Superpixel-Based Foreground Extraction With Fast Adaptive Trimaps
Lists
Only you see this
Abstract
Extracting the foreground from a given complex image is an important and challenging problem. Although there have been many methods to perform foreground extraction, most of them are time-consuming, and the trimaps used in the matting step are labeled manually. In this paper, we propose a fast interactive foreground extraction method based on the superpixel GrabCut and image matting. Specifically, we first extract superpixels from a given image and apply GrabCut on them to obtain a raw mask. Due to that the resulting mask border is hard and toothing, we further propose fast and adaptive trimaps (FATs), and construct an FATs-based shared matting for computing a refined mask. Finally, by interactive processing, we can obtain the final foreground. Experimental results on the BSDS500 and alphamatting datasets demonstrate that our proposed method is faster than five representative methods, and performs better than the interactive representative methods in terms of the three evaluation criteria: 1) mean square error; 2) sum of absolute difference; and 3) execution time.
BibTeX
@article{li2018superpixel,
author = {Xuelong Li and Kang Liu and Yongsheng Dong},
title = {{Superpixel-Based Foreground Extraction With Fast Adaptive Trimaps}},
journal = {IEEE Trans. Cybernetics},
year = {2018},
url = {https://openreview.net/forum?id=O4g10pE1Gd},
}Loading related content...