Deep multi-task learning for gait-based biometrics

The task of identifying people by the way they walk is known as ‘gait recognition’. Although gait is mainly used for identification, additional tasks as gender recognition or age estimation may be addressed based on gait as well. In such cases, traditional approaches consider those tasks as independent ones, defining separated task-specific features and models for them. This paper shows that by training jointly more than one gait-based tasks, the identification task converges faster than when it is trained independently, and the recognition performance of multi-task models is equal or superior to more complex single-task ones. Our model is a multi-task CNN that receives as input a fixed-length sequence of optical flow channels and outputs several biometric features (identity, gender and age).

[1]  P. KaewTrakulPong,et al.  An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection , 2002 .

[2]  Frans Coenen,et al.  Multi-attributes gait identification by convolutional neural networks , 2015, 2015 8th International Congress on Image and Signal Processing (CISP).

[3]  Gunnar Farnebäck,et al.  Two-Frame Motion Estimation Based on Polynomial Expansion , 2003, SCIA.

[4]  Nassir Navab,et al.  Robust Optimization for Deep Regression , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[5]  Thomas Wolf,et al.  Multi-view gait recognition using 3D convolutional neural networks , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[6]  Manuel J. Marín-Jiménez,et al.  Multimodal features fusion for gait, gender and shoes recognition , 2016, Machine Vision and Applications.

[7]  Xiaoou Tang,et al.  Facial Landmark Detection by Deep Multi-task Learning , 2014, ECCV.

[8]  Rafael Muñoz-Salinas,et al.  Fisher Motion Descriptor for Multiview Gait Recognition , 2016, Int. J. Pattern Recognit. Artif. Intell..

[9]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[12]  Michael J. Black,et al.  On the unification of line processes, outlier rejection, and robust statistics with applications in early vision , 1996, International Journal of Computer Vision.

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

[14]  Rich Caruana,et al.  Multitask Learning , 1997, Machine-mediated learning.

[15]  Xiaogang Wang,et al.  A Comprehensive Study on Cross-View Gait Based Human Identification with Deep CNNs , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Chang-Tsun Li,et al.  A robust speed-invariant gait recognition system for walker and runner identification , 2013, 2013 International Conference on Biometrics (ICB).

[17]  Shaogang Gong,et al.  Gait recognition without subject cooperation , 2010, Pattern Recognit. Lett..

[18]  Björn W. Schuller,et al.  The TUM Gait from Audio, Image and Depth (GAID) database: Multimodal recognition of subjects and traits , 2014, J. Vis. Commun. Image Represent..

[19]  Bir Bhanu,et al.  Individual recognition using gait energy image , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.