In this chapter we present a survey of biometric methods that exploit eye tracking technology for identification and verification purposes. Thanks to the availability of cheap and portable devices, it is now possible to deploy an eye tracker in several settings, both in indoor and outdoor environments. Unlike traditional techniques that prevent unauthorized access to secured systems and places, eye-based approaches have the advantage of allowing a contactless interaction that can sometimes even occur covertly. Different eye features will be considered, such as fixation data, scanpath characteristics, saccade dynamics, pupil size, and oculomotor traits. Moreover, although not strictly biometric techniques, ATM-like approaches will be also presented, where PINs or passwords are entered using the gaze instead of an ordinary keyboard.
CITATION STYLE
Bhanu, B., & Kumar, A. (2017). Deep learning for Biometrics. In Human Recognition in Unconstrained Environments: Using Computer Vision, Pattern Recognition and Machine Learning Methods for Biometrics (pp. 197–216). Elsevier.
Mendeley helps you to discover research relevant for your work.