Image Topic Discovery with Saliency Detection

This work proposes a biologically inspired approach to integrate latent topic model with saliency detection. Firstly, a saliency detection algorithm is presented to discriminate salient objects from background parts in the image. A hierarchical latent topic model is proposed to discover image topics by combining subtopics of both salient objects and background parts. We test the algorithm on public image datasets for saliency detection and image categorization. The experimental results show that the proposed approach robustly detects salient objects and categorizes image data, and it outperforms state-of-the-art methods for both saliency detection and unsupervised topic modelling.