Face Recognition Using DT-CWT Feature-Based 2DPCA

In face recognition, a way to enhance the discriminability is to provide effective feature representation. Dual-Tree Complex Wavelet transform (DT-CWT) provides a local multiscale description of images with good directional selectivity and shift invariance, and is robust to illumination variations and facial expression changes. In this paper, we propose a novel approach to face feature extraction and recognition using DT-CWT feature and 2DPCA. DT-CWT is used to extract face feature at different scales and orientations, then two-dimensional principal component analysis (2DPCA) is applied for dimensionality reduction in the DT-CWT feature space. Experimental results on ORL and AR face databases show that our proposed method works well.