We demonstrate a novel technique for face recognition. Our approach relies on the performances of a strongly discriminating optical correlation method along with the robustness of the independent component analysis (ICA) model. Simulations were performed to illustrate how this algorithm can identify a face with images from the Pointing Head Pose Image Database. While maintaining algorithmic simplicity, this approach based on ICA representation significantly increases the true recognition rate compared to that obtained using our previously developed all-numerical ICA identity recognition method and another method based on optical correlation and a standard composite filter.
© 2011 Optical Society of America
Original Manuscript: October 6, 2010
Revised Manuscript: January 18, 2011
Manuscript Accepted: January 18, 2011
Published: February 18, 2011
Vol. 6, Iss. 4 Virtual Journal for Biomedical Optics
A. Alfalou and C. Brosseau, "Robust and discriminating method for face recognition based on correlation technique and independent component analysis model," Opt. Lett. 36, 645-647 (2011)