Infrared and Hyper-Spectral Imaging, Face Recognition

June 2019

Thermal emissions from skin are an intrinsic property independent of illumination. Therefore the face images captured using thermal IR sensors will be nearly invariant to changes in ambient illumination. The illumination variation problem is one of the well-known problems in face recognition in uncontrolled environment. Infrared imaging sensors have become an area of growing interest. Thermal IR imagery has been suggested as an alternative source of information for detection and recognition of faces, while visual cameras measure the ultra-magnetic energy in the visible spectrum range(0.4-0.7um), sensor in IR cameras respond to the thermal radiation in the infrared spectrum range at 0.72-14.0um. While sacrificing colour recognition, thermal IR face  recognition techniques can be used to identify faces when there is little or no control over lighting conditions. To address this serious limitation of IR it is proposedto fusing IR with other forms of facial recognition techniques by combining IR with hyper-spectral face recognition for a better identification system.

24-28

2455-9997 (Online) - 2229-3531 (Print)

Vol.10 - No.3

Click here to download full paper

http://dx.doi.org/10.22147/jucit/100301