A novel model for two-dimensional independent TV-Based Quotient image and its application to face recognition

A novel model for Two-Dimensional Independent TV- Based Quotient Image is proposed in this paper, and the new proposed model is applied to face recognition with only one sample per subject on a large scale face database. In our model, an ETVQI model is firstly proposed to overcome drawbacks of the TVQI model. Then, a two-dimensional independent subspace analysis algorithm is proposed to reduce the dimension of face samples normalized by ETVQI model and to extract high-order statistical features of these samples. According to experiments on the CAS-PEAL face database, our proposed model could outperform ICA with architecture II (ICA2), (2D)²PCA and TVQI. And it also confirms that our model is robust not only to illumination, but to other outliers (expression, masking, occlusion etc.) in face recognition.