Figure-ground segmentation based on class-independent shape priors

Yang Li; Yang Liu; Guojun Liu; Maozu Guo

doi:10.1117/1.JEI.27.1.013018

14 February 2018 Figure-ground segmentation based on class-independent shape priors

Yang Li, Yang Liu, Guojun Liu, Maozu Guo

Author Affiliations +

Journal of Electronic Imaging, Vol. 27, Issue 1, 013018 (February 2018). https://doi.org/10.1117/1.JEI.27.1.013018

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.

Citation Download Citation

Yang Li, Yang Liu, Guojun Liu, and Maozu Guo "Figure-ground segmentation based on class-independent shape priors," Journal of Electronic Imaging 27(1), 013018 (14 February 2018). https://doi.org/10.1117/1.JEI.27.1.013018

Received: 12 October 2017; Accepted: 16 January 2018; Published: 14 February 2018

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available