Try Walking in My Shoes, if You Can: Accurate Gait Recognition Through Deep Learning

Human gait seamless continuous authentication, based on wearable accelerometers, is a novel biometric instrument which can be exploited to identify the user of mobile and wearable devices. In this paper, we present a study on recognition of user identity, by analysis of gait data, collected through body inertial sensors from 175 different users. The mechanism used for identity recognition is based on deep learning machinery, specifically on a convolutional network, trained with readings from different sensors, and on filtering and buffering mechanism to increase the accuracy. Results show a very high accuracy in both recognizing known and unknown identities.

[1]  Ausif Mahmood,et al.  Improved Gait recognition based on specialized deep convolutional neural networks , 2015, 2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).

[2]  E. van Vollenhoven,et al.  Transient Response of Butterworth Filters , 1965 .

[3]  Bruno Crispo,et al.  Hold and Sign: A Novel Behavioral Biometrics for Smartphone User Authentication , 2016, 2016 IEEE Security and Privacy Workshops (SPW).

[4]  Zhaohui Wu,et al.  Accelerometer-Based Gait Recognition by Sparse Representation of Signature Points With Clusters , 2015, IEEE Transactions on Cybernetics.

[5]  Jie Yang,et al.  User Verification Leveraging Gait Recognition for Smartphone Enabled Mobile Healthcare Systems , 2015, IEEE Transactions on Mobile Computing.

[6]  Qingquan Li,et al.  Robust Gait Recognition by Integrating Inertial and RGBD Sensors , 2016, IEEE Transactions on Cybernetics.

[7]  Manuel J. Marín-Jiménez,et al.  Automatic Learning of Gait Signatures for People Identification , 2016, IWANN.

[8]  Huiru Zheng,et al.  iGAIT: An interactive accelerometer based gait analysis system , 2012, Comput. Methods Programs Biomed..

[9]  Yasushi Makihara,et al.  View Transformation Model Incorporating Quality Measures for Cross-View Gait Recognition , 2016, IEEE Transactions on Cybernetics.

[10]  Einar Snekkenes,et al.  User authentication based on foot motion , 2011, Signal Image Video Process..

[11]  Zhaohui Wu,et al.  SmartShadow: Models and Methods for Pervasive Computing , 2013, Advanced Topics in Science and Technology in China.

[12]  Matjaz B. Juric,et al.  Inertial Sensor-Based Gait Recognition: A Review , 2015, Sensors.

[13]  Fabio Martinelli,et al.  Modeling Privacy Aware Information Sharing Systems: A Formal and General Approach , 2016, 2016 IEEE Trustcom/BigDataSE/ISPA.

[14]  John A. Stuller,et al.  Linear interpolation lattice , 1991, IEEE Trans. Signal Process..

[15]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[16]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[17]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[18]  Tardi Tjahjadi,et al.  Robust view-invariant multiscale gait recognition , 2015, Pattern Recognit..

[19]  M. Nixon,et al.  Automated Human Recognition by Gait using Neural Network , 2008, 2008 First Workshops on Image Processing Theory, Tools and Applications.