Adaptive saliency cuts

Yuantian Wang

doi:10.1007/s11042-018-5859-y

Adaptive saliency cuts

2018-03-24

3

PRE

AI

DOI：10.1007/s11042-018-5859-y

Original

Original request for help

Save

Abstract

En 中文

Saliency cuts aims to segment salient objects from a given saliency map. The existing saliency cuts methods are fixed to the input cues. It limits their performance when the input cues are changed. In this paper, we propose a novel saliency cuts method named adaptive saliency cuts, which takes advantage of all the input cues in a unified framework and adjusts its components adaptively. Given a saliency map, we first generate segmentation seeds with adaptive triple thresholding. Next, we extend GrabCut by combining different input cues, and use it to generate a rough-labeled map of salient objects. Finally, we refine the boundaries of the salient objects with adaptive initialized segmentation, and produce an accurate binary mask. To the best of our knowledge, this method is the first adaptive saliency cuts method for different input cues. We validated the proposed method on MSRA10K and NJU2000. The experimental results demonstrate that our method outperforms the state-of-the-art methods.

Keywords:

Saliency cuts

Segmentation seeds generation

Rough-labeled map generation

Object boundary refinement

Adaptive GrabCut

Adaptive saliency cuts

Abstract

AI Summary

Journal

Organization