A Study on Real Time Face Recognition Using Feature Based Image Processing Frameworks

Abstract

Face recognition systems are models to recognize human faces on the basis of some computation methods. There are lots of applications (Attendance systems, Criminal identifications, Surveillance systems, Human Computer Interfaces etc.) of such systems. This paper aims to build a system which is capable of providing the user with the ability to first create an image database by face detection and feature extraction, and then this database can be used to perform face recognition by comparing the input image (obtained through live video streaming) with the images stored during the training phase. This method used Viola-Jones algorithm for face detection (to create the training set), and Principal Component Analysis (PCA) for face recognition. We have created our own dataset for validating this automatic face recognition system. Experimental work of proposed method under identical physical conditions on our dataset gives 82% accuracy of face recognition.