Reversion Correction and Regularized Random Walk Ranking for Saliency Detection

In recent saliency detection research, many graphbased algorithms have applied boundary priors as background queries, which may generate completely reversed saliency maps if the salient objects are on the image boundaries. Moreover, these algorithms usually depend heavily on pre-processed superpixel segmentation, which may lead to notable degradation in image detail features. In this paper, a novel saliency detection method is proposed to overcome the above issues. First, we propose a saliency reversion correction process, which locates and removes the boundary-adjacent foreground superpixels, and thereby increases the accuracy and robustness of the boundary priorbased saliency estimations. Second, we propose a regularized random walk ranking model, which introduces prior saliency estimation to every pixel in the image by taking both region and pixel image features into account, thus leading to pixeldetailed and superpixel-independent saliency maps. Experiments are conducted on four well-recognized data sets; the results indicate the superiority of our proposed method against 14 state-of-the-art methods, and demonstrate its general extensibility as a saliency optimization algorithm. We further evaluate our method on a new data set comprised of images that we define as boundary adjacent object saliency, on which our method performs better than the comparison methods.