Saliency detection based on global color and space contrast

Abstract

Abstract. Saliency detection acts as an important role in many computer vision tasks. We propose a novel bottom-up, object-level saliency detection method based on global color and space contrast. The proposed method not only considers the global color contrast of the image but also takes the space information into account, leading to an advanced multi-feature combined saliency detection model. Through qualitative and quantitative evaluation, our method consistently outperformed 4 global color (or intensity)-based saliency detection methods, resulting in higher precision.