Return to search

Decision fusion for multi-modal person authentication.

Hui Pak Sum Henry. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2006. / Includes bibliographical references (leaves [147]-152). / Abstracts in English and Chinese. / Chapter 1. --- Introduction --- p.1 / Chapter 1.1. --- Objectives --- p.4 / Chapter 1.2. --- Thesis Outline --- p.5 / Chapter 2. --- Background --- p.6 / Chapter 2.1. --- User Authentication Systems --- p.6 / Chapter 2.2. --- Biometric Authentication --- p.9 / Chapter 2.2.1. --- Speaker Verification System --- p.9 / Chapter 2.2.2. --- Face Verification System --- p.10 / Chapter 2.2.3. --- Fingerprint Verification System --- p.11 / Chapter 2.3. --- Verbal Information Verification (VIV) --- p.12 / Chapter 2.4. --- Combining SV and VIV --- p.15 / Chapter 2.5. --- Biometric Decision Fusion Techniques --- p.17 / Chapter 2.6. --- Fuzzy Logic --- p.20 / Chapter 2.6.1. --- Fuzzy Membership Function and Fuzzy Set --- p.21 / Chapter 2.6.2. --- Fuzzy Operators --- p.22 / Chapter 2.6.3. --- Fuzzy Rules --- p.22 / Chapter 2.6.4. --- Defuzzification --- p.23 / Chapter 2.6.5. --- Advantage of Using Fuzzy Logic in Biometric Fusion --- p.23 / Chapter 2.7. --- Chapter Summary --- p.25 / Chapter 3. --- Experimental Data --- p.26 / Chapter 3.1. --- Data for Multi-biometric Fusion --- p.26 / Chapter 3.1.1. --- Speech Utterances --- p.30 / Chapter 3.1.2. --- Face Movement Video Frames --- p.31 / Chapter 3.1.3. --- Fingerprint Images --- p.32 / Chapter 3.2. --- Data for Speech Authentication Fusion --- p.33 / Chapter 3.2.1. --- SV Training Data for Speaker Model --- p.34 / Chapter 3.2.2. --- VIV Training Data for Speaker Independent Model --- p.34 / Chapter 3.2.3. --- Validation Data --- p.34 / Chapter 3.3. --- Chapter Summary --- p.36 / Chapter 4. --- Authentication Modules --- p.37 / Chapter 4.1. --- Biometric Authentication --- p.38 / Chapter 4.1.1. --- Speaker Verification --- p.38 / Chapter 4.1.2. --- Face Verification --- p.38 / Chapter 4.1.3. --- Fingerprint Verification --- p.39 / Chapter 4.1.4. --- Individual Biometric Performance --- p.39 / Chapter 4.2. --- Verbal Information Verification (VIV) --- p.42 / Chapter 4.3. --- Chapter Summary --- p.44 / Chapter 5. --- Weighted Average Fusion for Multi-Modal Biometrics --- p.46 / Chapter 5.1. --- Experimental Setup and Results --- p.46 / Chapter 5.2. --- Analysis of Weighted Average Fusion Results --- p.48 / Chapter 5.3. --- Chapter Summary --- p.59 / Chapter 6. --- Fully Adaptive Fuzzy Logic Decision Fusion Framework --- p.61 / Chapter 6.1. --- Factors Considered in the Estimation of Biometric Sample Quality --- p.62 / Chapter 6.1.1. --- Factors for Speech --- p.63 / Chapter 6.1.2. --- Factors for Face --- p.65 / Chapter 6.1.3. --- Factors for Fingerprint --- p.70 / Chapter 6.2. --- Fuzzy Logic Decision Fusion Framework --- p.76 / Chapter 6.2.1. --- Speech Fuzzy Sets --- p.77 / Chapter 6.2.2. --- Face Fuzzy Sets --- p.79 / Chapter 6.2.3. --- Fingerprint Fuzzy Sets --- p.80 / Chapter 6.2.4. --- Output Fuzzy Sets --- p.81 / Chapter 6.2.5. --- Fuzzy Rules and Other Information --- p.83 / Chapter 6.3. --- Experimental Setup and Results --- p.84 / Chapter 6.4. --- Comparison Between Weighted Average and Fuzzy Logic Decision Fusion --- p.86 / Chapter 6.5. --- Chapter Summary --- p.95 / Chapter 7. --- Factors Affecting VIV Performance --- p.97 / Chapter 7.1. --- Factors from Verbal Messages --- p.99 / Chapter 7.1.1. --- Number of Distinct-Unique Responses --- p.99 / Chapter 7.1.2. --- Distribution of Distinct-Unique Responses --- p.101 / Chapter 7.1.3. --- Inter-person Lexical Choice Variations --- p.103 / Chapter 7.1.4. --- Intra-person Lexical Choice Variations --- p.106 / Chapter 7.2. --- Factors from Utterance Verification --- p.108 / Chapter 7.2.1. --- Thresholding --- p.109 / Chapter 7.2.2. --- Background Noise --- p.113 / Chapter 7.3. --- VIV Weight Estimation Using PDP --- p.115 / Chapter 7.4. --- Chapter Summary --- p.119 / Chapter 8. --- Adaptive Fusion for SV and VIV --- p.121 / Chapter 8.1. --- Weighted Average fusion of SV and VIV --- p.122 / Chapter 8.1.1. --- Scores Normalization --- p.123 / Chapter 8.1.2. --- Experimental Setup --- p.123 / Chapter 8.2. --- Adaptive Fusion for SV and VIV --- p.124 / Chapter 8.2.1. --- Components of Adaptive Fusion --- p.126 / Chapter 8.2.2. --- Three Categories Design --- p.129 / Chapter 8.2.3. --- Fusion Strategy for Each Category --- p.132 / Chapter 8.2.4. --- SV Driven Approach --- p.133 / Chapter 8.3. --- SV and Fixed-Pass Phrase VIV Fusion Results --- p.133 / Chapter 8.4. --- SV and Key-Pass Phrase VIV Fusion Results --- p.136 / Chapter 8.5. --- Chapter Summary --- p.141 / Chapter 9. --- Conclusions and Future Work --- p.143 / Chapter 9.1. --- Conclusions --- p.143 / Chapter 9.2. --- Future Work --- p.145 / Bibliography --- p.147 / Appendix A Detail of BSC Speech --- p.153 / Appendix B Fuzzy Rules for Multimodal Biometric Fusion --- p.155 / Appendix C Full Example for Multimodal Biometrics Fusion --- p.157 / Appendix DReason for Having a Flat Error Surface --- p.161 / Appendix E Reason for Having a Relative Peak Point in the Middle of the Error Surface --- p.164 / Appendix F Illustration on Fuzzy Logic Weight Estimation --- p.166 / Appendix GExamples for SV and Key-Pass Phrase VIV Fusion --- p.175

Identiferoai:union.ndltd.org:cuhk.edu.hk/oai:cuhk-dr:cuhk_325651
Date January 2006
ContributorsHui, Pak Sum Henry., Chinese University of Hong Kong Graduate School. Division of Systems Engineering and Engineering Management.
Source SetsThe Chinese University of Hong Kong
LanguageEnglish, Chinese
Detected LanguageEnglish
TypeText, bibliography
Formatprint, xviii, 176 leaves : ill. ; 30 cm.
RightsUse of this resource is governed by the terms and conditions of the Creative Commons “Attribution-NonCommercial-NoDerivatives 4.0 International” License (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Page generated in 0.0024 seconds