Local fusion of complex dual-tree wavelet coefficients based face recognition for single sample problem

In this paper, we propose a novel face recognition method for the one sample problem. This approach is based on local appearance feature extraction using directional multiresolution decomposition offered by dual tree complex wavelet transform (DT-CWT). It provides a local multiscale description of images with good directional selectivity, effective edge representation and invariance to shifts and in-plane rotations. In the dual-tree implementation, two parallel discrete wavelet transforms (DWT) with different lowpass and highpass filters in different scales are used. The linear combination of subbands generated by two parallel DWT is used to generate 6 different directional subbands with complex coefficients. It is insensitive to illumination variations and facial expression changes. The 2-D dual-tree complex wavelet transform is less redundant and computationally efficient. The fusion of local DT-CWT coefficients of detail subbands are used to extract the facial features which improve the face recognition with small sample size in relatively short computation time. The local features based methods have been successfully applied to face recognition and achieved state-of-the-art performance. Normally for most of the local appearance based methods, the facial features are extracted from several local regions and concatenated into an enhanced feature vector as a face descriptor. In this approach we divide the fused face representation into several (m×m) non-overlapped parallelogram blocks instead of square or rectangular blocks. Experiments, on two well-known databases, namely, Yale and ORL databases, shows the Local fusion of DT-CWT approach performs well on illumination, expression and perspective variant faces with a single sample compared to PCA and global DT-CWT. Furthermore, in addition to the consistent and promising classification performances, our proposed Local fusion of DT-CWT based method has a really low computational complexity.