Probabilistic Diffusion for Interactive Image Segmentation

Authors:

Abstract
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 diffusion-based optimization strategy to maintain computational efficiency. Experiments on the Berkeley segmentation data set and Microsoft GrabCut database demonstrate that the proposed method can obtain better performance than the state-of-the-art methods.
Funding Information
  • Natural Science Foundation of Jiangsu Province (BK20180458)
  • National Natural Science Foundation of China (61802188)
  • China Postdoctoral Science Foundation (BX201700121)
  • China Postdoctoral Science Foundation (2017M621750)
  • National Natural Science Foundation of China (61673220, U1713208, 61472187)
  • 973 Program (2014CB349303)
  • Program for Changjiang Scholars

This publication has 23 references indexed in Scilit: