Biometric Signatures Repository
for the IEEE SP Society

This repository has been created for the Education Technical Commettee of the IEEE Signal Processing Society to act as a clearing house and a jumping stone in the field of Signal Processing Applications to Biometric Identification and Authentication. You will find a number of critically acclaimed works from several key names in this field and the material from talks given at various platforms by the IEEE Distinguished Lecturers and Invited Speakers of the Signal Processing Society.

We will try to have a brief explanation for each subarea or team and their best representaive work with permission from authors. We will also direct the reader to the appropriate websites when possible.

Digitized and Digital Signatures for Biometric Identification by H. Abut

Abstract:
Biometrics are best defined as measurable and/or behavioral characteristics that can be employed to verify the identity of a person. They include fingerprints, retinal and iris scanning, hand-writing and geometry, voiceprints, facial recognition, DNA codes, and other techniques and features. Initially, these techniques were employed primarily in access control of high security facilities, however, they are now being deployed or proposed for use in a much broader range of public facing situations. In this talk, we will present, the highlights of some of these techniques (except DNA codes) as well as the challenges encountered in their selection and deployment.

Slides from presentations can be downloaded in PDF format:
PDF color copy of slides (3.47 MB)

Phonetic, Idiolectic, and Acoustic Speaker Recognition by Joseph P. Campbell, Jr.

Outline of the Presentation:
Introduction
Acoustic & Channel Compensation
Idiolect & Phonetic
Detection Theory
Performance
Conclusions and Acknowledgements.

Slides in PDF format can be downloaded: Campbell_IEEE_DL
(They have been included with permission)

Fingerprint Image Enhancment Using Weak Models by J.H. Connell, N.K. Ratha, and R.M. Bolle

Abstract: Biometrics-based authentication and identification systems have to handle images acquired in noisy and hostile environments. The signal quality is assessed to decide if there is sufficient signal strength to process further. Poor quality signals require “enhancement” before further processing of the input signal. Often enhancement implies creating a more visibly pleasing image. However, biometrics signals need to improve the image quality for machine processability. This means that the enhancement algorithm should have some weak model about the sample (image) formation process. Enhancement is then some type of “normalization” or “beautification”. We present a weak model-based image enhancement algorithm for fingerprint images. The results of the proposed algorithm are presented in terms of the improvements in the overall system performance measured in terms of a Receiver Operating Characteristics curve.

Slides in PDF format can be downloaded:ibm_icip02
(They have been included with permission)

Enhancing Security and Privacy in Biometrics-based Authentication Systems by N. K. Ratha J. H. Connell R. M. Bolle, which appeared in the IBM Systems Journal, Vol. 40, No. 3, 2001 and we have also included that work in this repository.

Abstract: Because biometrics-based authentication offers several advantages over other authentication methods, there has been a significant surge in the use of biometrics for user authentication in recent years. It is important that such biometrics-based authentication systems be designed to withstand attacks when employed in security-critical applications, especially in unattended remote applications such as ecommerce. In this paper we outline the inherent strengths of biometrics-based authentication, identify the weak links in systems employing biometrics-based authentication, and present new solutions for eliminating some of these weak links. Although, for illustration purposes, fingerprint authentication is used throughout, our analysis extends to other biometrics-based methods.

Copy the paper in PDF format can be downloaded:IBMJournal

For more information in this topic, we recommend readers to visit the IBM website: Biometrics.
(The material in this section has been included with permission from the authors)

How Iris Recognition Works by J. Daugman

Abstract: Algoritms developed by the author for recognizing persons by their iris patterns have now been tested in six field and laboratory trials, producing no false matches in several million comparison tests. The recognition principle is the failure of a test of statistical independence on iris phase structure encoded by multi-scale quadrature wavelets. The combinatorial complexity of this phase information across different persons spans about 244 degrees of freedom and generates a discrimination entropy of about 3.2 bits/mm-square over the iris, enabling real-time decisions about personal identity with extremely high confidence.The high confidence levels are important because they allow very large databases to be searched exhaustively (one-to-many “identification mode”) without making any false matches, despite so many chances. Biometrics lacking this property can only survive one-to-one (“verification”) or few comparisons. This paper explains the algorithms for iris recognition, and presents the results of 2.3 million comparisons among eye images acquired in trials in Britain, the USA, and Japan.
Copy the paper in P DF format can be downloaded:irisrecog

(This material has been included with permission from the author.)

For more information in this topic, we recommend readers to visit the website of Prof. John Daugman at the University of Cambridge: jgd

 

Correlation Filters for Biometrics by Vijayakumar Bhagavatula

Abstract: Biometric recognition refers to the process of matching an input biometric to stored biometric information. In particular, biometric verification refers to matching the live biometric input from an individual to the stored biometric template about that individual. Examples of biometrics include face images, fingerprint images, iris images, retinal scans, etc. Thus, image processing techniques prove useful in the biometric recognition.

Slides in PDF format can be downloaded:Correlationfilters
For more information in this topic, we recommend readers to visit the author's website at Carnegie-Mellon University: kumar
(The material in this section has been included with permission from the author.)

Multimodal Biometrics by A. K. Jain.

Abstract: A biometric system is essentially a pattern recognition system which makes a personal identification by determining the authenticity of a specific physiological or behavioral characteristic possessed by the user. An important issue in designing a practical system is to determine how an individual is identified. Depending on the context, a biometric system can be either a verification (authentication) system or an identification system. User verification systems that use a single biometric indicator often have to contend with noisy sensor data, restricted degrees of freedom and unacceptable error rates. Attempting to improve the performance of individual matchers in such situations may not prove to be effective because of these inherent problems. Multimodal biometric systems seek to alleviate some of these drawbacks by providing multiple evidences of the same identity. These systems also help achieve an increase in performance that may not be possible by using a single biometric indicator.

Slides in PDF format can be downloaded :BC2002talk
(They have been included with permission)

Learning User-Specific Parameters in a Multibiometric System
by A.K. Jain A. Ross was presented in the ICIP2002 meeting. The authors have provided us an expanded version of the paper as the most indicative of the work from their group and we have included in this repository.
The readers interested in the ICIP2002 paper are recommended to access the proceedings or go to the authors.

For more information in this topic, we recommend readers to visit the website of Prof. A.K. Jain at Michigan State University: Biometrics Research

Digital Signal Processing in Biometric Identification: A Review by James L. Wayman

Abstract: Biometrics is the automatic identification or identity verification of living, human individuals based on physiological and behavioral characteristics. Biometrics is a subset of the larger field of human identification science. The term automatic in the definition means that digital computers will usually (but not always) be used. In this paper, we will consider the general state of digital signal processing in biometrics by examining the computational approaches to speaker, fingerprint, and face recognition. We note the generally weak relationship between physiology and biometric features and the potential for use of models to compensate for intra-class variation.

Copy the paper in PDF format can be downloaded: icip02jlw
(Reprint from ICIP2002 Proceedings have been included with permission.)

For more information in this topic, we recommend readers to visit the National Biometric Test Center website at San Jose State University: biometrics

Human Identification Technical Challenges by P. Jonathon Phillips.

Abstract: The HumanID program is developing techniques and methods for identifying humans at a distance. Techniques being investigated are face recognition; recognition from body dynamics in video including gait; recognition from infrared, mulitispectral, and hyperspectral imagery. To support these activities a large database of imagery is being collected, and to assess performance advanced statistical methods are being investigated.

Copy the paper in PDF format can be downloaded: darpa
(Reprint from ICIP2002 Proceedings have been included with permission.)

 


Last update: October 3, 2002