Information Divergence Based Saliency Detection with a Global Center-Surround Mechanism

In this paper a novel technique for saliency detection called Global Information Divergence is proposed. The technique is based on the diversity in information between two regions. Initially patches are extracted at multi-scales from the input images. This is followed by reducing the dimensionality of the extracted patches using Principal Component Analysis. After that the information divergence is evaluated between the reduced dimensionality patches, and calculated between a center and a surround region. Our technique uses a global method for defining the center patch and the surround patches collectively. The technique is tested on four competitive and complex datasets both for saliency detection and segmentation. The results obtained show a good performance in terms of quality of the saliency maps and speed compared with 16 state-of-the-art techniques.