Visual Saliency by Selective Contrast

Automatic detection of salient objects in visual media (e.g., videos and images) has been attracting much attention. The detected salient objects can be utilized for segmentation, recognition, retrieval, etc. However, the accuracy of saliency detection remains a challenge. The reason behind this challenge is mainly due to lack of well-defined model for interpreting saliency formulation. To tackle the problem, this paper proposes to detect salient objects based on selective contrast. Selective contrast intrinsically explores the most distinguishable component information in color, texture, and location. A large amount of experiments are thereafter carried out upon a benchmark dataset and the results are compared with those of 12 other popular algorithms as state-of-the-art. In addition, the advantage of the proposed algorithm is also demonstrated in a retargeting application.