Object-aware saliency detection for consumer images
Hao Tang · 2012
Many image analysis, computer vision and multimedia applications involving consumer images rely on or benefit from saliency maps which represent where important areas of images are located. To date, virtually all image saliency detection techniques tend to produce highly blurry saliency maps. However, there are situations where the awareness of objects and their boundaries in images can greatly facilitate solutions to the problems. In this paper, we propose a novel, effective and efficient image saliency detection algorithm. Notably, our algorithm is capable of detecting salient regions of an image with clear boundaries, corresponding to objects in the scene. Yet, the algorithm is robust to background clutter commonly found in typical consumer images. A comparison of our algorithm with several state-of-the-art image saliency detection algorithms reveals the favorable performance of our algorithm in terms of the quality of saliency maps and the computational time.