Biometric Authentication: A Machine Learning Approach

Biometric Authentication: A Machine Learning Approach

by S. Y. Kung, M. W. Mak, S. H. Lin
Released September 2004
Publisher(s): Pearson
ISBN: 9780131478244

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

  • 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



    •

    Table of contents

    1. Copyright
    2. Prentice Hall Information and System Sciences Series
    3. Preface
    4. Overview
      1. Introduction
      2. Biometric Authentication Methods
      3. Face Recognition: Reality and Challenge
      4. Speaker Recognition: Reality and Challenge
      5. Road Map of the Book
    5. Biometric Authentication Systems
      1. Introduction
      2. Design Tradeoffs
      3. Feature Extraction
      4. Adaptive Classifiers
      5. Visual-Based Feature Extraction and Pattern Classification
      6. Audio-Based Feature Extraction and Pattern Classification
      7. Concluding Remarks
    6. Expectation-Maximization Theory
      1. Introduction
      2. Traditional Derivation of EM
      3. An Entropy Interpretation
      4. Doubly-Stochastic EM
      5. Concluding Remarks
    7. Support Vector Machines
      1. Introduction
      2. Fisher's Linear Discriminant Analysis
      3. Linear SVMs: Separable Case
      4. Linear SVMs: Fuzzy Separation
      5. Nonlinear SVMs
      6. Biometric Authentication Application Examples
    8. Multi-Layer Neural Networks
      1. Introduction
      2. Neuron Models
      3. Multi-Layer Neural Networks
      4. The Back-Propagation Algorithms
      5. Two-Stage Training Algorithms
      6. Genetic Algorithm for Multi-Layer Networks
      7. Biometric Authentication Application Examples
    9. Modular and Hierarchical Networks
      1. Introduction
      2. Class-Based Modular Networks
      3. Mixture-of-Experts Modular Networks
      4. Hierarchical Machine Learning Models
      5. Biometric Authentication Application Examples
    10. Decision-Based Neural Networks
      1. Introduction
      2. Basic Decision-Based Neural Networks
      3. Hierarchical Design of Decision-Based Learning Models
      4. Two-Class Probabilistic DBNNs
      5. Multiclass Probabilistic DBNNs
      6. Biometric Authentication Application Examples
    11. Biometric Authentication by Face Recognition
      1. Introduction
      2. Facial Feature Extraction Techniques
      3. Facial Pattern Classification Techniques
      4. Face Detection and Eye Localization
      5. PDBNN Face Recognition System Case Study
      6. Application Examples for Face Recognition Systems
      7. Concluding Remarks
    12. Biometric Authentication by Voice Recognition
      1. Introduction
      2. Speaker Recognition
      3. Kernel-Based Probabilistic Speaker Models
      4. Handset and Channel Distortion
      5. Blind Handset-Distortion Compensation
      6. Speaker Verification Based on Articulatory Features
      7. Concluding Remarks
    13. Multicue Data Fusion
      1. Introduction
      2. Sensor Fusion for Biometrics
      3. Hierarchical Neural Networks for Sensor Fusion
      4. Multisample Fusion
      5. Audio and Visual Biometric Authentication
      6. Concluding Remarks
    14. Convergence Properties of EM
    15. Average Det Curves
    16. Matlab Projects
      1. Matlab Project 1: GMMs and RBF Networks for Speech Pattern Recognition
      2. Matlab Project 2: SVMs for Pattern Classification
    17. Bibliography
    18. Index

    Product information

    • Title: Biometric Authentication: A Machine Learning Approach
    • Author(s): S. Y. Kung, M. W. Mak, S. H. Lin
    • Release date: September 2004
    • Publisher(s): Pearson
    • ISBN: 9780131478244