A Review on Co-Saliency Detection Methods for Complex Background Images

Abstract

Human eye is perceptually more sensitive to certain colors and intensities and objects with such features are considered more salient. Co-saliency detection aims at discovering the common salient objects existing in multiple images, which is a relatively under-explored area. A review of various techniques used in co-saliency detection like cluster based co-saliency detection, Hierarchical segmentation, Base reconstruction, Low rank matrix recovery etc. are done in this paper. Detection of Salient image regions is useful in applications such as co-segmentation, common pattern discovery, co recognition, Image retrieval etc. The survey is represented in a tabular form for quick reference and also describes the advantages and disadvantages of papers.