Share Email Print

Proceedings Paper

A new method of NIR face recognition using kernel projection DCV and neural networks
Author(s): Ya Qiao; Yuan Lu; Yun-song Feng; Feng Li; Yongshun Ling
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A new face recognition system was proposed, which used active near infrared imaging system (ANIRIS) as face images acquisition equipment, used kernel discriminative common vector (KDCV) as the feature extraction algorithm and used neural network as the recognition method. The ANIRIS was established by 40 NIR LEDs which used as active light source and a HWB800-IR-80 near infrared filter which used together with CCD camera to serve as the imaging detector. Its function of reducing the influence of varying illuminations to recognition rate was discussed. The KDCV feature extraction and neural network recognition parts were realized by Matlab programming. The experiments on HITSZ Lab2 face database and self-built face database show that the average recognition rate reached more than 95%, proving the effectiveness of proposed system.

Paper Details

Date Published: 11 September 2013
PDF: 6 pages
Proc. SPIE 8907, International Symposium on Photoelectronic Detection and Imaging 2013: Infrared Imaging and Applications, 89071M (11 September 2013); doi: 10.1117/12.2032609
Show Author Affiliations
Ya Qiao, Electronic Engineering Institute (China)
Yuan Lu, Electronic Engineering Institute (China)
Yun-song Feng, Electronic Engineering Institute (China)
Feng Li, Electronic Engineering Institute (China)
Yongshun Ling, Electronic Engineering Institute (China)

Published in SPIE Proceedings Vol. 8907:
International Symposium on Photoelectronic Detection and Imaging 2013: Infrared Imaging and Applications
Haimei Gong; Zelin Shi; Qian Chen; Jin Lu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?