Hybridization of Biogeography-Based Optimization and Gravitational Search Algorithm for Efficient Face Recognition
This chapter aims to apply a novel hybridized evolutionary algorithm to the application of face recognition. Biogeography-based optimization (BBO) has some element of randomness to it that apart from improving the feasibility of a solution could reduce it as well. In order to overcome this drawback, this chapter proposes a hybridization of BBO with gravitational search algorithm (GSA), another nature-inspired algorithm, by incorporating certain knowledge into BBO instead of the randomness. The migration procedure of BBO that migrates SIVs between solutions is done between solutions only if the migration would lead to the betterment of a solution. BBO-GSA algorithm is applied to face recognition with the LFW (labelled faces in the wild) and ORL datasets in order to test its efficiency. Experimental results show that the proposed BBO-GSA algorithm outperforms or is on par with some of the nature-inspired techniques that have been applied to face recognition so far by achieving a recognition rate of 80% with the LFW dataset and 99.75% with the ORL dataset.