Detecting multiple salient objects in complex scenes is a challenging task. In this paper, we present a novel method to\ndetect salient objects in images. The proposed method is based on the general ââ?¬Ë?center-surroundââ?¬â?¢ visual attention\nmechanism and the spatial frequency response of the human visual system (HVS). The saliency computation is\nperformed in a statistical way. This method is modeled following three biologically inspired principles and compute\nsaliency by two ââ?¬Ë?scatter matricesââ?¬â?¢ which are used to measure the variability within and between two classes, i.e., the\ncenter and surrounding regions, respectively. In order to detect multiple salient objects of different sizes in a scene,\nthe saliency of a pixel is estimated via its saliency support region which is defined as the most salient region centered\nat the pixel. Compliance with human perceptual characteristics enables the proposed method to detect salient\nobjects in complex scenes and predict human fixations. Experimental results on three eye tracking datasets verify the\neffectiveness of the method and show that the proposed method outperforms the state-of-the-art methods on the\nvisual saliency detection task
Loading....