Boosting non-graph matching feature-based face recognition with a multi-stage matching strategy

In this paper, a multi-stage matching strategy is proposed to boost the performance of a non-graph matching feature-based face recognition. As the gallery size increases, the problem of recognition degradation gradually arises, due to the fact that the correct matching of feature points becomes more and more difficult. Other than only one round of matching in traditional methods, the multi-stage matching strategy determines the recognition result step by step. Instead of finding the best one matching, each step picks out a small portion of the training candidates and removes the others. The behavior of picking and removing repeats until the number of remaining candidates is small enough to produce the final result. Two multi-stage matching algorithms, n-ary elimination and divide and conquer, are introduced into the non-graph matching feature-based method from the perspectives of global and local, respectively. The experimental result shows that with the multi-stage matching strategy, the recognition accuracy of the non-graph matching feature-based method is evidently boosted. Moreover, the improvement level also increases with the gallery size.