Object segmentation framework based on dictionary‐group and sparse shape representation

Abstract

Given an input object whose shape is partly similar to some of the samples in the training set, a dictionary-group-based sparse model is introduced that can use the local information of those less similar shape neighbours to represent the object and guide the segmentation. The model follows from a new sparse energy function that combines a series of sparse local constraints with the fuzzy log-polar decomposition-based shape elements. Finally, a unified framework is built to connect the high-level shape representation with the low-level image segmentation. The model on the public datasets is tested, and the experimental results show the superior shape segmentation capabilities of the proposed model.