Part-based Face Recognition Using Near Infrared Images

Recently, we developed NIR based face recognition for highly accurate face recognition under illumination variations [10]. In this paper, we present a part-based method for improving its robustness with respect to pose variations. An NIR face is decomposed into parts. A part classifier is built for each part, using the most discriminative LBP histogram features selected by AdaBoost learning. The outputs of part classifiers are fused to give the final score. Experiments show that the present method outperforms the whole face-based method [10] by 4.53%.

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Ke Pan, ShengCai Liao, Zhijian Zhang, Stan Z. Li, Peiren Zhang
• Keywords: Accurate Face Recognition, Computer Vision, CVPR 2007, Discriminative Lbp Histogram, Nir Based Face, Nir Face