Abstract:
Human face recognition by computer systems has become a major field of interest. Face recognition algorithms are used in a wide range of applications like security control, video retrieving, Biometric signal processing, human computer interface, image database management, etc. It is difficult to develop a complete robust face detector due to various light operating conditions, different face sizes and face orientations, background and skin colors. This paper, proposes a face recognition method for locate the problem of unconstrained face recognition from remotely acquired images. The main factors to affect this system is challenging are image degradation due to blur, appearance variations due to illumination and pose. In this paper, using a blur-robust algorithm based on PCA with Euclidian(K-NN) Classifier, is a non-parametric method for classification and regression, which predicts objects' "values" or class memberships based on the Nth closest sampled examples in the feature space. In Future of the work propose a blur-robust algorithm based on Eigen Face with Bayes classifier whose main step involves a simple probabilistic classifier based on applying Bayes' theorem with strong independence assumptions. Finally to compare both the face recognition methods and prove that the proposed method is better by overcoming the disadvantages of existing method. A computer simulation using MATLAB/SIMULINK confirms the predicted results.

Keywords: Illumination Robust Face Recognition