Biometric recognition using 3D face

Abstract

Biometrics deals with recognizing a user based on his/her physiological or behavioural characteristics. By applying sensors, both physiological (such as fingerprint, iris, face, ear etc.) as well as behavioural (such as signature, handwriting, voice, etc.) characteristics can be captured from the user. These characteristics are relatively unique, permanent, and difficult to forge and share. Also, a user does not need to worry about forgetting them or making any special effort to carry them along. Among various biometric traits (features), face is the most widely used trait for user identification. The use of human face is becom ing popular day by day and many countries are currently using it as a prime tool for the identification/recognition of their citizens. Face recognition has recently gained considerable attention as one of the most success ful applications of image analysis and recognition, especially in the last few years. This can be attributed to at least two factors: the wide spectrum of its real-world applications such as authentication, access control and surveillance, and the availability of viable tech nologies after several years of continuous studies. However, the existing 2D Human face recognition systems have attained a certain level of maturity, but the limitations imposed by many real-world applications limit their success. The Challenges faced by 2D Human face recognition with changes in illumination and/or position and especially spoofing attacks, for example, are still unsolved. Here 3D face recognition technologies provide a solution to the challenges proposed as it could accurately recognize human faces even in low-light settings, with a variety of facial angles and expressions and can deal with spoofing. But the collection and processing of 3D data is itself a big challenge owing to its high computational power and resource requirements