Face recognition committee machine

Face recognition has been of interest to a growing number of researchers due to its applications on security. Within past years, there are numerous face recognition algorithms proposed by researchers. However, there is no unified framework for the integration. We implement different existing well-known algorithms, eigenface, Fisherface, elastic graph matching (EGM), support vector machine (SVM) and neural network, to give a comprehensive testing under same face databases. Moreover, we present a face recognition committee machine (FRCM), which is a novel approach for assembling the outputs of various face recognition algorithms to obtain a unified decision with improved accuracy. The machine consists of an ensemble of the above algorithms to cope with various face images. We have tested our system with the ORL face database and Yale face database. A comparative experimental result of different algorithms with the committee machine demonstrates that the proposed system achieves improved accuracy over the individual algorithms.