16th IEEE Computer Society Workshop on Biometrics 2021
Biometrics Workshop jointly with the Workshop on Analysis and Modeling of Faces and Gestures, CVPR 2021
Call for Papers
With a security-conscious society, biometrics-based authentication and identification have become the center of focus for many important applications because 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 biometric architectures and sensors increase, the need to disseminate research results increases as well. This workshop is intended to be at the frontier of biometrics research and showcase excellent and advanced work from academic and private research organizations as well as government laboratories.
Many applications require a level of accuracy that is not feasible with a single biometric. Fusing multiple biometrics can improve population coverage for people who cannot provide a single biometric and can improve system security against spoof attacks. This workshop addresses research issues in different modes and levels of fusion of biometric samples, sensing modes, and modalities, with the goal of improving biometric performance. Theoretical studies on sensor-fusion techniques applied to biometric authentication, recognition, and performance are encouraged.
Topics of interest:
- Sensing: intensity, depth, thermal, pressure, time-series, and exotic sensing
- Face, finger, ear, eye, iris, retina, vein pattern, palm, gait, foot, and exotic biometrics
- Biometric template computation, feature extraction, and matching
- Data and performance baselines
- Evolution of standards, competitions, and organized challenge problems
- Score-level, decision-level, and feature-level integration
- Architectures for integration and evidence integration
- Fusion-based identification techniques
- Normalization techniques involved in fusion techniques
- Machine learning techniques in biometric fusion
- Public databases and score files in multi-biometrics
- Application-dependent personalization of multi-biometric systems
- Theoretical studies showing models for integration
- Performance modeling, prediction, and evaluation of multi-biometric systems
- Security improvement assessment for multi-biometric systems
Overall Meeting Sponsors
Organizing Committee
General Chair
Bir Bhanu
University of California, Riverside
bbhanu@ucr.edu
Program Chair
Ajay Kumar
The Hong Kong Polytechnic University
Ajay.Kumar@polyu.edu.hk
Program Committee
- Arun Ross, Michigan State University, USA
- Hazim Ekenel, Istanbul Technical University, Turkey
- Matteo Ferrara, University of Bologna, Italy
- Pong C. Yuen, Hong Kong Baptist University, Hong Kong
- Qijun Zhao, Sichuan University, Chengdu, China
- Christoph Busch, Fraunhofer Institute, Germany
- Julian Fierrez, Universidad Autonoma de Madrid, Spain
- Koichi Ito, Tohoku University, Japan
- Chenhao Lin, Xi’an Jiaotong University, Xi’an, China
- Sunpreet Arora, Visa, USA
- Vishal Patel, Johns Hopkins University, USA
- Maneet Singh, AI Garage, MasterCard, India
- Olga Bellon, Universidade Federal do Parana, Brazil
- Vitomir Struc, University of Ljubljana, Slovenia
- Yasushi Makihara, Osaka University, Japan
Important Dates
Paper submission
March 7, 2021 · 11:59 PM PST
Decisions
April 6 and April 9, 2021
Camera-ready papers due
April 10 and April 16, 2021
Workshop date
June 19, 2021
Technical Program
CVPR 2021 Biometrics Workshop · June 19, 2021 · Online
The workshop was held online from 8:00 AM to 12:30 PM EDT.
| Code | Session, paper, or event |
|---|---|
| S1 | Session 1 8:00–9:00 AM · Session Chair: Maneet Singh (AI Garage, Master Card, India) |
| A Deep Adversarial Framework for Visually Explainable Periocular Recognition 8:00–8:20 · Joao Brito and Hugo Proenca (University of Beira Interior, Portugal) |
|
| Indirect Synthetic Attack on Thermal Face Biometric Systems via Visible-to-Thermal Spectrum Conversion 8:20–8:40 · Khawla Mallat and Jean-Luc Dugelay (EURECOM, France) |
|
| Differential Morph Face Detection using Discriminative Wavelet Sub-bands 8:40–9:00 · Baaria Chaudhary, Poorya Aghdaie, Sobhan Soleymani, Jeremy Dawson, and Nasser M. Nasrabadi (West Virginia University, USA) |
|
| Coffee Break 9:00–9:30 AM |
|
| T1 | Face Morphing Attack Detection 9:30–10:15 AM · Christoph Busch (NTNU, Norway) · Session Chair: Bir Bhanu |
| T2 | Perceiving Faces in 2D Images from 3D Perspective 10:15–11:00 AM · Qijun Zhao (Sichuan University, China) · Session Chair: Bir Bhanu |
| S2 | Session 2 11:00–11:30 AM · Session Chair: Kevin H. M. Cheng (University of Oulu, Finland) |
| Toe Prints: An Application Study for Biometric Verification in Adults 11:00–11:10 · Syed Sadaf Ali, Vivek Singh Baghel, Iyyakutti Iyappan Ganapathi, Surya Prakash, and Ngoc-Son Vu |
|
| Multistage Fusion of Face Matchers 11:10–11:20 · Sergey Tulyakov, Nishant Sankaran, Deen Mohan, Srirangaraj Setlur, and Venu Govindaraju (SUNY Buffalo, USA) |
|
| Group Leakage Overestimates Performance: A Case Study in Keystroke Dynamics 11:20–11:30 · Blaine Ayotte, Mahesh K. Banavar, Daqing Hou, and Stephanie Schuckers (Clarkson University, USA) |
|
| T3 | Federated Learning-based Biometrics Authentication on Mobile Devices 11:30 AM–12:10 PM · Vishal Patel (Johns Hopkins University, USA) · Session Chair: Bir Bhanu |
| Closing Remarks 12:10–12:20 PM |
S1 presentations were 20 minutes (15 minutes for presentation and 5 minutes for questions and answers). S2 presentations were 10 minutes (8 minutes for presentation and 2 minutes for questions, answers, and setup).
Invited Talk and Panel Session
Face Morphing Attack Detection
Speaker: Christoph Busch
Abstract: Widespread deployment of Automatic Border Control (ABC), along with electronic Machine Readable Travel Documents (eMRTD) for traveler verification, has enabled a prominent use case of face biometrics in border control applications. The trust anchor is the biometric passport. Many countries issue eMRTD passports on the basis of a printed biometric face photo submitted by the applicant, a procedure that allows the photo to be altered to beautify the subject’s appearance or morphed to conceal their identity. If an eMRTD passport is issued with a morphed facial image, two or more data subjects can use it to pass border control. This talk discusses the morphing attack problem and early solutions for detecting morphed facial images.
Perceiving Faces in 2D Images from 3D Perspective
Speaker: Qijun Zhao
Abstract: The face reveals information about identity, race, gender, age, emotion, intention, and health. Three-dimensional face models are therefore widely studied, but acquiring 3D faces remains more expensive and less convenient than acquiring 2D face images. This research reconstructs 3D face shapes from single or multiple uncalibrated 2D face images. The methods enable efficient generation of 3D face models when only 2D imaging devices are available and effective use of 3D face information to improve facial identity and expression recognition accuracy.
Federated Learning-based Biometrics Authentication on Mobile Devices
Speaker: Vishal Patel
Abstract: Federated learning is a decentralized machine-learning approach in which multiple local devices collaboratively learn a global model with the help of a server while preserving the privacy of data on the local devices. This talk gives an overview of federated learning and presents its application to biometrics-based active authentication, including the merits and drawbacks of available approaches and promising avenues for future research.
Paper Submission
All submissions were subject to a double-blind review process. Author names, affiliations, email addresses, personal acknowledgements, and similar identifying information were to be removed from the paper. Submissions could be up to 8 pages, excluding references, during the review process.
- All papers had to use the IEEE format and the provided LaTeX or MS-Word templates.
- Submitted papers could not have been published, accepted, or under review elsewhere.
- Accepted papers had to be presented by one of the authors, and at least one author had to register at the standard registration rate before the paper-registration deadline.
- Authors were required to transfer copyright to IEEE for papers published in the conference proceedings when submitting the camera-ready version.
Submission system: CMT for Biometrics 2021
Accepted Papers
- Group Leakage Overestimates Performance: A Case Study in Keystroke Dynamics
- Toe Prints: An Application Study for Biometric Verification in Adults
- Differential Morph Face Detection using Discriminative Wavelet Sub-bands
- Indirect Synthetic Attack on Thermal Face Biometric Systems via Visible-to-Thermal Spectrum Conversion
- Multistage Fusion of Face Matchers
- A Deep Adversarial Framework for Visually Explainable Periocular Recognition
Awards
Workshop Venue
Online workshop
The CVPR 2021 Biometrics Workshop was held online on June 19, 2021.