Face Recognition: A Comparative Analysis using SVM, KNN and K-Means Algorithms

摘要

Zn the past few years the domain of face recognition has received substantial attention, but is still very challenging. By the current date a lot of face recognition algorithms have been developed and analyzed but, because of advancement in technology only face recognition technology is not sufficient to provide security. Everyone has to think one step ahead of this, Era of multi model has on its peak in every domain, considering this in this paper we have proposed a method in which 3 level securities has been proposed, one is simple text password, second is face recognition and third is graphical password. In this paper the prime emphasis is to determine the efficiency of Support vector machine, K nearest neighbor algorithm and K-Means algorithm in face recognition on the basis of two parameters, intensity and time elapsed. This paper is an implementation of a project made on face recognition in MATLAB. In this work we have used three different methods to enhance the security of the system. Such enhanced security had no negative impact on the experimental work done.