Using Hidden Markov Models for accelerometer-based biometric gait recognition

Biometric gait recognition based on accelerometer data is still a new field of research. It has the merit of offering an unobtrusive and hence user-friendly method for authentication on mobile phones. Most publications in this area are based on extracting cycles (two steps) from the gait data which are later used as features in the authentication process. In this paper the application of Hidden Markov Models is proposed instead. These have already been successfully implemented in speaker recognition systems. The advantage is that no error-prone cycle extraction has to be performed, but the accelerometer data can be directly used to construct the model and thus form the basis for successful recognition. Testing this method with accelerometer data of 48 subjects recorded using a commercial of the shelve mobile phone a false non match rate (FNMR) of 10.42% at a false match rate (FMR) of 10.29% was obtained. This is half of the error rate obtained when applying an advanced cycle extraction method to the same data set in previous work.

[1]  Alex Bateman,et al.  An introduction to hidden Markov models. , 2007, Current protocols in bioinformatics.

[2]  Horst Bunke,et al.  Using HMM based recognizers for writer identification and verification , 2004, Ninth International Workshop on Frontiers in Handwriting Recognition.

[3]  Gary M. Weiss,et al.  Cell phone-based biometric identification , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[4]  Andrew J. Viterbi,et al.  Error bounds for convolutional codes and an asymptotically optimum decoding algorithm , 1967, IEEE Trans. Inf. Theory.

[5]  Shie Mannor,et al.  Activity and Gait Recognition with Time-Delay Embeddings , 2010, AAAI.

[6]  S. Sprager,et al.  A cumulant-based method for gait identification using accelerometer data with principal component analysis and support vector machine , 2009 .

[7]  Davrondzhon Gafurov,et al.  Performance and security analysis of Gait-based user authentication , 2008 .

[8]  Steve Young,et al.  The HTK book version 3.4 , 2006 .

[9]  Mikko Lindholm,et al.  Identifying people from gait pattern with accelerometers , 2005, SPIE Defense + Commercial Sensing.

[10]  Liu Ming,et al.  Identification of Individual Walking Patterns Using Gait Acceleration , 2007, 2007 1st International Conference on Bioinformatics and Biomedical Engineering.

[11]  Francisco Casacuberta,et al.  An off-line HTK-based OCR system for isolated handwritten lowercase letters , 2001 .

[12]  Davrondzhon Gafurov,et al.  A Survey of Biometric Gait Recognition: Approaches, Security and Challenges , 2007 .

[13]  Claudia Nickel,et al.  User Survey on Phone Security and Usage , 2010, BIOSIG.

[14]  Christoph Busch,et al.  Unobtrusive User-Authentication on Mobile Phones Using Biometric Gait Recognition , 2010, 2010 Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[15]  Steve Young,et al.  The HTK hidden Markov model toolkit: design and philosophy , 1993 .

[16]  Alex Pentland,et al.  Real-time American Sign Language recognition from video using hidden Markov models , 1995 .

[17]  Mark S. Nixon,et al.  A floor sensor system for gait recognition , 2005, Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID'05).

[18]  Thad Starner,et al.  Visual Recognition of American Sign Language Using Hidden Markov Models. , 1995 .

[19]  Heiga Zen,et al.  The HMM-based speech synthesis system (HTS) version 2.0 , 2007, SSW.

[20]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[21]  L. Baum,et al.  Statistical Inference for Probabilistic Functions of Finite State Markov Chains , 1966 .