Double Feature Combination: Region Contrast for Visual Salient Object Detection
Zhi Hai Sun, Teng Song, Wenhui Zhou, Zhang Hua · Applied Mechanics and Materials · 2012
Visual saliency detection has become an important step between computer vision and digital image processing. Recent methods almost form a computational model based on color, which are difficult to overcome the shortcoming with cluttered and textured background. This paper proposes a novel salient object detection algorithm integrating with region color contrast and histograms of oriented gradients (HoG). Extensively experiments show that our algorithm outperforms other state-of-art saliency methods, yielding higher precision and better recall rate, even lower mean absolution error.