1. IntroductionThe process of verifying a person's identity, also called authentication, plays an important role in various areas of daily life. Any user interaction situation where identity is required requires a way to verify the claimed identity. One of the most obvious and well-known application areas of identity verification technologies, i.e. authentication, is logical access control to computer systems, where authenticity is normally established by confirming a claimed identity with a secret password or PIN. Traditional methods of confirming the identity of an unknown person rely either on secret knowledge (such as a PIN or password) or on an object that the person possesses (such as a key or card). But testing secret knowledge or possession of special items can only confirm knowledge or presence, not the presence of the rightful owner. In fact, both could be stolen. Conversely, biometric technology is capable of establishing a much closer relationship between the user's identity and a particular body, through its unique characteristics or behavior. Biometric verification performs a comparison of the biometric template with the one in the records. Facial recognition is one of the techniques used in biometric verification. When performing facial recognition on a mobile platform, it not only suffers from the same issues as a computer system, such as lighting, occlusion, and pose variations, but is also limited by other factors: Limited processing power, limited memory [1]. To implement facial recognition-based authentication for incoming mobile calls, existing algorithms suffer from recognition time and accuracy trade-off, i.e., increasing robustness will increase recognition time. reco...... middle of paper ......a, M. Pietikainen and T. Maenpaa, “Classification of multiresolution grayscale and rotation-invariant textures with local binary patterns,” IEEE Trans. PAMI, vol.24, n°7, pp.971-987, July 2002.[4] T.Ahonen, A.Hadid, “Face recognition with local binary patterns”, Computer Vision-ECCV 2004-Springer, Volume 3021/2004, 469-481.[5] W.Zhang, S.Shan, “Local Gabor binary histogram sequence (LGBPHS): a new non-statistical model for face representation and recognition,” ICCV, vol. 1, pp.786-791, 2005.[6]E.Vazquez-Fernandez, H.Garcia-Pardo, “Embedded face recognition for intelligent photo sharing on mobile devices,” IEEE 2011.[7] OpenCV - Android website, http://opencv.willowgarage.com/wiki/Android.[8] L.Meylan, D.Alleysson, “Local retinal adaptation model for tonal mapping of color filter array images”, Vol. 24, no. 9/September 2007/ J. Opt. Soc. Am. A,p. 2807-2816.