To search, Click below search items.


All Published Papers Search Service


Impact of Locally Linear Regression and Fisher Linear Discriminant Analysis in Pose Invariant Face Recognition




Vol. 10  No. 10  pp. 111-115


Face Recognition is an increasingly popular identification technique which faces challenging problems in real life applications because of the variation in the input face images. Various face recognition algorithms, along with their extensions, have been proposed during the past three decades. In recent years, the focus is on the research on pose invariant face recognition system and many prominent approaches have been proposed. But, there are several issues in face recognition across pose variation which still remains open ended. This paper provides a research on the impact of Locally Linear Regression (LLR) and Fisher Linear Discriminant Analysis (FLDA) in pose invariant Face recognition where LLR is predicting the frontal image of non frontal face image, FLDA does recognition of faces with Principal Component Analysis (PCA) used for dimensionality reduction of the face image before the recognition. Image based face recognition in varying pose is one of the most challenging task in face recognition. The existing techniques in 2D pose Invariant face recognition are comprehensively reviewed and discussed. Validation of this approach is done with Yale Face Database B. Experimental results show the effectiveness of this approach in performance.


Face Recognition, Pose variation, Locally Linear Regression(LLR), Fisher Linear Discriminant Analysis(FLDA), Principal Component Analysis(PCA)