Structure preserving semantic coherent object segmentation

Abstract

We improve prior efforts to extract coherent image contents (objects) from complex scenes by exploiting structural and semantic coherency. Generative models like latent Dirichlet allocation (LDA) and its variants are popular methods for unsupervised object segmentation, but they lack comprehensive consideration of structure correlations. Even small amounts of globally distributed noise in the image can negatively effect results. In this paper, we introduce a structure preserving semantic coherent model (SP-SC) to support more comprehensive object segmentation. Our approach combines Euclidean distance, graph distances and structural similarity of homogeneous patches in a unified framework. The method groups structural and semantic coherent patches together thereby overcoming false segmentation due to many kinds of noise and scene complexities. Comparative results in segmentation experiments using standard image data sets show the efficacy of proposed approach.