Tutorials
There are four tutorials offered to the participants of ICB 2015 and each of these are detailed below. The registration details for these tutorials are available from the link here.
Tutorial Morning Session TM1: An Overview of the Recent Development of Computational Forensics for Criminal and Victim Identification
Kong Wai-Kin Adams (Nanyang Technological University, Singapore)
(19th May, 9:00-12:30)
Abstract : PDF
Slides : -
Abstract
Biometric researchers achieved a great success in the last decade. Their technologies, especially face, fingerprint and iris recognition systems, have been widely used in governmental and commercial applications. Many national ID projects have been carried out and biometric passports have been standardized. Recently, some biometric researchers put more effort on developing effective computational methods for criminal and victim identification. Their research covers a wide range of forensic demands. Some attempt to improve or automatize the current manual or semi-automatic recognition approaches used by law enforcement agencies. Some attempt to address new demands from sexual offenses, riots, digital crimes, and terrorism. In this talk, the tutor will give a brief summary of their recent research results, including latent print enhancement, tattoo retrieval, shoe print recognition, facial composite and sketch processing and matching, dental identification, authorship verification, soft biometrics, skin mark matching and individuality, blood vessel visualization, skin image restoration, prisoner imaging systems and androgenic hair pattern matching.
Brief Biography
Dr Adams Wai-Kin Kong received his PhD from the University of Waterloo, Canada. Currently, he is an associate professor at the Nanyang Technological University, Singapore and Director of the Cyber Security Laboratory. His previous research includes algorithm design and analysis, system implementation and evaluation, feature analysis and template protection. Based on his palmprint identification algorithms, he was selected as a finalist of the 4th Young Inventor Awards 2002-2003, organized by Hewlett Packard and Far Eastern Economic Review. In the summer of 2008, he served as an expert witness to the U.S. Department of Justice for a case of child sexual abuse. His forensic research results were reported by Channel NewsAsia, Straits Times, and HEY!. His papers have been published in TPAMI, TIP, TIFS, TSMC, TCSVT, CVPR, pattern recognition, BTAS and ICB. One of his papers was selected as a spotlight paper by TPAMI and another one was selected as Honorable Mention by Pattern Recognition. With his students, he received Best Student Paper Awards in The IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems and IEEE International Conference on Bioinformatics and Bioengineering. He has developed seven patents; five of his patents have been approved, and the other has been filed. His research interests include biometrics, forensics, medical image processing, image processing, and pattern recognition.
Tutorial Morning Session TM2: Remote, Mobile, and Wearable Video Face Recognition for Surveillance
Brian Lovell (University of Queensland, Australia)
(19th May, 9:00-12:30)
Abstract : PDF
Slides : PDF
Abstract
There has been a great deal of work on face recognition technologies over at least the last 35 years including some on video based recognition. In 14 years of research we have implemented and evaluated many state‐of‐the‐art systems, but all methods we have tested to date failed to address the pressing need for good recognition from uncontrolled low resolution image probes against uncontrolled low quality face galleries. Formal benchmarking on passport quality images often yields impressive recognition rates with virtually zero errors. Yet everyone with any experience in biometrics knows that such performance is simply unattainable in the field without enormously expensive image capture equipment. Obtaining good recognition rates is all about getting the image capture conditions absolutely perfect — and achieving this in the field is incredibly expensive.
In this tutorial we discuss the need for reliable non‐cooperative video recognition for CCTV surveillance. It turns out the strong non‐cooperative recognition technologies are also ideal for mobile and wearable applications. The presenter will first give a broad introduction to the field of face recognition and then concentrate on the challenging and open issues encountered when developing working non‐cooperative and mobile systems. The tutorial will include live demonstrations of state‐of the art CCTV, mobile and possibly even wearable face recognition systems that gained worldwide attention in 2014.
Brief Biography
Professor Lovell is Director of the Advanced Surveillance Group in the School of ITEE, UQ. He was President of the International Association for Pattern Recognition (IAPR) [2008‐2010], and is Fellow of the IAPR, Senior Member of the IEEE, and voting member for Australia on the Governing Board of the IAPR. He was General Co‐Chair of the IEEE International Conference on Image Processing in Melbourne, 2013 and Program Co‐Chair of the International Conference of Pattern Recognition in Tampa, 2008. In 2011, biometric systems developed by his research group won the IFSEC Industrial Prize for Best CCTV System (Birmingham, UK) and the APICTA Trophy for Best R&D in the Asia‐Pacific Region (Phuket, Thailand). These early systems were also demonstrated to the research community during invited presentations at CVPR2011 (Colorado Springs) and IJCB2011 (Washington). His research interests include non‐cooperative and mobile Face Recognition, Biometrics, Statistical Manifolds, and Pattern Recognition.
Tutorial Afternoon Session TA1: Spoofing and Anti-Spoofing in Biometrics: Lessons Learned from the TABULA RASA Project
Marcel Sébastien (Idiap research institute, Switzerland)
(19th May, 14:00-17:30)
Abstract : -
Slides : http://www.idiap.ch/~marcel/professional/ICB_2015.html
Abstract
This tutorial will present the main research outcome of the TABULA RASA project. TABULA RASA (Trusted Biometrics under Spoofing Attacks) is a European funded project (7th Framework Program) that is addressing some of the issues of direct (spoofing) attacks to trusted biometric systems. This is an issue that needs to be addressed urgently because it has recently been shown that conventional biometric techniques, such as fingerprints and face, are vulnerable to direct (spoofing) attacks.
Direct attacks are performed by falsifying the biometric trait and then presenting this falsified information to the biometric system, one such example is to fool a fingerprint system by copying the fingerprint of another person and creating an artificial or gummy finger which can then be presented to the biometric system to falsely gain access. This issue effects not only companies in the high security field but also emerging small and medium sized enterprises (SMEs) that wish to sell biometric technologies in emerging fields.
Brief Biography
Sébastien Marcel received the Ph.D. degree in signal processing from Université de Rennes I in France (2000) at CNET, the research center of France Telecom (now Orange Labs). He is a senior research scientist at the Idiap Research Institute (CH) where he leads the Biometrics group and conducts research on multi-modal biometrics including face recognition, speaker recognition, vein recognition, as well as spoofing and anti-spoofing. In 2010, he was appointed Visiting Professor at the University of Cagliari (IT) where he taught a series of lectures in face recognition. Since 2013, he is a lecturer at the Ecole Polytechnique Fédérale de Lausanne on "Fundamentals in Statistical Pattern Recognition'". He was the main organizer of a number of special scientific events or competitive evaluations all involving biometrics, and serves as an Associate Editor for IEEE Transactions on Information Forensics and Security (TIFS). He is the co-Editor of the Handbook of Biometric Anti-Spoofing published by Springer. He is Guest Editor of the IEEE TIFS Special Issue on Biometric Spoofing and Countermeasures and of the IEEE Signal Processing Magazine Special Issue on Biometric Security and Privacy. Sébastien Marcel is also the principal investigator of international research projects including MOBIO (http://www.mobioproject.org), TABULA RASA (http://www.tabularasa-euproject.org) and BEAT (https://www.beat-eu.org). Finally, he leads the development of the Bob (http://www.idiap.ch/software/bob/), the signal-processing and machine learning toolbox, used for reproducible research in biometrics.
Tutorial Afternoon Session TA2: Deep Learning Methods for Face Recognition
Wolf Lior (Tel Aviv University, Israel)
(19th May, 14:00-17:30)
Abstract : -
Slides : -
Abstract
Deep learning approaches currently lead performance charts in unconstrained face recognition. In this tutorial, I will assume no previous knowledge and will present the main deep learning workhorse currently used in computer vision -- the convolutional neural network (CNN). I will discuss how CNNs are trained and will present, in depth, their usage and adaptation for the task of face recognition.
Brief Biography
Prof. Lior Wolf is a faculty member at the School of Computer Science at Tel-Aviv University. Previously, he was a post-doctoral associate in Prof. Poggio's lab at MIT. He graduated from the Hebrew University, Jerusalem, where he worked under the supervision of Prof. Shashua. Lior Wolf was awarded the 2008 Sackler Career Development Chair, the Colton Excellence Fellowship for new faculty (2006-2008), the Max Shlumiuk Award for 2004, and the Rothchild Fellowship for 2004. His joint work with Prof. Shashua in ECCV 2000 received the best paper award, and their work in ICCV 2001 received the Marr Prize honorable mention. He was also awarded the best paper award at the post ICCV 2009 workshop on eHeritage, and the pre-CVPR2013 workshop on action recognition. Prof. Wolf research focuses on computer vision and applications of machine learning and includes topics such as face identification, document analysis, digital paleography, and video action recognition.