Thermal infrared exploitation for 3D face reconstruction

Bernard O. Abayowa

doi:10.1117/12.818720

29 April 2009 Thermal infrared exploitation for 3D face reconstruction

Bernard O. Abayowa

Proceedings Volume 7347, Evolutionary and Bio-Inspired Computation: Theory and Applications III; 73470F (2009) https://doi.org/10.1117/12.818720
Event: SPIE Defense, Security, and Sensing, 2009, Orlando, Florida, United States

Abstract

Despite the advances in face recognition research, current face recognition systems are still not accurate or robust enough to be deployed in uncontrolled environments. The existence of a pose and illumination invariant face recognition system is still lacking. This research exploits the relationship between thermal infrared and visible imagery, to estimate 3D face with visible texture from infrared imagery. The relationship between visible and thermal infrared texture is learned using kernel canonical correlation analysis(KCCA), and then a 3D modeler is used to estimate the geometric structure from predicted visual imagery. This research will find it's application in uncontrolled environments where illumination and pose invariant identification or tracking is required at long range such as urban search and rescue (Amber alert, missing dementia patient), and manhunt scenarios.

Citation Download Citation

Bernard O. Abayowa "Thermal infrared exploitation for 3D face reconstruction", Proc. SPIE 7347, Evolutionary and Bio-Inspired Computation: Theory and Applications III, 73470F (29 April 2009); https://doi.org/10.1117/12.818720

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