An innovative speedy approach to improve recognition accuracy in standard appearance based statistical face recognition using wavelet based decomposition

Abstract

Facial recognition has attracted considerable interest from the number of researchers close to pattern recognition in recent decades Face recognition has become very important because of its imminent use in law enforcement and commercial applications such as in the area of access control systems video surveillance user authentication and search Identity from a database for criminal investigations Although there are a number of face recognition systems that show better performance in restricted environments facial recognition is still a very difficult problem in real time applications Many problems arise in the facial recognition process due to the unpredictability of many parameters such as facial lighting expression pose scale low resolution partial face occlusion and other environmental conditions However low resolution recognition and partial facial recognition occlusion remain as major challenges in face recognition and both of these issues affect face recognition performance in access control authentication and surveillance applications To meet these challenges the present study proposes a face recognition system using four algorithms such as Enhanced Two Dimensional Principal Component E2DPCA Based Face Recognition Facial Image Recognition Using Supervised Pixel Invariant Principal Component SPIPCA A Robust Wavelet Based Facial Image Decomposition With2DPCA WBFD 2DPCA Facial Recognition and Bag of Visual Words Based Reinforced Support Vector Machine Classifier BOVW RSVM Based Facial Image Recognition. newline