Face Recognition using One-shot Learning
Nikhil Thakurdesai, Nikita Raut, Anupam Tripathi · International Journal of Computer Applications · 2018
Face Recognition represents one of the attractive research areas.It has drawn the attention of many researchers due to its varying applications such as security, healthcare, marketing, identity authentication, surveillance etc.In this order, different face recognition algorithms have been proposed however, one algorithm that stands out in the event of limited dataset is one shot learning."One shot" means learning from a single training item.This paper discusses a way for solving this problem.Neural networks are notorious for requiring extremely large datasets to reach a considerable accuracy.This paper proposes a method to solve this problem for the face recognition domain by bringing down the number of training samples required to just one and still achieving a decent accuracy close to 90%.