Face Recognition using VIS and Near-IR Images: A Comparison

摘要

This work treats aspects of image nature, acquisition and processing in facial recognition biometric technologies, in an attempt to develop robust solutions in this subject. In particular, this paper presents initial results in a study comparing the effectiveness of visible and infrared (IR) imagery for detecting and recognizing faces in areas where identification is critical, such outdoor environments with variable lighting conditions. This study is based on the Karhunen-Loeve Transform for feature extraction (reduction of dimensionality of the face image), and the identification process, using visible and infrared imagery. The combination of both types of images will be contemplated in future work.