Efficient face recognition using shifted phase-encoded fringe-adjusted joint transform correlator

A new shifted phase-encoded fringe-adjusted joint transform correlation technique is proposed in this paper for invariant face recognition while accommodating expression and illumination variations. The enhanced local binary pattern operator is utilized in the preprocessing stage for facial feature extraction. A phase-shifted and phase-encoded fringe-adjusted joint transform correlator (FJTC) is implemented in order to remove any overlapping patterns among the input scene objects and to better utilize the space bandwidth product, which are major drawbacks of classical JTC. Test results obtained using the Yale Face Database and the extended Yale Face Database B is presented to verify the efficiency of the proposed technique. Test results are then compared with alternate JTC techniques such as shifted phase-encoded fringe-adjusted joint transform correlation.