Face recognition using 1DLBP texture analysis

Abstract

A new algorithm for face recognition is proposed in this work; this algorithm is mainly based on Local Binary Pattern texture analysis in one dimensional space and Principal Component Analysis as a technique for dimensionalities reduction. The extraction of the face’s features is inspired from the principal that the human visual system combines between local and global features to differentiate between people. Starting from this assumption, the facial image is decomposed into several blocks with different resolutions, and each decomposed block is projected in one dimensional space. Next, the proposed descriptor is applied for each projected block. Then, the resulting vectors will be concatenated in one global vector. Finally, Principal Component Analysis is used to reduce the dimensionalities of the global vectors and to keep only the pertinent information for each person. The experimental results have shown that the proposed descriptor Local Binary Pattern in one Dimensional Space combined with Principal Component Analysis have given a very significant improvement at the recognition rate and the false alarm rate compared with other methods of face recognition, and a good effectiveness against different external factors as: illumination, rotations, and noise.