Simplified Nearest Feature Line Space for Face Recognition

In this paper, a novel subspace algorithm entitled Simplified Nearest Feature Line Space (SNFLS) is proposed based on Nearest Feature Line (NFL). NFL space (NFLS) is a subspace learning method and has desirable discriminant power. However, the computational complexity of NFLS is too high because all the feature lines are used. In SNFLS algorithm, some feature lines will be chosen for learning. SNFLS has the same discriminant power as NFLS. At the same time, SNFLS has a lower NFLS. Experimental results confirm its efficiency.