SALIENT OBJECT DETECTION BASED ON GLOBAL CONTRAST ON TEXTURE AND COLOR

Computationally detecting salient image object based on human attention is of great significance for image understanding. In this paper, we introduce a method for saliency map generation with a novel way of extracting texture feature and a strategy for feature fusion. Our method combines texture and color region contrasts to make the salient object stand out from images. We compare our algorithm to five salient region detection methods with ground truth and salient object segmentation. Our method outperforms the five algorithms on both the ground-truth evaluation and salient object segmentation.