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

作者：

Highlights：

• We develop the OSDL algorithm for learning the salient and non-salient dictionaries.

• We propose the SR-LTA feature for bottom-up saliency detection, in light of the learnt salient and non-salient dictionaries.

• We validate that the proposed SR-LTA feature can advance state-of-the-art saliency detection on natural images.

摘要

Highlights•We develop the OSDL algorithm for learning the salient and non-salient dictionaries.•We propose the SR-LTA feature for bottom-up saliency detection, in light of the learnt salient and non-salient dictionaries.•We validate that the proposed SR-LTA feature can advance state-of-the-art saliency detection on natural images.

论文关键词：Visual attention,Saliency detection,Sparse representation,Dictionary learning

论文评审过程：Received 21 January 2016, Revised 11 April 2016, Accepted 14 May 2016, Available online 21 May 2016, Version of Record 13 June 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.05.023