A proposed method for the improvement in biometric facial image recognition using document-based classification

This paper mainly focuses on improving the recognition rate and reducing the recognition time in facial image recognition application. The existing methods are based on statistical or neural network or fuzzy-based feature extraction. In this study, the feature extraction followed by classification method is carried out based on documentation-based approach called bag of visual words (BOVW). In BOVW method, the feature vectors were extracted on the basis of scale invariant feature transform (SIFT) and classified by support vector machine (SVM). In train 50% and test 50% strategy, four standard face databases were tested with BOVW documentation approach. For the face databases such as Our Databases of Face Research Lab (ORL), Surveillance, Yale, Face recognition technology (FERET), this method produced 98, 82, 89.33, and 97.9798% of recognition rate, respectively. In the leave-one-out strategy, nine standard face databases were tested. The BOVW method gave 100% of recognition rate for face databases such as Cohn–Kanade (CK+), Georgia Tech, Morphological, Surveillance, Yale and YaleB, whereas it gave 99.772% of recognition rate for ORL and 97.9798% for FERET face databases. Our choice of BOVW + SVM is a better approach to increase classification rate and also reduce recognition time.