In this paper, we consider the problem of feature selection and classifier fusion and discuss how they should be reflected in the fusion system architecture. We employed the genetic algorithm with a novel coding to search the worst performing fusion strategy. The proposed algorithm tunes itself between feature and matching score levels, and improves the final performance over the original on two levels, and as a fusion method, it not only contains fusion strategy to combine the most relevant features so as to achieve adequate and optimized results, but also has the extensive ability to select the most discriminative features and their appropriate classifiers. Sparse Representation Classifier (SRC) and Nearest Neighbor classifier with euclidean distance, mahalanobis distance, cosine distance and correlation distance are exploited to calculate all the similarity measures. Experiments are provided on the FRGC database and show that the proposed method produces significantly better results than the baseline fusion methods