PROJECT TITLE :

Face Recognition using supervised probabilistic Principal Component Analysis mixture model in Dimensionality Reduction without loss framework

ABSTRACT:

During this study, 1st a supervised version for probabilistic principal component analysis mixture model is proposed. Using this model, local linear underlying manifolds of information samples are obtained. These underlying manifolds are used in a dimensionality reduction without loss framework, for face recognition application. In this framework, the advantages of dimensionality reduction are employed in the predictive model, whereas using the projection penalty idea, the loss of helpful info can be minimised. The authors use support vector machine (SVM) and k-nearest neighbour (KNN) classifiers as the predictive models during this framework. To train and evaluate the proposed methodology, the well-known face databases are used. The experimental results show that the proposed technique with SVM as the predictive model have the most average classification accuracy compared with several traditional strategies that use predictive model SVM after dimensionality reduction, and conjointly compared with the projection penalty plan used for linear and non-linear kernel-based dimensionality reduction methods. Moreover, their experiments show that the proposed technique with KNN as predictive model is superior to the case that dimensionality reduction is performed, and then the KNN classifier is applied.