Face recognition using infrared imaging

• Main Author: Pereira, Diogo Camara
• Other Authors: Fargues, Monique P.
• Published: Monterey, California. Naval Postgraduate School 2012
• Online Access: http://hdl.handle.net/10945/3471

Approved for public release; distribution in unlimited. === This study investigated a (IR) face recognition system using an uncooled IR camera. A computer-based image collection set-up was designed and used to create a small database of 420 facial images, from 14 volunteers. Man-ual and automated facial image cropping routines were implemented. Two linear approaches for the dataset di-mension reduction and classification were implemented and their resulting classification performances compared: PCA-based and LDA approaches. Results show that the best PCA-based average classification performance is equal to 92.22% while the LDA-based classification performance is equal to 99.40%. These results successfully show that an uncooled IR camera may be used to discriminate between individual subjects obtained from a small database collected under a very controlled environment.