The present chapter is an attempt to highlight the possible applications of nanotechnology through the nano-human brain neurons to provide a secure face identification system. The principle of neural networks has been applied to construct an artificial biological substitute that imitates, maintains and restores the expert functionality of human neurons. Face identification is quite a challenging task, as faces are highly dynamic and undergo wide variations due to pose, illumination, occlusion and expressions. Selection and implementation of a face descriptor, which is both discriminative and computationally efficient, is very crucial. The present study explores the well-known techniques of face representation, viz. Zernike moments and Pseudo-Zernike moments, due to their efficient image representation ability. The chapter also investigates the ability of recently introduced polar harmonic transforms to represent the faces in real-time environments. The techniques are validated on benchmark ORL, Yale and FERET face databases. Recognition is performed using the three neural network-based classifiers, viz., back-propagation neural network, adaptive neuro-fuzzy inference system and support vector machine. It is proved that the proposed face recognition set-up provides successful results in real-time environments despite diverse facial variations.