West Virginia Universityoffice (304) 293-4326
fax (304) 293-8602

 

BTAS 2016 Special Session - Representation Learning and Biometrics

Biometrics can be perceived as a research area with broader impact and success of large scale projects such as OBIM (previously known as US VISIT), India’s UID (Aadhar), and FBI AFIS projects have touched the lives of billions. Biometrics is a multidisciplinary areas which includes sensor design, image processing, computer vision, pattern recognition, machine learning, and information fusion. Among these areas, advancements in pattern recognition and machine learning have helped biometrics research in addressing challenges such as identity recognition in unconstrained environment, very large scale identification, and feature learning from millions of data. If we focus on different steps of a biometrics pipeline, one of the important aspects is feature representation. While traditional approaches have focused on handcrafted features such as Local Binary Pattern and Scale Invariant Feature Transform, with the advent in computing technology learning representations have attracted several researchers worldwide.

As mentioned by Bengio et al. [1], The performance of machine learning methods is heavily dependent on the choice of data representation (or features) on which they are applied. Research in representation learning focuses on understanding the data distributions and utilize them in developing novel ways of extracting meaningful features that can help in improving the system performance. In biometrics, this improvement can be seen as higher accuracies and improved user convenience. There are multiple ingredients in representation learning such as deep learning, dictionary learning, non-convex optimization, and non-negative matrix factorization.

The objective of this special session on “Representation Learning and Biometrics” is to identify recent challenges in biometrics, present the algorithms following the representation learning approaches, and discuss the key results and future research directions. This special session will focus on all aspects of representation learning including deep learning and dictionary learning, with a particular emphasis on solving challenging biometrics problems and/or unsolved biometrics issues.

The topics of interest include, but are not limited to:
• Novel unsupervised, semi-supervised, and supervised representation learning algorithms,
• Deep learning, dictionary learning, and other learning based representation algorithms
• Novel metric learning and kernel learning approaches in representation learning framework
• Optimization and regularization for representation learning
• Brain-like computing for biometrics applications
• Applications of representation learning for face, fingerprint, ocular, and/or other biometric modalities
• Novel representation learning algorithms for heterogeneous biometric recognition such as (a) matching visible images to near-infrared images, (b) matching cross-resolution images, and (c) matching sketches with digital face images
• Novel representation learning algorithms for transferring knowledge from one biometric domain to another.

References:
[1] Y. Bengio, A. Courville, P. Vincent, “Representation Learning: A Review and New Perspectives,” IEEE Trans- actions on Pattern Analysis and Machine Intelligence, vol. 35, no. 8, pp. 1798-1828, Aug., 2013.

Organizers: Mayank Vatsa, Vishal Patel, Jiwen Lu, Nasser M. Nasrabadi, Thirimachos Bourlai

Biographies:

Mayank Vatsa received the M.S. and Ph.D. degrees in Computer Science in 2005 and 2008, respectively, from the West Virginia University, Morgantown, USA. He is currently an Associate Professor and AR Krishnaswamy Faculty Research Fellow at the Indraprastha Institute of Information Technology (IIIT) Delhi, India. His research has been funded by the UIDAI, DST and DeitY. He is the recipient of FAST award by DST, India. His areas of interest are biometrics, image processing, machine learning, and information fusion. He has over 150 research papers and received several best paper and best poster awards as well as NVIDIA Innovation Award 2015. Dr. Vatsa is a senior member of the IEEE, member of Computer Society and Association for Computing Machinery. He is Vice President (Publications) of IEEE Biometrics Council, an area editor of IEEE Biometric Compendium, and associate editor of Information Fusion Journal, Elsevier and IEEE Access. He is/was also program committee co-chair of IAPR International Conference on Biometrics 2013 and IEEE/IAPR International Joint Conference on Biometrics 2014, and IEEE International Conference on Identity, Security, and Behavior Analysis 2017.

Vishal M. Patel
received the B.S. degrees in electrical engineering and applied mathematics (Hons.) and the M.S. degree in applied mathematics from North Carolina State University, Raleigh, NC, USA, in 2004 and 2005, respectively, and the Ph.D. degree in electrical engineering from the University of Maryland College Park, MD, USA, in 2010. He is currently an Assistant Professor in the Department of Electrical and Computer Engineering (ECE) at Rutgers University. Prior to joining Rutgers University, he was a member of the research faculty with the University of Marylands Institute for Advanced Computer Studies, College Park, MD, USA. His current research interests include signal processing, computer vision, and pattern recognition with applications in biometrics and imaging. He was a recipient of the ORAU Post-Doctoral Fellowship in 2010. He is a member of Eta Kappa Nu, Pi Mu Epsilon, and Phi Beta Kappa.

Jiwen Lu
is currently an Associate Professor at the Department of Automation, Tsinghua University, China. His research interests include computer vision, pattern recognition, and machine learning. He has authored/co-authored over 120 scientific papers in these areas, where 30 papers are published in the IEEE Transactions journals such as TPAMI, TIP, and TCSVT, and 17 papers are published in the top-tier computer vision conferences such as CVPR, ICCV and ECCV. He serves as an Associate Editor of Pattern Recognition Letters, Neurocomputing, and IEEE Access, a Guest Editor of Image and Vision Computing and Neurocomputing, and an elected member of the Information Forensics and Security Technical Committee of the IEEE Signal Processing Society. He is/was the Workshop Co-Chair for ACCV2016, the Special Session Co-Chair for VCIP’15, and the Area Chair for WACV’16, ICB?16, ICME’15, and ICB’15, the TPC member for over 20 international conferences such as ICCV, CVPR, and ECCV, and the reviewer for over 40 international journals such as TPAMI, TIP and TCSVT. He organized several workshops/competitions at some international conferences such as FG 2015, ACCV 2014, ICME2014, and IJCB2014. He was a recipient of the First-Prize National Scholarship and the National Outstanding Student Award from the Ministry of Education of China in 2002 and 2003, the Best Student Paper Award from Pattern Recognition and Machine Intelligence Association of Singapore in 2012, the Top 10% Best Paper Award from IEEE International Workshop on Multimedia Signal Processing in 2014, and the National 1000 Young Talents Pn Program in 2015, respectively. Recently, he has given tutorials at CVPR 2015, FG 2015, ACCV 2014, ICME 2014, and IJCB 2014. He is a senior member of the IEEE.

Nasser M. Nasrabadi
received the B.Sc. (Eng.) and Ph.D. degrees in Electrical Engineering from Imperial College of Science and Technology (University of London), London, England, in 1980 and 1984, respectively. From October 1984 to December 1984 he worked for IBM (UK) as a senior programmer. During 1985 to 1986 he worked with Philips research laboratory in NY as a member of technical staff. From 1986 to 1991 he was an assistant professor in the Department of Electrical Engineering at Worcester Polytechnic Institute, Worcester, MA. From 1991 to 1996 he was an associate professor with the Department of Electrical and Computer Engineering at State University of New York at Buffalo, Buffalo, NY. From September 1996 to 2015 he was a Senior Research Scientist (ST) with the US Army Research Laboratory (ARL). Since August 2015 he has been a professor at Lane Dept. of Computer Science and Electrical Engineering. Dr. Nasrabadi has served as an associate editor for the IEEE Transactions on Image Processing, the IEEE Transactions on Circuits, Systems and Video Technology, and the IEEE Transactions on Neural Networks. His current research interests are in image processing, computer vision, biometrics, statistical machine learning theory, sparsity, robotics, and neural networks applications to image processing. He is also a Fellow of ARL, SPIE and IEEE.

 

- Thirimachos Bourlai is an Assistant Professor at the LCSEE Department, an Adjunct Assistant Professor (Eye Institute, Dept. of Ophthalmology) and an Adjunct Assistant Professor (Dept. of Forensic and Investigative Sciences), all at West Virginia University (WVU). He has several years of experience in the field of computer vision, and has worked on, initiated, and directed various research projects with the roles of principal or co-investigator, as well as project research participant. His research interests span various computer vision related fields, with a current focus in the areas of image restoration of damaged documents and biometric systems using visible and hyper-spectra imaging sensors, useful for short- to long-range based surveillance applications. His research projects have been funded by DoD-ONR and DoD-DTRA, CITeR (NSF I/UCRC), FBI and TechConnect WV. In 2009, Dr. Bourlai founded and, since then, has been directing the WVU Multi-Spectral Imagery Lab (MILAB). Currently, his lab involves about fifteen Ph.D., M.S., and undergraduate students. Dr. Bourlai served and has been invited to serve as a chair of different events of primary biometrics conferences including ICB, BTAS, SPIE, ISS World Americas, IDGA and FEI. He has served and has been invited to serve as a member on technical program committees for other primary computer vision and biometrics focused conferences (IJCB, ICIP, BTAS, SPIE, ICB, CHI etc.). Several government agencies, organizations and academic institutions have invited Dr. Bourlai to present his work, including the CIA, NSA, FBI, Biometrics Institute, NLETS, IDGA, Biometrics Summit, IEEE Signal Processing Society, Notre Dame, Univ. of Pittsburgh, Rutgers Univ., Univ. of Newcastle (UK), Univ. of Rochester, SRC Inc. etc. He is also a reviewer for premier journals in computer vision, biometrics and related areas (TIFS, TIP, IJCV, TCSVT, PRL, MVA etc.).