Probabilistic Diffusion for Interactive Image Segmentation

doi:10.1109/TIP.2018.2867941

Return

Probabilistic Diffusion for Interactive Image Segmentation

2019-01-01

PRE

王

王涛 (Tao Wang)

Jian Yang (Jian Yang)

DOI：10.1109/TIP.2018.2867941

Original

Original request for help

Save

Abstract

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.

Keywords:

Interactive image segmentation

paired distance measurement

likelihood learning

probabilistic estimation

unary potentials

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.