Overview

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, Fisher's Linear Discriminant Analysis (LDA), 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 mac

Full Product Details

Author:   S.Y. Kung ,  M.W. Mak ,  S.H. Lin
Publisher:   Pearson Education (US)
Imprint:   Prentice Hall
Dimensions:   Width: 23.60cm , Height: 3.80cm , Length: 17.60cm
Weight:   1.116kg
ISBN:  

9780131478244

ISBN 10:   0131478249
Pages:   496
Publication Date:   23 September 2004
Audience:   College/higher education ,  Tertiary & Higher Education
Format:   Hardback
Publisher's Status:   Out of Print
Availability:   Awaiting stock  

Table of Contents

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.

Reviews

Author Information

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.

Tab Content 6

Author Website:  

Customer Reviews

Recent Reviews

No review item found!

Add your own review!

Countries Available

All regions