Image Saliency Detection with Sparse Representation of Learnt Texture Atoms

Abstract

This paper proposes a saliency detection method using a novel feature on sparse representation of learnt texture atoms (SR-LTA), which are encoded in salient and non-salient dictionaries. For salient dictionary, a novel formulation is proposed to learn salient texture atoms from image patches attracting extensive attention. Then, online salient dictionary learning (OSDL) algorithm is provided to solve the proposed formulation. Similarly, the non-salient dictionary can be learnt from image patches without any attention. A new pixel-wise feature, namely SR-LTA, is yielded based on the difference of sparse representation errors regarding the learnt salient and non-salient dictionaries. Finally, image saliency can be predicted via linear combination of the proposed SR-LTA feature and conventional features, i.e., luminance and contrast. For the linear combination, the weights corresponding to different feature channels are determined by least square estimation on the training data. The experimental results show that our method outperforms several state-of-the-art saliency detection methods.