Multiple Uses of Correlation Filters for Biometrics

Prof. B.V.K. Vijaya Kumar

Dept. of Electrical and Computer Engineering

Carnegie Mellon University, Pittsburgh, USA

Abstract: The most important challenge in biometrics is to be able to match a query biometric to a reference biometric in spite of the within-class variations and between-class similarities. Most conventional biometric image matching methods are based on segmenting the regions of interest, extracting the features and applying carefully-trained classifiers to separate these features. However, there are advantages to using signal processing methods that work in the spatial frequency domain. Correlation filters are one class of frequency domain-based methods that offer advantages such as shift-invariance (i.e., the object of interest can be off-center), no need for segmentation, graceful degradation and closed-form solutions. This talk will provide an overview of correlation filter design approaches and their applications in biometrics including matching patterns, image alignment, providing information for graphical models, creating cancellable biometrics and biometric encryption.

About the Speaker: Prof. B.V.K. Vijaya Kumar received his Ph.D. in Electrical Engineering from Carnegie Mellon University (CMU), Pittsburgh and since 1982, he has been a faculty member in the Electrical and Computer Engineering (ECE) Department at CMU where he is now a Professor and the Associate Dean for the College of Engineering. He served as the Associate Head of the ECE Department and also as its Acting Department Head. Professor Kumar's research interests include Pattern Recognition (for automatic target recognition and biometrics applications) and Coding and Signal Processing for Data Storage Systems and for Digital Communications. He has authored or co-authored over 500 technical papers, fifteen book chapters and one book entitled Correlation Pattern Recognition. He served as a Topical Editor for Applied Optics and as an Associate Editor of IEEE Trans. Information Forensics and Security. Professor Kumar is a Fellow of IEEE, a Fellow of SPIE, a Fellow of Optical Society of America (OSA) and a Fellow of the International Association of Pattern Recognition (IAPR).

Hand-Based Biometrics: Research and Development in BRC, PolyU

Prof. David Zhang

Director, Chair Professor
Biometrics Research Center, Dept. of Computing
The Hong Kong Polytechnic University, Hong Kong

Abstract: In recent times, an increasing, worldwide effort has been devoted to the development of automatic personal identification systems that can be effective in a wide variety of security contexts. As one of the most powerful and reliable means of personal authentication, biometrics has been an area of particular interest. Hand-based biometrics have attracted a lot of interest. Except some popular biometrics, including fingerprint and hand geometry, other hand-based biometrics like palmprint have been developed. In this talk, we will overview our research work on hand-based biometrics. Some other developments related to hand-based biometrics are also introduced.

About the Speaker: David Zhang graduated in Computer Science from Peking University. He received his MSc in 1982 and his PhD in 1985 in Computer Science from the Harbin Institute of Technology (HIT), respectively. From 1986 to 1988 he was a Postdoctoral Fellow at Tsinghua University and then an Associate Professor at the Academia Sinica, Beijing. In 1994 he received his second PhD in Electrical and Computer Engineering from the University of Waterloo, Ontario, Canada. He has been a Chair Professor since 2005 at the Hong Kong Polytechnic University where he is the Founding Director of the Biometrics Technology Centre (UGC/CRC) supported by the Hong Kong SAR Government in 1998. He also serves as Visiting Chair Professor in Tsinghua University, and Adjunct Professor in Peking University, Shanghai Jiao Tong University, HIT, and the University of Waterloo. He is the Founder and Editor-in-Chief, International Journal of Image and Graphics (IJIG); Book Editor, Springer International Series on Biometrics (KISB); Organizer, the International Conference on Biometrics Authentication (ICBA); Associate Editor of more than ten international journals including IEEE Transactions and so on; and the author of more than 10 books,over 250 international journal papers. He is a Croucher Senior Research Fellow, Distinguished Speaker of the IEEE Computer Society, and a Fellow of both IEEE and IAPR.

Abstract: The biometrics is a field of technology to automatically identify a person using physiological or behavioral traits like the fingerprint, iris, face, hand vein, etc. Among them, fingerprint recognition is the most popular for its small size, relatively high accuracy and economical price. However, conventional fingerprint sensors available in the market are all touch-based and a user needs to press his/her finger on a sensor causing many problems including image distortion, inconsistent image view, latent image, scratches or germs on the sensor.

In this talk, touchless fingerprint recognition developed in BERC(Biometrics Engineering Research Center) is introduced. It is a new concept of capturing a fingerprint image without making a contact of a finger onto the sensor to overcome the difficulties in touch-based sensors. For one finger scan, the first BERC model with its internal structure is illustrated and compared with others. Then, the second BERC model having two side mirrors attached to the finger hole is illustrated. It is to obtain an expanded fingerprint image by mosaicking two side-view images reflected through the mirrors with the center view image taken as before. Additionally, the third BERC model for capturing all five fingerprint images at one time is presented. It has a rotating camera with five holes to hold five fingers. Lastly, a touchless model utilizing multi-spectral illuminators to detect spoof fingers will be introduced.

About the Speaker: Dr. Jaihie Kim received the Ph.D. degree in Electrical Engineering at the Case Western Reserve University, USA. Since 1984, he has been a professor in the School of Electrical and Electronic Engineering, Yonsei University in the Republic of Korea. Currently, Dr. Kim is the Director of the Biometric Engineering Research Center in Korea, the Chairman of the Korea Biometric Association, a member of the National Academy of Engineering of Korea, and in 2008 he was the President of the IEEK (Institute of Electronics Engineers of Korea) and now an Emeritus President of the IEEK.

Dr. Kim’s general research interests include biometrics, pattern recognition and computer vision. Specifically, some of his recent research topics include touchless fingerprint recognition, fake biometrics detection, iris recognition at a distance and face age estimation. He was the Keynote Speaker at the Security Symposium 2006 in Japan, the Biometric Consortium Conference 2007 in USA, the IEICE General Meeting 2008 in Japan, the FAN 2009 in Japan, the UKC 2009 in USA, the ICEIC 2010 at Philippine. He was the author of many international technical journals and conferences, some of which can be found at ‘http://cherup.yonsei.ac.kr/’.

Abstract: Mobile phones are becoming ubiquitous. This explosive growth has made mobile security more important than ever. In particular, the need for more advanced identity check techniques such as biometric verification emerges. Due to the differences between mobile devices and general computing, however, biometric verification in a mobile context is subject to special constraints. This talk discusses the special requirements of mobile biometrics and presents a brief overview of recent developments.
　

About the Speaker: Dr. Jiang studied Computer Science at Peking University and received his PhD and Venia Docendi (Habilitation) degree in Computer Science from the University of Bern, Switzerland. He was an associate professor at the Technical University of Berlin, Germany. Since 2002 he is a full professor of Computer Science at University of Munster, Germany. Currently, he is Editor-in-Chief of Int. Journal of Pattern Recognition and Artificial Intelligence and also serves on the advisory board and editorial board of several other journals including Pattern Recognition, IEEE Trans. on Systems, Man, and Cybernetics – Part B, and Chinese Science Bulletin. He is Senior Member of IEEE and Fellow of IAPR. His research interests include medical image analysis, 3D image analysis, pattern recognition, and mobile multimedia.

Invited Speakers

Multiple Uses of Correlation Filters for Biometrics