IEEE Computer Society Workshop
on Biometrics

Call for Papers 

With a very security conscious society, biometrics based authentication and identification have become center of focus for many important applications as it is believed that biometrics can provide accurate and reliable identification. Biometrics research and technology continue to mature rapidly, driven by pressing industrial and government needs and supported by industrial and government funding.  As the number and types of biometrics architectures and sensors increases, the need to disseminate research results increases as well.  This workshop is intended to be positioned at the frontier of biometrics research and showcase the most excellent and advanced work underway at academic and private research organizations as well as government labs. 

Many of the applications require higher level of accuracy performance not feasible with a single biometrics today. Additionally, it is also believed that fusing multiple biometrics will also improve wider coverage of population who may not be able to provide a single biometrics and also improve security of the systems in terms of spoof attacks. This workshop will address all aspects of research issues in different modes and levels of fusion of biometrics samples, sensing modes and modalities with a sole goal of improving performance of biometrics. Theoretical studies on sensor fusion techniques applied to biometrics authentication, recognition and performance are encouraged. The topics of interest are: 

- Sensing; intensity, depth, thermal, pressure, time-series, exotic 
- Face, finger, ear, eye, iris, retina, vein pattern, palm, gait, foot, exotic
- Biometric template computation and feature extraction, matching 
- Data and performance baselines 
- Evolution of standards, competitions and organized challenge problems 
- Score level, decision level and feature level integration 
- Architectures for integration, evidence integration 
- Fusion based identification techniques 
- Normalization techniques involved in fusion techniques 
- Machine learning techniques in biometrics fusion 
- Public databases and score files in multi-biometrics 
- Application dependence personalization of multi-biometrics systems 
- Theoretical studies in showing models for integration 
- Performance modeling, prediction and evaluation of multi-biometrics systems
- Security improvement assessment for multi-biometrics systems 

Chairs:

Bir Bhanu (Professor, University of California, Riverside, bhanu@cris.ucr.edu)
Nalini K. Ratha (Research Staff Member, IBM Research, ratha@us.ibm.com)
Venu Govindaraju (Professor, SUNY Buffalo, venu@cubs.buffalo.edu), Web & Publicity Chair

Program Committee:  

Samy Bengio,  IDIAP, Switzerland
Josef Bigun,  Halmstad University, Sweden
Michael Boshra,  Authentec, USA 
Rama Chellappa,  University of Maryland, USA
Amit Roy-Chowdhary, University of California, Riverside, USA 
Pat Flynn,  University of Notre Dame, USA
Venu Govindraju,  University of Buffalo, USA
Patrick Grother,  NIST, USA 
Jaihie Kim,  Yonsei University, South Korea
Josef Kittler,  University of Surrey, UK 
Ajay Kumar,  IIT, New Delhi, India 
Vijaya Kumar,  Carnegie Mellon University, USA
Ludmila Kuncheva, University of Wales,  UK
Larry Nadel,  Mitretek, USA
Jonathon Phillips,  NIST, USA
Fabio Roli,  University of Cagliari, Italy 
Arun Ross,  West Virginia University, USA
Tieniu Tan,  CAS, USA
Xunjun Tan,  QMotions, USA 
Massimo Tistarelli,  Univ. Of Sassari, Italy 
Pramod Varshney,  Syracuse University, USA
Jim Wayman,  San Jose State University, USA
David Zhang,  Polytech University, Hong Kong 

Schedule:

- Several oral paper sessions 
- Invited talks 
- A poster session 

Deadlines: 

Paper submission: April 2, 2007 
Reviews completed: April 20, 2007 
Final Papers due: April 25, 2007   

All the selected papers will be included in CVPR-dvd; in addition, the organizers are planning a special issue in leading workshop.  

Paper Submission: 

Accepted Papers: 

Final Workshop Program: 

Invited Talk: 

Title: Three biometrics, two evaluation, and one meta-analysis  
 
Speaker: Jonathon Phillips  
 
Abstract:  
 
In this talk I will present the large-scale experimental results from the Face Recognition Vendor Test (FRVT) 2006 and the Iris Challenge Evaluation (ICE) 2006. The FRVT 2006 looks at recognition from high-resolution still images and three-dimensional (3D) face images, and measures performance for still images taken under controlled and uncontrolled illumination. The ICE 2006 reports iris recognition performance from left and right iris images. The FRVT 2006 results from controlled still images and 3D images. The FRVT 2006 and the ICE 2006 compared recognition performance from very-high resolution still face images, 3D face images, and single-iris images. In an experiment comparing human and algorithm performance, the best-performing face recognition algorithms were more accurate than humans.  
 
Iris recognition has long been widely regarded as a highly accurate biometric, despite the lack of independent, large-scale testing of its performance. Recently, however, three third-party evaluations of iris recognition were performed: ICE 2006, ITIRT, and IRIS'06. In this talk I will present a meta-analysis of the three evaluations that compares and contrasts the results of these independent evaluations and finds that despite differences in methods, hardware, and/or software among them, all three studies report error rates of the same order of magnitude, and the differences between the best performers' error rates are an order of magnitude smaller than the errors.  
 
The FRVT 2006 and ICE 2006 is joint work with W. T. Scruggs, A. J. O'Toole, P. J. Flynn, K. W. Bowyer, C. L. Schott, M. Sharpe. The meta-analysis is joint work with E. Newton.    

Best Paper Awards for: 

Recognizing Faces of Moving People by Hierarchical Image-Set Matching  
Masashi Nishiyama, Mayumi Yuasa, Tomoyuki Shibata, Tomokazu Wakasugi, Tomokazu Kawahara and Osamu Yamaguchi  
Corporate Research & Development, Toshiba Corporation, Japan  
masashi.nishiyama@toshiba.co.jp  
 
Anonymous and Revocable Fingerprint Recognition  
Faisal Farooq, Ruud M. Bolle, Tsai-Yang Jea and Nalini Ratha  
IBM TJ Watson Research Center  
Hawthorne, NY, 10532

Special Issue: 

A special issue/edited book is under consideration.