A Conversive Hidden Non-Markovian Model Approach for 2D and 3D Online Movement Trajectory Verification

A novel approach for stochastically modelling movement trajectories is presented that has already been implemented and evaluated for classification scenarios in previous research and in this article its applicability to verification scenarios is analysed. The models are based on Conversive Hidden non-Markovian Models that are especially suited to mimic temporal dynamics of time series. In contrast to the popular Hidden Markov Models (HMM) and the dynamic time warping (DTW) method, timestamp information of the data is an integral part. A verification system is presented that create trajectory models from several examples and its verification performance is deduced from experiments on different data sets including signatures, doodles, pseudo-signatures and hand gestures recorded with a Kinect. The results are compared to other publications and they reveal that the developed system already performs similar to a general DTW approach, but expectedly does not yet reach the quality of specialized HMM systems. It is also shown that the system can be applied to three dimensional data and further possibilities to improve the results are discussed.

[1]  Wenyuan Xu,et al.  KinWrite: Handwriting-Based Authentication Using Kinect , 2013, NDSS.

[2]  Berrin A. Yanikoglu,et al.  Identity authentication using improved online signature verification method , 2005, Pattern Recognit. Lett..

[3]  Graham Horton,et al.  Evaluating a New Conversive Hidden non-Markovian Model Approach for Online Movement Trajectory Verification , 2017, ICPRAM.

[4]  Gernot A. Fink,et al.  Markov Models for Pattern Recognition: From Theory to Applications , 2007 .

[5]  Graham Horton,et al.  An improved conversive hidden non-markovian model-based touch gesture recognition system with automatic model creation , 2015 .

[6]  Berrin A. Yanikoglu,et al.  SUSIG: an on-line signature database, associated protocols and benchmark results , 2008, Pattern Analysis and Applications.

[7]  Julian Fiérrez,et al.  HMM-based on-line signature verification: Feature extraction and signature modeling , 2007, Pattern Recognit. Lett..

[8]  Julian Fiérrez,et al.  The DooDB Graphical Password Database: Data Analysis and Benchmark Results , 2013, IEEE Access.

[9]  Gernot A. Fink,et al.  Markov Models for Pattern Recognition , 2014, Advances in Computer Vision and Pattern Recognition.

[10]  Takashi Matsumoto,et al.  An HMM online signature verifier incorporating signature trajectories , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[11]  Marcos Faúndez-Zanuy,et al.  On-line signature recognition based on VQ-DTW , 2007, Pattern Recognit..

[12]  Julian Fiérrez,et al.  Mobile signature verification: feature robustness and performance comparison , 2014, IET Biom..

[13]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[14]  Graham Horton,et al.  Using conversive hidden non-markovian models for multi-touch gesture recognition , 2013 .

[15]  Juan J. Igarza,et al.  MCYT baseline corpus: a bimodal biometric database , 2003 .