Interactive Image Segmentation via Pairwise Likelihood Learning
Abstract
This paper presents an interactive image segmentation approach where the segmentation problem is formulated as a probabilistic estimation manner. Instead of measuring the distances between unseeded pixels and seeded pixels, we measure the similarities between pixel pairs and seed pairs to improve the robustness to the seeds. The unary prior probability of each pixel belonging to the foreground F and background B can be effectively estimated based on the similarities with label pairs (F, F),(F, B),(B, F) and (B, B). Then a likelihood learning framework is proposed to fuse the region and boundary information of the image by imposing the smoothing constraint on the unary potentials. Experiments on challenging data sets demonstrate that the proposed method can obtain better performance than state-of-the-art methods.
Cite
Text
Wang et al. "Interactive Image Segmentation via Pairwise Likelihood Learning." International Joint Conference on Artificial Intelligence, 2017. doi:10.24963/IJCAI.2017/412Markdown
[Wang et al. "Interactive Image Segmentation via Pairwise Likelihood Learning." International Joint Conference on Artificial Intelligence, 2017.](https://mlanthology.org/ijcai/2017/wang2017ijcai-interactive-a/) doi:10.24963/IJCAI.2017/412BibTeX
@inproceedings{wang2017ijcai-interactive-a,
title = {{Interactive Image Segmentation via Pairwise Likelihood Learning}},
author = {Wang, Tao and Sun, Quan-Sen and Ge, Qi and Ji, Zexuan and Chen, Qiang and Xia, Guiyu},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2017},
pages = {2957-2963},
doi = {10.24963/IJCAI.2017/412},
url = {https://mlanthology.org/ijcai/2017/wang2017ijcai-interactive-a/}
}