Two-Dimensional Principal Component Analysis with Local Direction Descriptor

This paper proposes a novel approach using two-dimensional principal component analysis (2D-PCA) and local direction descriptor for face recognition. The proposed method utilizes the transformed image obtained from local direction descriptor as the direct input image of 2D-PCA algorithms. The performance comparison was performed using principal component analysis (PCA) and Gabor-wavelets based on local binary pattern (LBP). The extended Yale B face database was accompanied for performance evaluation of proposed method. From the experimental result, we confirmed the effectiveness of the proposed method under varying lighting conditions.