Face Recognition Using Local Ternary Pattern and Booth's Algorithm

In the literature of face recognition many methods have been proposed which extract local texture features for robust pattern classification. But for final computation of the feature the information about central pixel is not taken into account. In this paper, we propose a novel method which utilizes Local Ternary pattern and Booth's Algorithm techniques to capture the local face features, which utilize central pixel for computation of the feature. Face images are spatially varied and classification works better with local descriptors, a Non-overlapping block wise processing is done on image to limit the features. The Support Vector Machine (SVM) and KNN classifier with proposed similarity measure is used for face classification. Finally, ROC and CMC are plotted for analysis of the system. Experiments are conducted on ORL and faces94 datasets demonstrates that the proposed method has better classification accuracy than previously proposed methods.