Always Learning

Advanced Search

Biometric Authentication

Biometric Authentication

A Machine Learning Approach

S.Y. Kung, M.W. Mak, S.H. Lin

Sep 2004, Hardback, 496 pages
ISBN13: 9780131478244
ISBN10: 0131478249
This title is no longer available.
105.99

This title cannot be purchased online
  • Print pagePrint page
  • Email this pageEmail page
  • Write a reviewWrite a review
  • Share

  • A breakthrough approach to improving biometrics performance
  • Constructing robust information processing systems for face and voice recognition
  • Supporting high-performance data fusion in multimodal systems
  • Algorithms, implementation techniques, and application examples

Machine learning: driving significant improvements in biometric performance

As they improve, biometric authentication systems are becoming increasingly indispensable for protecting life and property. This book introduces powerful machine learning techniques that significantly improve biometric performance in a broad spectrum of application domains.

Three leading researchers bridge the gap between research, design, and deployment, introducing key algorithms as well as practical implementation techniques. They demonstrate how to construct robust information processing systems for biometric authentication in both face and voice recognition systems, and to support data fusion in multimodal systems.

Coverage includes:

  • How machine learning approaches differ from conventional template matching
  • Theoretical pillars of machine learning for complex pattern recognition and classification
  • Expectation-maximization (EM) algorithms and support vector machines (SVM)
  • Multi-layer learning models and back-propagation (BP) algorithms
  • Probabilistic decision-based neural networks (PDNNs) for face biometrics
  • Flexible structural frameworks for incorporating machine learning subsystems in biometric applications
  • Hierarchical mixture of experts and inter-class learning strategies based on class-based modular networks
  • Multi-cue data fusion techniques that integrate face and voice recognition
  • Application case studies


  • A breakthrough approach to improving biometrics performance
  • Constructing robust information processing systems for face and voice recognition
  • Supporting high-performance data fusion in multimodal systems
  • Algorithms, implementation techniques, and application examples

Machine learning: driving significant improvements in biometric performance

As they improve, biometric authentication systems are becoming increasingly indispensable for protecting life and property. This book introduces powerful machine learning techniques that significantly improve biometric performance in a broad spectrum of application domains.

Three leading researchers bridge the gap between research, design, and deployment, introducing key algorithms as well as practical implementation techniques. They demonstrate how to construct robust information processing systems for biometric authentication in both face and voice recognition systems, and to support data fusion in multimodal systems.

Coverage includes:

  • How machine learning approaches differ from conventional template matching
  • Theoretical pillars of machine learning for complex pattern recognition and classification
  • Expectation-maximization (EM) algorithms and support vector machines (SVM)
  • Multi-layer learning models and back-propagation (BP) algorithms
  • Probabilistic decision-based neural networks (PDNNs) for face biometrics
  • Flexible structural frameworks for incorporating machine learning subsystems in biometric applications
  • Hierarchical mixture of experts and inter-class learning strategies based on class-based modular networks
  • Multi-cue data fusion techniques that integrate face and voice recognition
  • Application case studies


Preface.

1. Overview.

Introduction.

Biometric Authentication Methods.

Face Recognition: Reality and Challenge.

Speaker Recognition: Reality and Challenge.

Road Map of the Book.

2. Biometric Authentication Systems.

Introduction.

Design Tradeoffs.

Feature Extraction.

Adaptive Classifiers.

Visual-Based Feature Extraction and Pattern Classification.

Audio-Based Feature Extraction and Pattern Classification.

Concluding Remarks.

3. Expectation-Maximization Theory.

Introduction.

Traditional Derivation of EM.

An Entropy Interpretation.

Doubly-Stochastic EM.

Concluding Remarks.

4. Support Vector Machines.

Introduction.

Fisher's Linear Discriminant Analysis.

Linear SVMs: Separable Case.

Linear SVMs: Fuzzy Separation.

Nonlinear SVMs.

Biometric Authentication Application Examples.

5. Multi-Layer Neural Networks.

Introduction.

Neuron Models.

Multi-Layer Neural Networks.

The Back-Propagation Algorithms.

Two-Stage Training Algorithms.

Genetic Algorithm for Multi-Layer Networks.

Biometric Authentication Application Examples.

6. Modular and Hierarchical Networks.

Introduction.

Class-Based Modular Networks.

Mixture-of-Experts Modular Networks.

Hierarchical Machine Learning Models.

Biometric Authentication Application Examples.

7. Decision-Based Neural Networks.

Introduction.

Basic Decision-Based Neural Networks.

Hierarchical Design of Decision-Based Learning Models.

Two-Class Probabilistic DBNNs.

Multiclass Probabilistic DBNNs.

Biometric Authentication Application Examples.

8. Biometric Authentication by Face Recognition.

Introduction.

Facial Feature Extraction Techniques.

Facial Pattern Classification Techniques.

Face Detection and Eye Localization.

PDBNN Face Recognition System Case Study.

Application Examples for Face Recognition Systems.

Concluding Remarks.

9. Biometric Authentication by Voice Recognition.

Introduction.

Speaker Recognition.

Kernel-Based Probabilistic Speaker Models.

Handset and Channel Distortion.

Blind Handset-Distortion Compensation.

Speaker Verification Based on Articulatory Features.

Concluding Remarks.

10. Multicue Data Fusion.

Introduction.

Sensor Fusion for Biometrics.

Hierarchical Neural Networks for Sensor Fusion.

Multisample Fusion.

Audio and Visual Biometric Authentication.

Concluding Remarks.

Appendix A. Convergence Properties of EM.

Appendix B. Average DET Curves.

Appendix C. Matlab Projects.

Matlab Project 1: GMMs and RBF Networks for Speech Pattern Recognition.

Matlab Project 2: SVMs for Pattern Classification.

Bibliography.

Index.

Sun-Yuan Kung is a professor of electrical engineering at Princeton University. His research and teaching interests include VLSI signal processing; neural networks; digital signal, image, and video processing; and multimedia information systems. His books include VLSI Array Processors and Digital Neural Networks (Prentice Hall PTR).

Man-Wai Mak is an assistant professor at The Hong Kong Polytechnic University and chairman of the IEEE Hong Kong Section Computer Chapter. His research interests include speaker recognition, machine learning, and neural networks.

Shang-Hung Lin is a senior architect at Nvidia, a leader in video and imaging products.



Your opinions count

Be the first to review this product. Write your review now.