An Exploratory Study of Biometrics using Trajectory Images of Eye Movements collected by Natural Image as Stimuli

• Antonio Ricardo Alexandre Brasil IFES
• Luiz Alberto Pinto IFES
• Karin Satie Komati IFES

DOI: https://doi.org/10.5753/sbseg_estendido.2020.19268

Abstract

The study of eye movements as biometrics began in 2004 and its typical process is to capture movements using stimulus images, treating these data as signals in time followed by classification. This work proposes two differentials, one is the use of the DOVES database of eye movements collected using natural images as a stimulus, and the other is the treatment of eye movements as images. Images of the eye movement trajectories are generated, which are the input of two types of architectures: one which uses the HOG and LBP techniques for extracting characteristics, followed by the SVM, MLP, and random forest classifiers and other which uses the power of Convolutional Neural Network (CNN) VGG-19 and ResNet-50 for person identification. The highest accuracy was 39.59% with the ResNet-50 architecture, a result comparable with the best of EMVIC 2014 competition, which used face images as a stimulus, of 39.63%.

References

Bednarik, R., Kinnunen, T., Mihaila, A., and Fränti, P. (2005). Eye-movements as a biometric. Image analysis, pages 16–26.

Brasil, A. R. A., Andrade, J. O., and Komati, K. S. (2020a). Eye movements biometrics: A bibliometric analysis from 2004 to 2019. International Journal of Computer Applications, 176(24):1–9.

Brasil, A. R. A., Andrade, J. O., Pinto, L. A., and Komati, K. S. (2020b). An exploratory study of biometrics using eye movement trajectory images collected by natural image stimuli. In Anais da XLVII edição do Seminário Integrado de Software e Hardware, pages 25–36, Porto Alegre, RS, Brasil. SBC.

Brasil, A. R. A., Pinto, L. A., and Komati, K. S. (2018). Predição da tendência de valorização do bitcoin usando técnicas de aprendizado de máquina. In Anais Estendidos do XIV Simpósio Brasileiro de Sistemas de Informação, pages 126–128. SBC.

Brasil, A. R. A., Pinto, L. A., and Komati, K. S. (2019). Comparação de técnicas de Aprendizado de máquina na Predição da Tendência de Valorização da BITCOIN. In Information Systems and Technology Management, pages 244–254. Antonella Carvalho de Oliveira.

Brownlee, J. (2017). A gentle introduction to transfer learning for deep learning.

Ceravolo, I. A., Brasil, A. R. A., and Komati, K. S. (2019). Classificação de dislexia a partir de movimentos oculares durante a leitura usando aprendizado de máquina e wavelets. In Anais do XVI Encontro Nacional de Inteligência Artificial e Computacional, pages 880–891. SBC.

Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, volume 1, pages 886–893. IEEE.

Gama, J., Faceli, K., Lorena, A. C., and De Carvalho, A. C. P. L. F. (2011). Inteligência artificial. LTC, Rio de Janeiro.

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.

Holland, C. and Komogortsev, O. V. (2011). Biometric identification via eye movement scanpaths in reading. In 2011 International joint conference on biometrics (IJCB), pages 1–8. IEEE.

Jain, A. K., Flynn, P., and Ross, A. A. (2007). Handbook of biometrics. Springer Science & Business Media.

Kasprowski, P. (2004). Human identification using eye movements. Institute of Computer Science.

Kasprowski, P. and Harezlak, K. (2014). The second eye movements verification and identification competition. In Biometrics (IJCB), 2014 IEEE International Joint Conference on, pages 1–6. IEEE.

Komogortsev, O. V., Jayarathna, S., Aragon, C. R., and Mahmoud, M. (2010). Biometric identification via an oculomotor plant mathematical model. In Proceedings of the 2010 Symposium on Eye-Tracking Research & Applications, pages 57–60. ACM.

Li, C., Xue, J., Quan, C., Yue, J., and Zhang, C. (2018). Biometric recognition via texture features of eye movement trajectories in a visual searching task. PloS one, 13(4):e0194475.

Ojala, T., Pietikainen, M., and Maenpaa, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on pattern analysis and machine intelligence, 24(7):971–987.

Rigas, I., Economou, G., and Fotopoulos, S. (2012). Biometric identification based on the eye movements and graph matching techniques. Pattern Recognition Letters, 33(6):786–792.

Rigas, I., Friedman, L., and Komogortsev, O. (2018). Study of an extensive set of eye movement features: Extraction methods and statistical analysis. Journal of Eye Movement Research, 11(1):3.

Rigas, I. and Komogortsev, O. V. (2014a). Biometric recognition via fixation density maps. In Biometric and Surveillance Technology for Human and Activity Identification XI, volume 9075, page 90750M. International Society for Optics and Photonics.

Rigas, I. and Komogortsev, O. V. (2014b). Biometric recognition via probabilistic spatial projection of eye movement trajectories in dynamic visual environments. IEEE Transactions on Information Forensics and Security, 9(10):1743–1754.

Rigas, I. and Komogortsev, O. V. (2017). Current research in eye movement biometrics: An analysis based on BioEye 2015 competition. Image and Vision Computing, 58:129–141.

Rodrigues, D. S., Brasil, A. R. A., Costa, M. B., Komati, K. S., and Pinto, L. A. (2018). A comparative analysis of loan requests classification algorithms in a peer-to-peer lending platform. In Proceedings of the XIV Brazilian Symposium on Information Systems, page 42. ACM.

Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115(3):211–252.

Saeed, K. (2016). New directions in behavioral biometrics. CRC Press.

Van Der Linde, I., Rajashekar, U., Bovik, A. C., and Cormack, L. K. (2009). Doves: a database of visual eye movements. Spatial vision, 22(2):161–177.