Dual Tree Complex Wavelet Transform based Face Recognition with Single View K.Jaya Priya Research Scholar, Mother Teresa Women’s University, India E-mail:kjp.jayapriya@yahoo.com Dr. R.S. Rajesh Reader, Department of Computer Science and Engineering, Manonmaniam Sundaranar University, India E-mail: rs_rajesh1@yahoo.co.in ABSTRACT In this paper, we propose a novel local appearance feature extraction method based on multi-resolution Dual Tree Complex Wavelet Transform (DT-CWT). Each face is described by a subset of band filtered images containing block-based DT-CWT coefficients. These coefficients characterize the face texture. The block based mean and variance of complex wavelet coefficients are used to describe the face image. The use of the complex wavelet transform is motivated by the fact that it helps eliminate the effects of non-uniform illumination, and the directional information provided by the different sub bands makes it possible to detect edge features with different directionalities in the corresponding image. The resulting complex wavelet-based feature vectors are as discriminating as the Gabor wavelet- derived features and at the same time are of lower dimension when compared with that of Gabor wavelets. 2-D dual-tree complex wavelet transform is less redundant and computationally efficient. Experiments, on two well-known databases, namely, Yale and ORL databases, shows the DT-CWT in block based approach performs well on illumination, expression and perspective variant faces with single sample compared to PCA and global DT-CWT. Furthermore, in addition to the consistent and promising classification performances, our proposed method has a really low computational complexity. Keywords: gabor wavelet transform, dual tree discrete wavelet transform, dual tree complex wavelet transform. 1 INTRODUCTION In recent years face recognition received more attention in the field of biometric authentication. This is due to increased concerns in security. However, the general problem of face recognition remains to be solved, since most of the systems to date can only successfully recognize faces when images are obtained under prescribed conditions. Their performance will degrade abruptly when face images are captured under varying pose, lighting, with accessories and expression. Another one of the most challenging problems for face recognition is the so-called Single Sample Problem (SSP) problem, i.e., a single face for a subject is used for training. Large training samples can not be guaranteed in practice such as identity card verification, passport verification, etc. Some face recognition algorithms have been proposed to solve the face recognition problem with only a single training image with various mode of process [1]. A face recognition system should, to a large extent, take into account all the above-mentioned natural constraints and cope with them in an effective manner. In order to achieve this, one must have efficient and effective representations for faces. Many techniques have been proposed in the literature for representing face images. Some of these include principal components analysis [2], discrete wavelet transform [3, 4], and discrete cosine transform [5]. Gabor wavelet-based representation provides an excellent solution when one considers all the above desirable properties. For this reason, Gabor wavelets have been extensively implemented in many face recognition approaches [6-9]. Even though Gabor wavelet-based face image representation is optimal in many respects, it has got two important drawbacks that shadow its success. First, it is computationally very complex. A full representation encompassing many directions (e.g., 8 directions), and many scales (e.g., 5 scales) requires the convolution of the face image with 40 Gabor wavelet kernels. Second, memory requirements for storing Gabor features are very high. The size of the