Ambient temperature normalization for infrared face recognition based on the second-order polynomial model

Zhengzi Wang

doi:10.1117/12.2197248

22 August 2015 Ambient temperature normalization for infrared face recognition based on the second-order polynomial model

Zhengzi Wang

Author Affiliations +

Proceedings Volume 9656, International Symposium on Photonics and Optoelectronics 2015; 96560O (2015) https://doi.org/10.1117/12.2197248
Event: International Symposium on Photonics and Optics, 2015, Shanghai, China

Abstract

The influence of ambient temperature is a big challenge to robust infrared face recognition. This paper proposes a new ambient temperature normalization algorithm to improve the performance of infrared face recognition under variable ambient temperatures. Based on statistical regression theory, a second order polynomial model is learned to describe the ambient temperature’s impact on infrared face image. Then, infrared image was normalized to reference ambient temperature by the second order polynomial model. Finally, this normalization method is applied to infrared face recognition to verify its efficiency. The experiments demonstrate that the proposed temperature normalization method is feasible and can significantly improve the robustness of infrared face recognition.

Citation Download Citation

Zhengzi Wang "Ambient temperature normalization for infrared face recognition based on the second-order polynomial model", Proc. SPIE 9656, International Symposium on Photonics and Optoelectronics 2015, 96560O (22 August 2015); https://doi.org/10.1117/12.2197248

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