Bottom-up saliency detection with sparse representation of learnt texture atoms

This paper proposes a saliency detection method by exploring a novel low level feature on sparse representation of learnt texture atoms (SR-LTA). The learnt texture atoms are encoded in salient and non-salient dictionaries. For salient dictionary, a formulation is proposed to learn salient texture atoms from image patches attracting extensive attention. Then, the online salient dictionary learning (OSDL) algorithm is presented to solve the proposed formulation. Similarly, the non-salient dictionary is learnt from image patches without any attention. Then, the pixel-wise SR-LTA feature is yielded based on the difference of sparse representation errors, regarding the learnt salient and non-salient dictionaries. Finally, image saliency can be predicted by linearly combining the proposed SR-LTA feature and conventional features, luminance and contrast. For the linear combination, the weights of different feature channels are determined by least square estimation on the training data. The experimental results show that our method outperforms 9 state-of-the-art methods for bottom-up saliency detection.