Superpixel based color contrast and color distribution driven salient object detection

作者：

Highlights：

• A comprehensive saliency detection system is proposed, which combines the color contrast and color distribution in a unified manner.

• Additional stages such as global saliency smoothing and meanshift segmentation refinement are introduced, which improve the performance.

• Our method outperforms the state-of-the-art on both qualitative and quantitative evaluation.

• The results on other applications like content-aware image resizing also show the superiority of our method.

摘要

Highlights•A comprehensive saliency detection system is proposed, which combines the color contrast and color distribution in a unified manner.•Additional stages such as global saliency smoothing and meanshift segmentation refinement are introduced, which improve the performance.•Our method outperforms the state-of-the-art on both qualitative and quantitative evaluation.•The results on other applications like content-aware image resizing also show the superiority of our method.

论文关键词：Salient object detection,Saliency maps,Color contrast,Color distribution,Superpixels

论文评审过程：Received 7 March 2013, Revised 17 July 2013, Accepted 18 July 2013, Available online 26 July 2013.

论文官网地址：https://doi.org/10.1016/j.image.2013.07.005