Evaluation framework of superpixel methods with a global regularity measure

Rémi Giraud; Vinh-Thong Ta; Nicolas Papadakis

doi:10.1117/1.JEI.26.6.061603

6 July 2017 Evaluation framework of superpixel methods with a global regularity measure

Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis

Author Affiliations +

Journal of Electronic Imaging, Vol. 26, Issue 6, 061603 (July 2017). https://doi.org/10.1117/1.JEI.26.6.061603

Abstract

In the superpixel literature, the comparison of state-of-the-art methods can be biased by the nonrobustness of some metrics to decomposition aspects, such as the superpixel scale. Moreover, most recent decomposition methods allow setting a shape regularity parameter, which can have a substantial impact on the measured performances. We introduce an evaluation framework that aims to unify the comparison process of superpixel methods. We investigate the limitations of existing metrics and propose to evaluate each of the three core decomposition aspects: color homogeneity, respect of image objects, and shape regularity. To measure the regularity aspect, we propose a global regularity (GR) measure, which addresses the nonrobustness of state-of-the-art metrics. We evaluate recent superpixel methods with these criteria, at several superpixel scales and regularity levels. The proposed framework reduces the bias in the comparison process of state-of-the-art superpixel methods. Finally, we demonstrate that the proposed GR measure is correlated with the performances of various applications.

Citation Download Citation

Rémi Giraud, Vinh-Thong Ta, and Nicolas Papadakis "Evaluation framework of superpixel methods with a global regularity measure," Journal of Electronic Imaging 26(6), 061603 (6 July 2017). https://doi.org/10.1117/1.JEI.26.6.061603

Received: 22 April 2017; Accepted: 7 June 2017; Published: 6 July 2017

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