An experimental evaluation of different face recognition algorithms using closed circuit Television images

Bio-metric based recognition is rapidly replacing the non-biometric based recognition systems. Face recognition is one of the most important bio-metric based recognition technique. Different algorithms exist for face recognition that works well on high resolution digital images. The aim of this work is to check whether these existing face recognition algorithms work on low quality Closed Circuit Television images? We have considered three such algorithms. These algorithms are Artificial Neural Network, Principal Component Analysis and Single Value Decomposition. We have experimentally evaluated these for Closed Circuit Television images. Our experiments show that using the CCTV images the accuracy rate of ANN for face recognition is 85%, for PCA the accuracy rate is 75% and for SVD the accuracy rate is 65%. The experiments also show that the accuracy of all the three algorithms reduces when the number of input faces increases.