FARFE: Face Recognition Feature Extraction Approach
Anshul Mishra1, Arun Kumar Shukla2

1Anshul Mishra, Department of Computer Science, Sam Higginbottom. Institute of Agriculture & Technology Sciences Naini, Allahabad 211007, (U.P), India.
2Arun Kumar Shukla, Department of Computer Science, Sam Higginbottom. Institute of Agriculture & Technology Sciences Naini, Allahabad 211007, (U.P), India.
Manuscript received on October 09, 2016. | Revised Manuscript received on October 12, 2016. | Manuscript published on October 25, 2016. | PP: 12-15 | Volume-4 Issue-6, October 2016. | Retrieval Number: F1128094616
Open Access | Ethics and Policies | Cite
© The Authors. Published By: 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: In the modern era of computing, object recognition form a deeply entrenched and omnipresent component of intelligent social systems. With data and information accumulating in abundance, there is a crucial need for high security. Biometrics has now received more attention. Face biometrics, useful for a person’s authentication is a simple and non-intrusive method that recognizes face in complex multidimensional visual model and develops a computational model for it. In this work we presented a novel Face Recognition feature selection system, FARFE, based on combination of Particle Swarm Optimization (PSO) and Oriented FAST Rotated Brief (ORB). The proposed PSO and ORB based feature selection system is utilized to search the feature space for the optimal feature subset where features are carefully selected according to a well-defined discrimination criterion. The classifier performance and the length of selected feature vector are considered for performance evaluation using MATLAB in ORL face database
Keywords: Face Recognition, Feature selection, PSO, ORB, ORL Dataset, Computer Vision, SURF, SIFT