Share Email Print

Journal of Electronic Imaging

Figure-ground segmentation based on class-independent shape priors
Author(s): Yang Li; Yang Liu; Guojun Liu; Maozu Guo
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

We propose a method to generate figure-ground segmentation by incorporating shape priors into the graph-cuts algorithm. Given an image, we first obtain a linear representation of an image and then apply directional chamfer matching to generate class-independent, nonparametric shape priors, which provide shape clues for the graph-cuts algorithm. We then enforce shape priors in a graph-cuts energy function to produce object segmentation. In contrast to previous segmentation methods, the proposed method shares shape knowledge for different semantic classes and does not require class-specific model training. Therefore, the approach obtains high-quality segmentation for objects. We experimentally validate that the proposed method outperforms previous approaches using the challenging PASCAL VOC 2010/2012 and Berkeley (BSD300) segmentation datasets.

Paper Details

Date Published: 14 February 2018
PDF: 13 pages
J. Electron. Imag. 27(1) 013018 doi: 10.1117/1.JEI.27.1.013018
Published in: Journal of Electronic Imaging Volume 27, Issue 1
Show Author Affiliations
Yang Li, Harbin Institute of Technology (China)
Yang Liu, Harbin Institute of Technology (China)
Guojun Liu, Harbin Institute of Technology (China)
Maozu Guo, Harbin Institute of Technology (China)
Beijing Univ. of Civil Engineering and Architecture (China)

© SPIE. Terms of Use
Back to Top