Abstract

The following paper presents a simple and fast liveness detection method based on gaze direction estimation under a challenge-response user authentication scenario. To estimate a line of sight, a procedure composed of several steps, including face and eye detection, derivation of gaze direction representation and subsequent classification, has been proposed. The proposed, novel gaze orientation descriptor is easy to compute and it provides sufficiently accurate estimates for the considered task. To assess a probability of genuine biometric trait presentation, recorded gaze direction responses induced by presentation of a randomly generated on-screen object, are matched against expected patterns.

Highlights

  • O NE OF the main threats that exist for unattended biometric authentication systems are so called ’presentation attacks’, where a system is presented with a biometric artefact

  • The following paper presents a simple and fast liveness detection method based on gaze direction estimation under a challenge-response user authentication scenario

  • The proposed algorithm proves that liveness detection can be performed using line-of-sight estimation, by using a simple camera for image acquisition

Read more

Summary

INTRODUCTION

O NE OF the main threats that exist for unattended biometric authentication systems are so called ’presentation attacks’, where a system is presented with a biometric artefact. To enable unattended (including remote, by means of popular mobile devices) user verification, biometric systems must cope with the stated problem For this purpose, a methodology aimed at verification of biometric trait authenticity, referred to as liveness detection, has been developed. An application of a similar challengeresponse scheme in video based face analysis have been proposed in [5], where a challenge requires a user to make voluntary blinks and mouth movements (opening and closing) Another interesting example of challenge-response scheme that utilizes gaze tracking and that is intended as a secure method for logging to computer systems has been proposed in [6]. The proposed algorithm for line-of-sight direction estimation is based both on salient feature detection and appearance-based eye modeling, and it is followed by regression based analysis, so it combines both of the presented general methodologies.

GAZE ESTIMATION ALGORITHM
ROI Derivation
Line-of-sight Direction Assessment
EXPERIMENTAL EVALUATION OF THE PROCEDURE
Findings
CONCLUSION
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call