Saliency Cuts: An automatic approach to object segmentation

Abstract

Interactive graph cuts are widely used in object segmentation but with some disadvantages: 1) Manual interactions may cause inaccurate or even incorrect segmentation results and involve more interactions especially for novices. 2) In some situations, the manual interactions are infeasible. To overcome these disadvantages, we propose a novel approach, namely Saliency Cuts, to segment object from background automatically. By exploring the effects of labels to graph cuts, the so called “Professional Labels” is introduced to evaluate labels. With the aid of saliency detection, a multiresolution framework is designed to provide “Professional Labels” automatically and implement object segmentation using graph cuts. The experiments demonstrate the promising performance of Saliency Cuts.

DOI: 10.1109/ICPR.2008.4761383

Extracted Key Phrases

3 Figures and Tables

01020200920102011201220132014201520162017
Citations per Year

71 Citations

Semantic Scholar estimates that this publication has 71 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Fu2008SaliencyCA, title={Saliency Cuts: An automatic approach to object segmentation}, author={Yu Fu and Jian Cheng and Zhenglong Li and Hanqing Lu}, booktitle={ICPR}, year={2008} }