A New Algorithm for Generalized Optimal Discriminant Vectors

A study has been conducted on the algorithmof solving generalized optimal set of discriminant vectors in thispaper. This paper proposes an analytical algorithm of solvinggeneralized optimal set of discriminant vectors theoretically for thefirst time. A lot of computation time can be saved because all thegeneralized optimal sets of discriminant vectors can be obtainedsimultaneously with the proposed algorithm, while it needs no iterativeoperations. The proposed algorithm can yield a much higherrecognition rate. Furthermore, the proposed algorithm overcomes theshortcomings of conventional human face recognition algorithms whichwere effective for small sample size problems only. These statements aresupported by the numerical simulation experiments on facial database ofORL.