Examplers based image fusion features for face recognition

We showed the relative advantage of using examplers in comparison with single model approach such as by averaging. In the case of exampler based approach, the increased usage of memory enables the use of more identity information as opposed to single model approach. Although single model approach is computationally less expensive, the use of examplers enables a stable performance even with reduced feature dimensionality. The presented method outperforms other major algorithms in overall robustness across various natural variabilities. This is attributed to the use of texture based spatial change features and the use of local binary decisions classifier. Further, the use of multiple training samples helps in compensation of natural variability and increases the probability for a true match. In addition, a useful aspect of this method is its ability to detect natural variability which sets this method apart from its counterparts. Finally, from the results it is evident that any increase in the number of examplers will make the recognition performance higher and more stable across variations in natural variability and feature dimensionality.