ABSTRACT
Recent results suggest that biometric identification based on human's eye movement characteristics can be used for authentication. In this paper, we present three new methods and benchmark them against the state-of-the-art. The best of our new methods improves the state-of-the-art performance by 5.2 percentage points. Furthermore, we investigate some of the factors that affect the robustness of the recognition rate of different classifiers on gaze trajectories, such as the type of stimulus and the tracking trajectory length. We find that the state-of-the-art method only works well when using the same stimulus for testing that was used for training. By contrast, our novel method more than doubles the identification accuracy for these transfer cases. Furthermore, we find that with only 90 seconds of eye tracking data, 86.7% accuracy can be achieved.
Supplemental Material
- Leo Breiman. 1996. Bagging Predictors. Machine Learning 24, 2 (1996), 123--140. DOI: http://dx.doi.org/10.1007/BF00058655Google ScholarDigital Library
- Leo Breiman. 2001. Random Forests. Machine Learning 45, 1 (2001), 5--32. DOI: http://dx.doi.org/10.1023/A:1010933404324Google ScholarDigital Library
- David S. Broomhead and David Lowe. 1988. Multivariable Functional Interpolation and Adaptive Networks. Complex Systems 2, 3 (1988).Google Scholar
- Ali Darwish and Michel Pasquier. 2013. Biometric identification using the dynamic features of the eyes. In IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013, Arlington, VA, USA, Sept. 29 - Oct. 2, 2013. 1--6. DOI: http://dx.doi.org/10.1109/BTAS.2013.6712724Google ScholarCross Ref
- Ali Alhaj Darwish. 2013. Biometric Identification Based on Eye Movements and Iris Features Using Task-Driven and Task-Independent Stimuli. Master's thesis. American University of Sharjah.Google Scholar
- Nastaran Maus Esfahani. 2016. A Brief Review of Human Identification Using Eye Movement. Journal of Pattern Recognition Research 11, 1 (2016), 15--24. DOI: http://dx.doi.org/10.13140/RG.2.1.3466.3924Google ScholarCross Ref
- Lee Friedman, Mark S. Nixon, and Oleg V. Komogortsev. 2017. Method to assess the temporal persistence of potential biometric features: Application to oculomotor, gait, face and brain structure databases. PLOS ONE 12, 6 (06 2017), 1--42. DOI: http://dx.doi.org/10.1371/journal.pone.0178501Google ScholarCross Ref
- Chiara Galdi and Michele Nappi. 2019. Eye Movement Analysis in Biometrics. Springer Singapore, Singapore, 171--183. DOI: http://dx.doi.org/10.1007/978--981--13--1144--4_8Google ScholarCross Ref
- Chiara Galdi, Michele Nappi, Daniel Riccio, and Harry Wechsler. 2016. Eye movement analysis for human authentication: a critical survey. Pattern Recognition Letters 84 (2016), 272--283. DOI: http://dx.doi.org/10.1016/j.patrec.2016.11.002Google ScholarDigital Library
- Anjith George and Aurobinda Routray. 2016. A score level fusion method for eye movement biometrics. Pattern Recognition Letters 82 (2016), 207--215. DOI: http://dx.doi.org/10.1016/j.patrec.2015.11.020Google ScholarDigital Library
- Tin Kam Ho. 1995. Random decision forests. In Third International Conference on Document Analysis and Recognition, ICDAR 1995, August 14 - 15, 1995, Montreal, Canada. Volume I. 278--282. DOI: http://dx.doi.org/10.1109/ICDAR.1995.598994Google ScholarCross Ref
- Corey Holland and Oleg V. Komogortsev. 2011. Biometric identification via eye movement scanpaths in reading. In 2011 IEEE International Joint Conference on Biometrics, IJCB 2011, Washington, DC, USA, Oct. 11--13, 2011. 1--8. DOI: http://dx.doi.org/10.1109/IJCB.2011.6117536Google ScholarDigital Library
- Corey D. Holland and Oleg V. Komogortsev. 2012. Biometric verification via complex eye movements: The effects of environment and stimulus. In IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012, Arlington, VA, USA, September 23--27, 2012. 39--46. DOI: http://dx.doi.org/10.1109/BTAS.2012.6374556Google ScholarCross Ref
- Tilke Judd, Krista A. Ehinger, Frédo Durand, and Antonio Torralba. 2009. Learning to predict where humans look. In IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, Sept. 27 - Oct. 4, 2009. 2106--2113. DOI: http://dx.doi.org/10.1109/ICCV.2009.5459462Google ScholarCross Ref
- Lukasz Kaiser, Aidan N. Gomez, Noam Shazeer, Ashish Vaswani, Niki Parmar, Llion Jones, and Jakob Uszkoreit. 2017. One Model To Learn Them All. arXiv:1706.05137 (2017). http://arxiv.org/abs/1706.05137Google Scholar
- Pawel Kasprowski, Oleg V. Komogortsev, and Alex Karpov. 2012. First eye movement verification and identification competition at BTAS 2012. In IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012, Arlington, VA, USA, September 23--27, 2012. 195--202. DOI: http://dx.doi.org/10.1109/BTAS.2012.6374577Google ScholarCross Ref
- Pawel Kasprowski and Józef Ober. 2004. Eye Movements in Biometrics. In Biometric Authentication, ECCV 2004 International Workshop, BioAW 2004, Prague, Czech Republic, May 15, 2004, Proceedings. 248--258. DOI: http://dx.doi.org/10.1007/978--3--540--25976--3_23Google ScholarCross Ref
- Tomi Kinnunen and Haizhou Li. 2010. An overview of text-independent speaker recognition: From features to supervectors. Speech Communication 52, 1 (2010), 12--40. DOI: http://dx.doi.org/10.1016/j.specom.2009.08.009Google ScholarDigital Library
- Tomi Kinnunen, Filip Sedlak, and Roman Bednarik. 2010. Towards task-independent person authentication using eye movement signals. In Proceedings of the 2010 Symposium on Eye-Tracking Research & Applications, ETRA 2010, Austin, Texas, USA, March 22--24, 2010. 187--190. DOI: http://dx.doi.org/10.1145/1743666.1743712Google ScholarDigital Library
- Anneli Olsen and Ricardo Matos. 2012. Identifying parameter values for an I-VT fixation filter suitable for handling data sampled with various sampling frequencies. In Proceedings of the 2012 Symposium on Eye-Tracking Research and Applications, ETRA 2012, Santa Barbara, CA, USA, March 28--30, 2012. 317--320. DOI: http://dx.doi.org/10.1145/2168556.2168625Google ScholarDigital Library
- Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, and others. 2011. Scikit-learn: Machine learning in Python. Journal of machine learning research 12, Oct (2011), 2825--2830.Google ScholarDigital Library
- Ken Pfeuffer, Matthias J. Geiger, Sarah Prange, Lukas Mecke, Daniel Buschek, and Florian Alt. 2019. Behavioural Biometrics in VR: Identifying People from Body Motion and Relations in Virtual Reality. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI '19). ACM, NY, NY, USA, Article 110, 12 pages. DOI: http://dx.doi.org/10.1145/3290605.3300340Google ScholarDigital Library
- Ioannis Rigas and Oleg V. Komogortsev. 2017. Current research in eye movement biometrics: An analysis based on BioEye 2015 competition. Image Vision Comput. 58 (2017), 129--141. DOI: http://dx.doi.org/10.1016/j.imavis.2016.03.014Google ScholarDigital Library
- Dario D. Salvucci and Joseph H. Goldberg. 2000. Identifying fixations and saccades in eye-tracking protocols. In Proceedings of the Eye Tracking Research & Application Symposium, ETRA 2000, Palm Beach Gardens, Florida, USA, November 6--8, 2000. 71--78. DOI: http://dx.doi.org/10.1145/355017.355028Google ScholarDigital Library
Index Terms
- Robustness of Eye Movement Biometrics Against Varying Stimuli and Varying Trajectory Length
Recommendations
Current research in eye movement biometrics: An analysis based on BioEye 2015 competition
AbstractOn the onset of the second decade of research in eye movement biometrics, the already demonstrated results strongly support the promising perspectives of the field. This paper presents a description of the research conducted in eye ...
Highlights- We present a review of the state-of-the-art in eye movement biometrics.
- We ...
Towards a multi-source fusion approach for eye movement-driven recognition
We investigate the effects of multi-source fusion in the field of eye movement biometrics.We introduce the concept of multi-stimulus fusion.We suggest a weighted fusion scheme based on stimulus-specific and algorithm-specific weights.The proposed weight-...
Eye Movement Biometrics on Wearable Devices: What Are the Limits?
CHI EA '16: Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing SystemsThis paper presents a study of the perspectives of eye tracking on wearable devices and their use to perform eye movement biometrics. In such devices, the reduction in power consumption is very important, and can be partially achieved by reducing the ...
Comments