LAUSR

Human Face Verification (HFV) is used for distinguishing the human as an authorized or unauthorized Person in security and biometric related applications. HFV has huge applications in many areas. HFV process involves the collection, detection, pre-processing, extraction, classifying and Verification stages. The main problem in HFV system is to detect the faces automatically from front view with variation in illumination, expression, and occlusion and so on. This work is mainly focused on extraction and recognition stages. LBP is widely used method for texture analysis. LBP usually compares the center pixel to its neighbors over a fixed radius. LBP is generally sensitive to noise. In order to overcome this problem ELBP method had been proposed which deals with the rotation invariant of face images. The proposed method is evaluated for noise environment, pose variations and emotions. For each one, the experimental results are tabulated and analyzed. From the result analysis, the proposed method provides better accuracy than existing methods.