Occlusion of eyeglasses, and strong specular reflections on eyeglasses (especially in near infrared (NIR) images), can deteriorate face recognition performance. In this paper, we present a novel method to overcome these problems. The proposed method applies the sparse representation (SR) technique in a local feature space so as to be more tolerant to mis-alignment and abnormal specular pixel values. The SR face features are further transformed by using discriminant analysis. These lead to a good balance between efficiency and robustness. Extensive experiments on a large NIR face database containing 292 persons with/without eyeglasses show the superiority of the proposed method compared with state-of-the-art methods.
Paper
Full text
Learning sparse feature for eyeglasses problem in face recognition
Semantic Scholar · Computer Science · 2011
Abstract
Occlusion of eyeglasses, and strong specular reflections on eyeglasses (especially in near infrared (NIR) images), can deteriorate face recognition performance. In this paper, we present a novel method to overcome these problems. The proposed method applies the sparse representation (SR) technique in a local feature space so as to be more tolerant to mis-alignment and abnormal specular pixel values. The SR face features are further transformed by using discriminant analysis. These lead to a good balance between efficiency and robustness. Extensive experiments on a large NIR face database containing 292 persons with/without eyeglasses show the superiority of the proposed method compared with state-of-the-art methods.