Biometric Authentication: International ECCV 2002 Workshop Copenhagen, Denmark, June 1, 2002 Proceedings (Lecture Notes in Computer Science, 2359)

✍ Scribed by Massimo Tistarelli (editor), Josef Bigun (editor), Anil K. Jain (editor)

• Publisher: Springer
• Year: 2002
• Tongue: English
• Leaves: 203
• Edition: 2002
• Category: Library

✦ Synopsis

Biometric authentication refers to identifying an individual based on his or her distinguishing physiological and/or behavioral characteristics. It associates an individual with a previously determined identity based on that individual s appearance or behavior. Because many physiological or behavioral characteristics (biometric indicators) are distinctive to each person, biometric identifiers are inherently more reliable and more capable than knowledge-based (e.g., password) and token-based (e.g., a key) techniques in differentiating between an authorized person and a fraudulent impostor. For this reason, more and more organizations are looking to automated identity authentication systems to improve customer satisfaction, security, and operating efficiency as well as to save critical resources. Biometric authentication is a challenging pattern recognition problem; it involves more than just template matching. The intrinsic nature of biometric data must be carefully studied, analyzed, and its properties taken into account in developing suitable representation and matching algorithms. The intrinsic variability of data with time and environmental conditions, the social acceptability and invasiveness of acquisition devices, and the facility with which the data can be counterfeited must be considered in the choice of a biometric indicator for a given application. In order to deploy a biometric authentication system, one must consider its reliability, accuracy, applicability, and efficiency. Eventually, it may be necessary to combine several biometric indicators (multimodal-biometrics) to cope with the drawbacks of the individual biometric indicators.

✦ Table of Contents

Biometric Authentication
Preface
Program Committee Members
Table of Contents
An Incremental Learning Algorithm for Face
Introduction
IRDB
Algorithm
Experiments
Conclusions and Future Work
References
Face Recognition Based on ICA Combined with FLD
Introduction
Related Work
Eigenfaces and Fisherfaces
ICA Based Face Recognition
(ICA+FLD) Method
Experiments
Conclusions
References
Understanding Iconic Image-Based Face Biometrics
Introduction
Understanding Face Recognition Algorithms
Statistical Error Measurements
Iconic Face Matching
Face Image Registration
System Testing
Analysis and Discussion
References
Fusion of LDA and PCA for Face Verification
Introduction
PCA and LDA for Face Verification
Principal Component Analysis
Linear Discriminant Analysis
Fusion of LDA and PCA
Our Face Verification Protocol
Our Approach to Threshold Computation
The Fusion Algorithms
Experimental Results
Data Set
Results
Conclusions
References
Complex Filters Applied to Fingerprint Images Detecting Prominent Symmetry Points Used for Alignment
Introduction
Symmetry Point Extraction
Filters for Rotational Symmetry Detection
Multi-scale Filtering
Maximum Filter Response
Implementation
Experiments
Conclusion
Acknowledgment
References
Fingerprint Matching Using Feature Space Correlation
Ridge Feature Maps
Constructing the Ridge Feature Map
Introduction
Fingerprint Matching Using Ridge Feature Maps
Experiments and Results
Summary and Future Work
References
Fingerprint Minutiae: A Constructive Definition
Fingerprints
Fingerprint Processing
Minutia Definition
Minutia Position Estimation
Conclusions
References
Pseudo-entropy Similarity for Human Biometrics
Multimedia and Artificial Intelligence Background
Statement of Problem
Notions of Pseudo-entropy, Pseudo-information, Pseudo-divergence
Mathematical and Algorithmic Notations of the JeK Criterion
Example of Automatic Measuring of Audio Objects Similarity
Sensitivity, Stability and Relative Linearity of Measure JeK in Area of Similarity
Examples and Perspective of Similarity Measuring of 2D and 3D Biometric Objects
Conclusion Remarks
References
Mental Characteristics of Person as Basic Biometrics
Expanding of Traditional Meaning of the Biometric Technology
Problem Statement
Person Mental Characteristic Measuring in S. Dellinger’s Method
Auto ID: Geom.-Cogn. ’01 Program System Performances
Some Scientific Aspects of Expanded Experimental Research
On Experimental Results
Some Fundamental Properties of the Indexed Vector Space
Mental Abilities Test Named as Kotelnikov-Shannon_Theorem_Test
Conclusion and Near Future Works
References
Detection of Frontal Faces in Video Streams
Introduction
Face Detection
Our Color Approach
Features Detection
The Procedure
Detection Experiments
Conclusions and Future Work
Acknowledgements
References
Genetic Model Optimization for Hausdorff Distance-Based Face Localization
Introduction
Hausdorff Distance-Based Face Detection
Genetic Model Optimization
Genotype Coding
Fitness Function
Selection, Crossover, Mutation, Population Size
Initialization
Experiments
Conclusions
References
Coarse to Fine Face Detection Based on Skin Color Adaption
Introduction
Skin Region Selection
Accurate Face Detection
Accurate Online Training Model
Validating the Face Hypothesis
Experiments
Conclusion
Acknowledgment
References
Robust Face Recognition Using Dynamic Space Warping
Introduction
Salient Feature Extraction
Region Matching for Face Recognition
The Dynamic Warping Process
Maximum Likelihood for Accurate Face Recognition
Experiments
Databases and Feature Matching
Noise and Blurring Robustness
Occlusion and Rotation Efficiency
Conclusion and Future Work
References
Subspace Classification for Face Recognition
Introduction
Face Location and Feature Extraction
Subspace Learning and Classification Using MKL
KL for Face Recognition (Eigenfaces Approach)
MKL for Face Recognition
Experimental Results
Conclusions
References
Gait Appearance for Recognition
Introduction
Previous Work
Gait Sequence Representation
Gait Image Features
Gait Sequence Features
Experimental Methods and Results
Recognition Using Averaged Appearance Features
Recognition Using Appearance Histograms
Recognition Using Fundamental Spectral Decomposition Features
Discussion
Conclusions
Acknowledgments
References
View-invariant Estimation of Height and Stride for Gait Recognition
Introduction
Assumptions
Background and Related Work
Method
Estimating Ground Position
Estimating Stride Parameters
Estimating Height Parameters
Error Analysis
Gait Classifier
Experiments and Results
Conclusions and Future Work
Acknowledgment
References
Improvement of On-line Signature Verification System Robust to Intersession Variability
Introduction
Verification Process Using Five Data from Tablet
Verification Process
Degradation of Verification Rate Along Time
Improvement of Verification Rate by Reference Renewal
Reference Renewal Method
Reference Renewal Adapting Threshold to the Matching Error of Last Five Authenticated Data
Conclusion
References
Biometric Identification in Forensic Cases According to the Bayesian Approach
Introduction
Biometric Systems and Classical Forensic Reporting
Is Acceptance/Rejection the Objective of Forensic Recognition?
Bayesian Analysis of Forensic Evidence
Assessment of Forensic Biometric Systems
Specific Application in Speaker Recognition
Computation of Likelihood Ratios in Forensic Speaker Recognition
DET and Tippet Plots with NIST-Ahumada Data
Conclusions
Acknowledgements
References
A New Quadratic Classifier Applied to Biometric Recognition
Introduction
The Quadratic Discriminant Classifier
Sample Size Effects
Other Quadratic Classifiers
Reguralized Discriminant Analysis (RDA) Classifier
Leave-One-Out Covariance (LOOC)Classifier
Simplified Quadratic Discriminant Function (SQDF) Classifier
A New Quadratic Classifier
The “Loss of Covariance Information”
Maximum Entropy Covariance Selection Method
Experiments and Results
Experiments
Results
Conclusion
Acknowledgment
References
Author Index