A Novel Approach to Face Recognition with Pose and Illumination Variation using Support Vector Machine as Classifier
R.Rajalakshmi1, M.K.Jeyakumar2
1R. Rajalakshmi, Research Scholar, Department of Computer Application, Noorul Islam University, Kumaracoil (Tamil Nadu), India.
2Dr. M.K. Jeya Kumar, Professor, Department of Computer Application, Noorul Islam University, Kumaracoil (Tamil Nadu), India.
Manuscript received on 10 September 2013 | Revised Manuscript received on 19 September 2013 | Manuscript Published on 30 September 2013 | PP: 4-10 | Volume-3 Issue-4, September 2013 | Retrieval Number: D1155093413/13©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Human face recognition has attracted significant consideration as one of the most effective applications of image analysis and understanding. Face recognition is one among the diverse techniques used to identify an individual. Pose and Illumination are the two major challenges, among the several factors that influence face recognition. The objective of this paper is to implement an automated machine supported Face recognition System that recognizes well the identity of a person in the images that were not used in a training phase That is an initialization and training by representative sample of images precede an evaluation phase. Pose and illumination variations severely affect the performance of face recognition. Feature Extraction and Dimensionality Reduction is applied using Principal Component Analysis(PCA) and Linear Discriminant Analysis(LDA). During Recognition phase different classifiers such as ANFIS(Adaptive Neuro Fuzzy Inferrence Engine), NN(Neural Network), SVM (Support Vector Machine), K-NN(KNearest Neighbourhood) algorithms are used to the analyze and evaluate the Recognition Rate.
Keywords: Eigen Vector, Recognition Rate, Training Sets, Testing Set.
Scope of the Article: Pattern Recognition