Salient object detection using feature clustering and compactness prior

Yanbang Zhang, Fen Zhang, Lei Guo, Henry Han

Abstract: Salient object detection has been challenging computer vision though some advances have been made recently. In this study, we propose a novel salient object detection method by using feature clustering and compactness prior, in the situation of the absence of any prior information. The proposed method consists of four rigorous steps. Superpixel preprocessing is first employed to segment image into superpixels for suppressing noise and reducing computational complexity. Then, clustering algorithm is applied to get the classification of color features. Furthermore, two-dimensional entropy is used to measure the compactness of each cluster and build the background model. Finally, the salient feature is defined as the contrast between background region and other regions, and enhanced by designing a Gauss filter. To better evaluate the salient object detection accuracy, detailed experimental analysis is carried out by using 7 evaluation indexes. Our proposed method outperforms some peers in extensive experiments. It will inspire more similar techniques to be developed in this research topic.