Achieving Robustness in Face Recognition by Effective Feature Acquisition

In the past few decades, face recognition has been a widely researched topic, since it is a robust means of authentication. Extraction of features from the face images during face recognition is a very challenging task. Hence, proper selection of appropriate feature extraction algorithms is vital in this regard. Many robust feature extraction techniques do exist. But their proper selection and combination also plays an utmost role. In this study, 2D face recognition was achieved using the combination of local binary pattern (LBP), principal component analysis (PCA) and Support Vector Machines (SVM). Along with retaining most of the information, PCA is used to reduce multidimensional data to lower dimensions. LBP was mainly used to tackle the problems arising due to expressions. As the facial expression changes, the effect gets prevalent on the rest of the organs of the face. Similarly, the intensity of the corresponding pixels of images also changes. Hence, this study aims to overcome these challenges by applying PCA and LBP algorithms on face images to increase the recognition rate. SVM was used to perform classification on these datasets. This hybrid approach of using LBP and PCA in conjunction increased the recognition rate (RR) and decreased the false match rate. Therefore, this method was found to be more suitable for real-time applications.