Analysis of Filters in Performance Assessment of Principal Component Analysis (PCA) based Face Recognition System

The main challenges in state-of-the-art biometric-based identification systems are accuracy with respect to recognition and robustness with respect to real-time performance. In the past few decades, numerous facial recognition systems have been developed to improve the accuracy and real-time performance of the existing recognition systems. However, the existing systems and techniques could not achieve the required level of performance for recognition. This is due to various factors affecting the performance of these systems. Some of these factors include the availability of limited data sets, a perturbation in the image, lightening, and background color variations, etc. In this article, we provide an analysis of the performance of Principal Component Analysis (PCA) based face recognition system by applying three different linear filters. Experiments have been done by applying different filters over the face images and then a comparative analysis is provided to show the accuracy of each filter using PCA based facial recognition system.