This book focuses on how machine learning techniques can be used to analyze and make use of one particular category of behavioral biometrics known as the gait biometric. A comprehensive Ground Reaction Force (GRF)-based Gait Biometrics Recognition framework is proposed and validated by experiments. In addition, an in-depth analysis of existing recognition techniques that are best suited for performing footstep GRF-based person recognition is also proposed, as well as a comparison of feature extractors, normalizers, and classifiers configurations that were never directly compared with one another in any previous GRF recognition research. Finally, a detailed theoretical overview of many existing machine learning techniques is presented, leading to a proposal of two novel data processing techniques developed specifically for the purpose of gait biometric recognition using GRF. This book
· introduces novel machine-learning-based temporal normalization techniques
· bridges research gaps concerning the effect of footwear and stepping speed on footstep GRF-based person recognition
· provides detailed discussions of key research challenges and open research issues in gait biometrics recognition· compares biometrics systems trained and tested with the same footwear against those trained and tested with different footwear
|
1 Introduction to Gait Biometrics |
|
|
1 | (8) |
|
|
|
1 | (2) |
|
|
|
3 | (2) |
|
1.3 Summary of Contributions |
|
|
5 | (1) |
|
|
|
5 | (1) |
|
|
|
5 | (1) |
|
|
|
5 | (1) |
|
|
|
6 | (3) |
|
|
|
6 | (3) |
|
2 Gait Biometric Recognition |
|
|
9 | (28) |
|
2.1 Introduction to Machine Learning |
|
|
9 | (7) |
|
2.1.1 Machine Learning Paradigm |
|
|
9 | (1) |
|
2.1.2 Machine Learning Design Cycle |
|
|
10 | (6) |
|
2.2 General Principles of Designing Gait Biometric-Based Systems |
|
|
16 | (6) |
|
2.3 Authentication Using the Gait Biometric |
|
|
22 | (10) |
|
2.3.1 Privacy and Security Implications of Gait Biometrics |
|
|
23 | (1) |
|
2.3.2 Gait Biometric Approaches |
|
|
24 | (8) |
|
|
|
32 | (5) |
|
|
|
33 | (4) |
|
3 Gait Biometric Recognition Using the Footstep Ground Reaction Force |
|
|
37 | (16) |
|
3.1 The Ground Reaction Force |
|
|
37 | (5) |
|
|
|
42 | (2) |
|
|
|
44 | (1) |
|
3.4 Classification Approaches |
|
|
45 | (3) |
|
|
|
48 | (1) |
|
3.6 The Demonstrative Experiment |
|
|
49 | (1) |
|
|
|
50 | (3) |
|
|
|
50 | (3) |
|
|
|
53 | (36) |
|
|
|
53 | (11) |
|
|
|
64 | (8) |
|
|
|
72 | (6) |
|
|
|
78 | (7) |
|
|
|
85 | (4) |
|
|
|
86 | (3) |
|
|
|
89 | (22) |
|
|
|
90 | (4) |
|
|
|
94 | (5) |
|
|
|
99 | (10) |
|
|
|
109 | (2) |
|
|
|
110 | (1) |
|
|
|
111 | (46) |
|
|
|
112 | (4) |
|
6.2 Multilayer Perceptron Neural Network |
|
|
116 | (6) |
|
6.3 Support Vector Machine |
|
|
122 | (10) |
|
6.4 Linear Discriminant Analysis |
|
|
132 | (13) |
|
6.5 Least Square Probabilistic Classifier |
|
|
145 | (8) |
|
|
|
153 | (4) |
|
|
|
154 | (3) |
|
7 Experimental Design and Dataset |
|
|
157 | (18) |
|
7.1 Evaluation of Gait Biometric-Based Systems |
|
|
157 | (4) |
|
|
|
161 | (6) |
|
7.2.1 Recognition Techniques |
|
|
162 | (1) |
|
7.2.2 Experimental Biometric System |
|
|
163 | (2) |
|
|
|
165 | (2) |
|
|
|
167 | (4) |
|
|
|
171 | (4) |
|
|
|
172 | (3) |
|
|
|
175 | (14) |
|
|
|
175 | (4) |
|
8.2 Stepping Speed Normalization |
|
|
179 | (4) |
|
|
|
183 | (5) |
|
|
|
188 | (1) |
|
|
|
188 | (1) |
|
|
|
189 | (14) |
|
|
|
189 | (6) |
|
|
|
190 | (1) |
|
|
|
191 | (2) |
|
|
|
193 | (2) |
|
9.2 Considerations and Implications |
|
|
195 | (3) |
|
|
|
196 | (1) |
|
|
|
196 | (1) |
|
|
|
197 | (1) |
|
9.3 Potential Improvements |
|
|
198 | (2) |
|
|
|
199 | (1) |
|
|
|
199 | (1) |
|
|
|
200 | (1) |
|
|
|
200 | (3) |
|
|
|
201 | (2) |
|
10 Applications of Gait Biometrics |
|
|
203 | (6) |
|
|
|
203 | (1) |
|
|
|
204 | (1) |
|
10.3 Gait Biometric Methods in Commercial Use and Research and Development |
|
|
205 | (2) |
|
10.4 Integration of Gait Biometrics with Other Biometrics or Technologies |
|
|
207 | (2) |
|
|
|
207 | (2) |
|
11 Conclusion and Remarks |
|
|
209 | (8) |
|
|
|
209 | (3) |
|
|
|
212 | (5) |
|
11.2.1 Gait Biometric Trends and Challenges |
|
|
212 | (2) |
|
11.2.2 Advances in Biometric Gait Recognition |
|
|
214 | (1) |
|
|
|
215 | (2) |
| Appendix: Experiment Code Library |
|
217 | (2) |
| Index |
|
219 | |
James Eric Mason obtained his BSEng and MASc from the University of Victoria, Canada, in 2009 and 2014, respectively. During his Masters program, under the supervision of Dr. Issa Traore, his research focused primarily on biometric security solutions with a particular emphasis on the gait biometric. In 2014 he completed his thesis titled Examining the impact of Normalization and Footwear on Gait Biometrics Recognition using the Ground Reaction Force, which served as an inspiration for the work presented in this book. His research interests include biometric security, machine learning, software engineering, web development, and weather/climate sciences. Since 2011, he has been working with the software startup Referral SaaSquatch as a full stack software developer.
Issa Traore obtained a PhD in Software Engineering in 1998 from Institute Nationale Polytechnique (INPT)-LAAS/CNRS, Toulouse, France. He has been with the faculty of the Department of Electrical and Computer Engineering of the University of Victoria since 1999. He is currently a Full Professor and the Coordinator of the Information Security and object Technology (ISOT) Lab at the University of Victoria. His research interests include biometrics technologies, computer intrusion detection, network forensics, software security, and software quality engineering. He is currently serving as Associate Editor for the International Journal of Communication Systems (IJCS) and the International Journal of Communication Networks and Distributed Systems (IJCNDS). Dr. Traore is also a co-founder and Chief Scientist of Plurilock Security Solutions Inc., a network security company which provides innovative authentication technologies, and is one of the pioneers in bringing behavioral biometric authentication products to the market.
Isaac Woungang received his M.Sc. & Ph.D degrees, all in Mathematics, from the University of Aix Marseille II, France, and University of South, Toulon and Var, France, in 1990 and 1994 respectively. In 1999, he received a MSc degree from the INRS-Materials and Telecommunications, University of Quebec, Montreal, QC, Canada. From 1999 to 2002, he worked as a software engineer at Nortel Networks, Ottawa, Canada, in the Photonic Line Systems Group. Since 2002, he has been with Ryerson University, where he is now a full professor of Computer Science and Director of the Distributed Applications and Broadband (DABNEL) Lab. His current research interests include radio resource management in next generation wireless networks, biometrics technologies, network security. Dr. Woungang has published 8 books and over 89 refereed technical articles in scholarly international journals and proceedings of international conferences. He has served as Associate Editor of the Computers and Electrical Engineering (Elsevier), and the International Journal of Communication Systems (Wiley). He has Guest Edited several Special Issues withvarious reputed journals such as IET Information Security, Mathematical and Computer Modeling (Elsevier), Computer Communications (Elsevier), Computers and Electrical Engineering (Elsevier), and Telecommunication Systems (Springer). Since January 2012, He serves as Chair of Computer Chapter, IEEE Toronto Section.
Biežāk uzdotie jautājumi par e-grāmatām