.png){kind=icon}
返回
Probabilistic Diffusion for Interactive Image Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2018.2867941.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper presents an interactive image segmentation approach in which we formulate segmentation as a probabilistic estimation problem based on the prior user intention. Instead of directly measuring the relationship between pixels and labels, we first estimate the distances between pixel pairs and label pairs using a probabilistic framework. Then, binary probabilities with label pairs are naturally converted to unary probabilities with labels. The higher order relationship helps improve the robustness to user inputs. To improve segmentation accuracy, a likelihood learning framework is proposed to fuse the region and the boundary information of the image by imposing a smoothing constraint on the unary potentials. Furthermore, we establish an equivalence relationship between likelihood learning and likelihood diffusion and propose an iterative diffusionbased optimization strategy to maintain computational efficiency. Experiments on the Berkeley segmentation data set andMicrosoft GrabCut database demonstrate that the proposed method can obtain better performance than the state-of-the-art methods.
Keyword:
Interactive image segmentation
paired distance measurement
likelihood learning
probabilistic estimation
unary potentials
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
暂无机构信息
引用论文
.png){kind=icon}
分享收藏分享收藏
Image Segmentation Based on GrabCut Framework Integrating Multiscale Nonlinear Structure Tensor
PREAI
分享收藏
查看更多内容