In this paper, a novel 3-channel orthogonal filter bank was proposed at first, and then an efficient face recognition method combining the filter bank and 2DLDA (two-dimensional linear discriminant analysis) was presented. The framework of the proposed method consists of two steps: First, each face image was decomposed into nine sub images by using the 3-channel filter bank, and then 2DLDA was used to extract the features for face classification from the sub images. Better performance of the proposed method is confirmed by the Yale face database.
Published in:
Computer Engineering and Technology, 2009. ICCET '09. International Conference on
(Volume:2
)
Date of Conference: 22-24 Jan. 2009