ICB 2019

Abstract

Human identification at a distance is a very challenging task, which has long been a popular research topic in the field of computer vision. The gait sequences of different people can be very distinctive, which makes gait an important body characteristic that can be used for human identification. The tutorial will include the challenging problems in gait recognition, such as benchmarks, segmentation, feature representation, recognition. We also will introduce the history, the recent progress and the trend in gait recognition.

Outline

• Introduction and overview of the tutorial: motivations, challenges, available gait datasets.
• A comprehensive survey on the whole pipeline of gaitbased human identification.
• Robust feature extraction on CNN, AE and GAN for gait recognition to solve view and other variations.
• Intensity metric learning for gait recognition. Gait energy response function and joint intensity and spatial metric learning approaches for clothing and carrying status conditions are introduced.
• Construction of large-scale gait databases with over 60,000 subjects using an automatic gait data collection system in conjunction with experience-based long-run exhibition.
• Application of gait verification systems to criminal investigation.
• Open questions and discussion.

Biography

Prof. Shiqi Yu

shiqi.yu@szu.edu.cn

Associate Professor in the College of Computer Science and Software Engineering, Shenzhen University, China.

Shiqi Yu received his B.E. degree in computer science and engineering from the Chu Kochen Honors College, Zhejiang University in 2002, and Ph.D. degree in pattern recognition and intelligent systems from the Institute of Automation, Chinese Academy of Sciences in 2007. He worked as an assistant professor and then as an associate professor in the Shenzhen Institutes of Advanced Technology, Chinese Academy of Science from 2007 to 2010. Currently, he is an associate professor in the College of Computer Science and Software Engineering, Shenzhen University, China. He is the member of the council of China Society of Image and Graphics, and served as the program chair of the 12th Chinese Conference on Biometric Recognition 2017, and the organization chair of the IAPR/IEEE Winter School on Biometrics 2018 and 2019. He especially focuses on gait recognition since 2003.

Prof. Yasushi Makihara

makihara@am.sanken.osaka-u.ac.jp

Associate Professor in the Institute of Scientific and Industrial Research, Osaka University, Japan.

Yasushi Makihara received the B.S., M.S., and Ph.D. degrees in Engineering from Osaka University in 2001, 2002, and 2005, respectively. He is currently an Associate Professor of the Institute of Scientific and Industrial Research, Osaka University. His research interests are computer vision, pattern recognition, and image processing including gait recognition, pedestrian detection, morphing, and temporal super resolution. He is a member of IPSJ, IEICE, RSJ, and JSME. He has obtained several honors and awards, including the 2nd Int. Workshop on Biometrics and Forensics (IWBF 2014), IAPR Best Paper Award, the 9th IAPR Int. Conf. on Biometrics (ICB 2016), Honorable Mention Paper Award, the 28th British Machine Vision Conf. (BMVC 2017), Outstanding Reviewers, the 11th IEEE Int. Conf. on Automatic Face and Gesture Recognition (FG 2015), Outstanding Reviewers, and the 30th IEEE Conf. on Computer Vision and Pattern Recognition (CVPR 2017), Outstanding Reviewers. He has served as an associate editor of IPSJ Transactions on Computer Vision and Applications (CVA), a program co-chair of the 4th Asian Conf. on Pattern Recognition (ACPR 2017), and reviewers of CVPR, ICCV, ECCV, ACCV, ICPR, FG, etc.

Prof. Daigo Muramatsu

muramatsu@am.sanken.osaka-u.ac.jp

Associate Professor in the Institute of Scientific and Industrial Research, Osaka University, Japan.

Daigo Muramatsu received the B.S., M.E., and Ph.D. degrees in electrical, electronics, and computer engineering from Waseda University, Tokyo, Japan, in 1997, 1999, and 2006, respectively. He is currently an Associate Professor of The Institute of Scientific and Industrial Research, Osaka University. His current research interests include gait recognition, signature verification, and biometric fusion. He is a member of the IEEE, IEICE, and the IPSJ. He has obtained several honors and awards, including the 2nd Int. Workshop on Biometrics and Forensics (IWBF 2014), IAPR Best Paper Award, the 9th IAPR Int. Conf. on Biometrics (ICB 2016), Honorable Mention Paper Award, and the 11th Int. Workshop on Robust Computer Vision (IWRCV 2016), Best Poster Honorable Mention Award. He has served as reviewers of ICPR, ICB, ACPR, ISBA.

Prof. Yongzhen Huang

yongzhen.huang@nlpr.ia.ac.cn

Associate Professor in the Institute of Automation, Chinese Academy of Sciences, China.

Yongzhen Huang received the B.E. degree from Huazhong University of Science and Technology in 2006 and Ph.D. degree from Institute of Automation, Chinese Academy of Sciences (CASIA) in 2011. Then he joined National Laboratory of Pattern Recognition (NLPR) as an Assistant Professor in July 2011, and became an Associated Professor since Nov. 2013. His research interests include computer vision, pattern recognition and machine learning. He has published one book and more than 60 papers in international journals and conferences such as IEEE TPAMI, IJCV, IEEE TIP, IEEE TMSCB, IEEE TCSVT, IEEE TMM, CVPR, ICCV, NIPS, AAAI. He has obtained several honors and awards, including the Excellent Doctoral Thesis of Chinese Association for Artificial Intelligence (2012), the Best Student Paper of Chinese Conference on Computer Vision (2015), the Champion of PASCAL VOC Challenges on object detection (2010 and 2011), the Champion of Internet Contest for Cloud and Mobile Computing on Human Segmentation (2013), and the Second Prize and the Prize of Highest Accuracy with Low Energy in LPIRC (Low-Power Image Recognition Challenge) (2015). Dr. Huang is now a Senior Member of IEEE. He has served as Associate Editor of Neurocomputing, the web chair of AVSS2012, the publicity chair of CCPR2012, the program committee member of 6 conferences, and the peer reviewer of over 20 journals and conferences.

Prof. Yasushi Yagi

yagi@am.sanken.osaka-u.ac.jp

Professor in the Institute of Scientific and Industrial Research, Osaka University, Japan.

Yasushi Yagi is the Executive Vice President of Osaka university. He received his Ph.D. degrees from Osaka University in 1991. In 1985, he joined the Product Development Laboratory, Mitsubishi Electric Corporation, where he worked on robotics and inspections. He became a Research Associate in 1990, a Lecturer in 1993, an Associate Professor in 1996, and a Professor in 2003 at Osaka University. He was also Director of the Institute of Scientific and Industrial Research, Osaka university from 2012 to 2015. International conferences for which he has served as Chair include: FG1998 (Financial Chair), OMINVIS2003 (Organizing chair), ROBIO2006 (Program co-chair), ACCV2007 (Program chair), PSVIT2009 (Financial chair), ICRA2009 (Technical Visit Chair), ACCV2009 (General chair), ACPR2011 (Program co-chair) and ACPR2013 (General chair). He has also served as the Editor of IEEE ICRA Conference Editorial Board (2007--2011). He is the Editorial member of IJCV and the Editor-in-Chief of IPSJ Transactions on Computer Vision \& Applications. He was awarded ACM VRST2003 Honorable Mention Award, IEEE ROBIO2006 Finalist of T.J. Tan Best Paper in Robotics, IEEE ICRA2008 Finalist for Best Vision Paper, MIRU2008 Nagao Award, and PSIVT2010 Best Paper Award. His research interests are computer vision, medical engineering and robotics. He is a fellow of IPSJ and a member of IEICE, RSJ, and IEEE.

Abstract

Convolutional Neural Networks (CNNs) have garnered immense interest among the research community in many disciplines, thanks to the numerous breakthroughs enabled by CNNs. Not surprisingly, CNNs have also brought huge success for biometrics research. This success was further fueled by the commercialization of biometric systems based on CNNs. One of the main advantages of CNNs is alleviating the need to design hand-crafted or engineered features extractors, and rather combine representation extraction and prediction in a single unified framework. This advantage has made them particularly attractive for newly explored imaging modalities, such as thermal and depth data, for which traditional feature extraction techniques, such as SIFT (scale invariant feature transform) or HoG (histogram of oriented gradients) may not perform satisfactorily. In this tutorial, we will focus on advances in CNNs that have been recently explored for biometric applications, such as multi-task learning and attention mechanisms. We will also cover the challenges and current solutions for training CNNs for newly explored unconventional imaging modalities. Hence, in this tutorial, we aim to list and explain these emerging topics and trace a possible roadmap for future research for biometric applications. We hope that this tutorial will help researchers to bring forces in these exciting research areas.

Outline

• An introduction to CNN.
• A review of CNN for biometric application.
• Multi-tasking based on convolutional neural network (CNN) for better robust for biometric application.
• Attention mechanism based on CNN for better feature representation.
• CNNs for Unconventional Imaging Modalities.
• A brief recap of the related ongoing projects.

Biography

Dr. Abhijit Das

Researcher, Inria, France

He is currently working as a Researcher at Inria Sophia Antipolis– Méditerranée, France. Since 10 years he is conducting research on a range of topics of machine learning and computer vision. His current investigation focuses on learning techniques based on Convolution Neural Network applied to human health monitoring, biometrics and face analysis employing facial and corporeal- based visual feature. During his research career, he has published several scientific articles in conferences, journals and a book chapter and has also received several awards from the IEEE, and other scientific organizations. Dr. Das is involved in organizing scientific events such as international conferences, workshop, competitions and special sessions at conferences, and has served as guest editor for special issues, technical program committee member for several reputed international conference and reviewer of top- ranking journals.

Dr. Mohamed Hussein

Computer Scientist, ISI, USC, USA.

Dr. Hussein is a Computer Scientist at the Information Sciences Institute (ISI). Prior to joining ISI, he spent three years as an assistant professor at Egypt-Japan University of Science and Technology in Egypt (E-JUST), after three other years at Alexandria University in Egypt. Prior to that, Dr. Hussein spent about two years as an Adjunct Member Research Staff at Mitsubishi Electric Research Labs, in Cambridge, MA, USA, after receiving his PhD degree in Computer Science from the University of Maryland at College Park, MD, USA in 2009. Dr. Hussein served on the supervision and examination committees of several PhD students, and has been the PI/Co-PI on multiple industry and government funded research projects on Sign Language Recognition and Crowd Scene Analysis, and Biometrics Anti-Spoofing. Dr. Hussein has over 30 published papers, and three issued patents.