Autoassociative Signature Authentication Based on Recurrent Neural Network
In online handwriting authentication, it is difficult to forge handwriting because stroke characteristics cannot be reproduced using only a handwriting trajectory. However, it is difficult to completely reproduce registered stroke characteristics, even when signers attempt to reproduce their own signatures. For this reason, the principal criteria for authentication must be lowered. In this study, we use a recurrent neural network to model the behavior of the musculoskeletal function for handwriting. The proposed model can represent the handwriting stroke process for a character visualized by the authenticator. This research is an anti-counterfeit effort to reduce the error between autoassociative stroke information and handwriting stroke information.
KeywordsOnline handwriting authentication Recurrent neural network BPTT
In this research, I would like to thank S. Sugawara for receiving great advice on data collection and RNN construction.
- 3.Tsukamoto, M., Kaneoya, T., Mano, W.: Verification of humans using the Musculo-Skeletal model with electromyograms. J. IEICE J J97–A(11), 672–682 (2014)Google Scholar
- 6.Taguchi, H., Fujii, K.: A functional description of brain mechanics in the writing movement control. J. IEICE J70–D(3), 640–649 (1987)Google Scholar
- 7.Fukuda, O., Tsuji, T., Bu, N., Kaneko, M.: Pattern discrimination of time series EEG signals using a recurrent neural network. In: Proceedings of Artificial Intelligence and Soft Computing, pp. 450–455 (2002)Google Scholar
- 9.Nakai, M., Akira, N., Shimodaira, H., Sagayama, S.: Substroke approach to HMM-based on-line Kanji handwriting recognition. In: Proceedings of Sixth International Conference on Document Analysis and Recognition, pp. 491–495 (2001)Google Scholar
- 11.Pham, V., Bluche, T., Kermorvant, C., Louradour, J.: Dropout improves recurrent neural networks for handwriting recognition. In: Proceedings of 14th International Conference on Frontiers in Handwriting Recognition, pp. 285–290 (2014)Google Scholar
- 12.Wei, W., Guanglai, G.: Online handwriting Mongolia words recognition with recurrent neural networks. In: Proceedings of Fourth International Conference on Computer Sciences and Convergence Information Technology, pp. 165–167 (2009)Google Scholar
- 13.Goh, W.L., Mital, D.P., Babri, H.A.: An artificial neural network approach to handwriting recognition. In: Proceedings of Knowledge-Based Intelligent Electronic Systems vol.1, pp. 132–136 (1997)Google Scholar
- 14.Doetsch, P., Germany, A., Kozielski, M., Ney, H.: Fast and robust training of recurrent neural networks for offline handwriting recognition. In: Proceedings of 14th International Conference on Frontiers in Handwriting Recognition, pp. 279–284 (2014)Google Scholar