Ensemble dictionary learning for saliency detection

作者：

Highlights：

• We propose an ensemble dictionary learning (EDL) framework for saliency detection.

• The saliency detection within this framework is treated as a novelty detection problem.

• A novel dictionary atom reduction is proposed for boosting the distinctness of salient region.

• A good probabilistic interpretation is with the proposed EDL model.

摘要

•We propose an ensemble dictionary learning (EDL) framework for saliency detection.•The saliency detection within this framework is treated as a novelty detection problem.•A novel dictionary atom reduction is proposed for boosting the distinctness of salient region.•A good probabilistic interpretation is with the proposed EDL model.

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

论文评审过程：Received 19 April 2013, Revised 22 October 2013, Accepted 30 December 2013, Available online 16 January 2014.

论文官网地址：https://doi.org/10.1016/j.imavis.2013.12.015