Prior Decomposition

Abstract

Natural images usually contain structure component and texture component. The existing image segmentation models based on piecewise smooth cannot handle such natural images containing texture well. For this reason, in this paper, a multi-region image segmentation model based on low-rank prior decomposition is proposed. We use the low-rank prior to characterize the texture component, and the total variational norm to characterize the piecewise smooth structure component so that the proposed method can perform image decomposition and image segmentation tasks simultaneously. Then, the decomposed structure image can be used for image segmentation, and thus we can improve the accuracy of segmentation. To solve the new model, the alternating direction multiplier method is designed. The experimental results show that compared with the related classical models, the new model can significantly improve the subjective visual effect of image segmentation and the mean values of the precision rate, F1-measure, and Jaccard similarity coefficient for the new model on the test images are at least 3.29%, 1.74%, and 3.13% higher, respectively.