Article Preview
TopIntroduction
The face recognition task in the computer vision system can be described as follows: Given an input face image and a database of face images of known individuals, how can we verify or determine the identity of the person in the input image? A robust face recognition system is used in a biometric application for verifying and identifying an individual of interest. Researchers from the areas of image analysis, computer vision, machine learning, pattern recognition, and many others are working cooperatively, inspired not only by the fundamental challenges but also by various real-life applications in which person of interest identification is required. The interest of researchers is also increased by the fact that with the rising public concern for security, the need for identity verification such as face recognition is more apparent. Also, advance technology, such as in mobile devices and digital cameras made face recognition more important and easier to approach. The various state-of-art methods of face recognition in constrained environments have achieved satisfactory results. There are still many issues which are untouched in unconstrained environments, such as partial occlusions, large pose variations, etc.
In this paper, we have proposed an approach which utilized the Local Generic Feature (LGF) to recognize the face in the partial occlusion by fusing features Scale Invariant Feature Transform (SIFT) & Multi-Block Local Binary Pattern (MB-LBP). It also utilizes a Robust Kernel method for classification of the query image.
The following is the organization of this paper. In Section 2, we have briefly described the related work. In Section 3, the proposed model for robust face recognition is described. Section 4 shows the result and discussion of experimental results on standard datasets. Finally, section 5 elaborates the conclusion and future scope.