Improved similarity measure-based graph embedding for face recognition

Yongxin Ge; Dan Yang; Xiaohong Zhang; Jiwen Lu

doi:10.1117/1.JEI.21.1.013002

22 February 2012 Improved similarity measure-based graph embedding for face recognition

Yongxin Ge, Dan Yang, Xiaohong Zhang, Jiwen Lu

Author Affiliations +

Journal of Electronic Imaging, Vol. 21, Issue 1, 013002 (February 2012). https://doi.org/10.1117/1.JEI.21.1.013002

Abstract

We propose an improved similarity measure (ISM) and apply it to the existing graph embedding (GE) framework to derive a new improved similarity measure-based graph embedding (ISM-GE) method for face recognition. Our work is motivated by the fact that both the Euclidean metric and the correlation metric are useful and effective for characterizing the similarity of face samples, and we combine these two metrics to form a new ISM to measure the similarity of face samples. We further utilize the proposed ISM in the existing GE framework and develop a new ISM-GE method for face feature extraction and recognition. Experimental results on two widely used face databases demonstrate the efficacy of the proposed method.

Citation Download Citation

Yongxin Ge, Dan Yang, Xiaohong Zhang, and Jiwen Lu "Improved similarity measure-based graph embedding for face recognition," Journal of Electronic Imaging 21(1), 013002 (22 February 2012). https://doi.org/10.1117/1.JEI.21.1.013002

Published: 22 February 2012

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