Robust Real Time based Face Recognition using Support Vector Machine & Histogram Equalization Algorithm

A face recognition algorithm based Support Vector Machine & Histogram Equalization Methods. These methods allow standardizing the faces illumination reducing in such way that the variations for further features extraction, which are extracted using the image phase spectrum of the histogram equalized image together with the principal components analysis. This algorithm operates by mapping training set into a high-dimensional feature space, and separate positive and negative samples. In statistical learning theory, for some classes of well behaved data, the choice of the maximum margin hyper plane will lead to maximal generalization when predicting the classification. The input dataset is divided into training and testing dataset and experiments are performed by varying dataset size. The effect of performing image intensity normalization, histogram equalization, and input scaling are observed. Proposed scheme allows a reduction of the amount of data without much information loss. Evaluation results show that the proposed feature extraction scheme, when used together with the support vector machine (SVM), provides a recognition rate higher than 97 % and a verification error lower than 0.003 %.