A Genetic Programming Approach for Constructing Foreground and Background Saliency Features for Salient Object Detection

Abstract

Salient Object Detection (SOD) methods have been widely investigated in order to mimic human visual system in selecting regions of interest from complex scenes. The majority of existing SOD methods have focused on designing and combining handcrafted features. This process relies on domain knowledge and expertise and becomes increasingly difficult as the complexity of candidate models increases. In this paper, we develop an automatic feature combination method for saliency features to relieve human intervention and domain knowledge. The proposed method contains three phases, two Genetic Programming (GP) phases to construct foreground and background features and a spatial blending phase to combine those features. The foreground and background features are constructed to complement each other, therefore one can improve other’s shortcomings. This method is compared with the state-of-the-art methods on four different benchmark datasets. The results indicate the new automatic method is comparable with the state-of-the-art methods and even improves SOD performance on some datasets.