Effective Face Recognition using Deep Learning based Linear Discriminant Classification

Linear Discriminant Regression Classification (LDRC) is an effective method developed in the recent years on aim of providing enhancement to the accuracy of Face Recognition (FR) based systems. The visible general problems in face recognition are fraudulent faces and the factors affecting recognition accuracy such as noise, diversions in the angle, poses and expression. These problems are the main cause for system to lose its perfection and many researchers are working on LDRC to make it efficient for resisting against the problems. In this paper, Deep Learning method is introduced with as a part of learning based strategy to provide a complete analysis about the face samples present in the system. It also improves the performance of the LDRC by keeping the track of history information about the faces arriving as an input. The experimental results acquired on YALE and ORL database shows that the proposed system performs well than the early methods of LRC algorithms.