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

Lau, Chun Wai. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (leaves 119-123). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Overview --- p.1 / Chapter 1.2 --- Multimodal Biometric Systems --- p.3 / Chapter 1.3 --- Objectives --- p.7 / Chapter 1.4 --- Thesis Outline --- p.7 / Chapter 2 --- Background --- p.9 / Chapter 2.1 --- Decision Fusions in Multimodal Biometric Systems --- p.10 / Chapter 2.2 --- Fuzzy Logic --- p.15 / Chapter 2.2.1 --- Fuzzy Sets and Their Operations --- p.15 / Chapter 2.2.2 --- Fuzzy Rules --- p.17 / Chapter 2.2.3 --- Defuzzification --- p.18 / Chapter 2.2.4 --- Applications of Fuzzy Logic --- p.19 / Chapter 2.3 --- Demspter-Shafer Theory of Evidence --- p.20 / Chapter 2.3.1 --- Belief and Plausibility --- p.20 / Chapter 2.3.2 --- Dempster's Rule of Combination --- p.21 / Chapter 2.3.3 --- Applications of Dempster-Shafer Theory of Evidence --- p.22 / Chapter 2.4 --- Chapter Summary --- p.23 / Chapter 3 --- Biometric Modalities --- p.24 / Chapter 3.1 --- Speaker Verification --- p.24 / Chapter 3.1.1 --- Data Collection --- p.25 / Chapter 3.1.2 --- Experiment and Results --- p.26 / Chapter 3.2 --- Face Identification --- p.27 / Chapter 3.2.1 --- Data Collection --- p.28 / Chapter 3.2.2 --- Experiment and Results --- p.29 / Chapter 3.3 --- Fingerprint Verification --- p.35 / Chapter 3.3.1 --- Data Collection --- p.36 / Chapter 3.3.2 --- Experiment and Results --- p.37 / Chapter 3.4 --- Chapter Summary --- p.38 / Chapter 4 --- Baseline Fusions --- p.39 / Chapter 4.1 --- Majority Voting --- p.40 / Chapter 4.2 --- Fusion by Weighted Average Scores --- p.45 / Chapter 4.3 --- Comparison of Fusion by Majority Voting and Fusion by Weighted Average Scores --- p.51 / Chapter 4.4 --- Chapter Summary --- p.53 / Chapter 5 --- Fuzzy Logic Decision Fusion --- p.54 / Chapter 5.1 --- Introduction --- p.55 / Chapter 5.2 --- Fuzzy Inference System --- p.56 / Chapter 5.2.1 --- Input Fuzzy Variables and Fuzzy Sets for Face Biometric --- p.56 / Chapter 5.2.2 --- Input Fuzzy Variables and Fuzzy Sets for Fingerprint Biometric --- p.59 / Chapter 5.2.3 --- Output Fuzzy Variables and Fuzzy Sets --- p.62 / Chapter 5.2.4 --- Fuzzy Rules for Face Biometric --- p.63 / Chapter 5.2.5 --- Fuzzy Rules for Fingerprint Biometric --- p.64 / Chapter 5.3 --- Experiments with Fuzzy Logic Fusion --- p.66 / Chapter 5.4 --- Significance Testing --- p.71 / Chapter 5.5 --- Comparison of Fuzzy Logic Fusion and Weighted Average Scores --- p.74 / Chapter 5.6 --- Testing of Fuzzy Rule Properties --- p.76 / Chapter 5.6.1 --- Experiment 1 --- p.77 / Chapter 5.6.2 --- Experiment 2 --- p.80 / Chapter 5.6.3 --- Experiment 3 --- p.83 / Chapter 5.6.4 --- Comparison of Results --- p.86 / Chapter 5.7 --- Chapter Summary --- p.86 / Chapter 6 --- Decision Fusion Based on Dempster-Shafer Theory of Evi- dence --- p.88 / Chapter 6.1 --- Introduction --- p.89 / Chapter 6.2 --- Framework of Fusion Based on Dempster-Shafer Theory of Evidence --- p.90 / Chapter 6.2.1 --- Evidences for Biometric Systems --- p.91 / Chapter 6.2.2 --- Intra-Modality Combination --- p.95 / Chapter 6.2.3 --- Inter-Modality Combination --- p.97 / Chapter 6.3 --- Experiments with Fusion Based on Dempster-Shafer Theory of Evidence --- p.99 / Chapter 6.4 --- Significance Testing --- p.103 / Chapter 6.5 --- Comparison of Fusion Based on Dempster-Shafer Theory of Evidence and Weighted Average Scores --- p.106 / Chapter 6.6 --- Comparison of Fusion Based on Dempster-Shafer Theory of Evidence and Fuzzy Logic Fusion --- p.108 / Chapter 6.7 --- Chapter Summary --- p.110 / Chapter 7 --- Conclusions --- p.112 / Chapter 7.1 --- Summary --- p.112 / Chapter 7.2 --- Contributions --- p.115 / Chapter 7.3 --- Future Work --- p.117 / Bibliography --- p.119 / Chapter A --- Fuzzy Rules --- p.124

Ouyang, Hua. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2007. / Includes bibliographical references (leaves 81-89). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Biometric Authentication --- p.1 / Chapter 1.2 --- Multimodal Biometric Authentication --- p.2 / Chapter 1.2.1 --- Combination of Different Biometric Traits --- p.3 / Chapter 1.2.2 --- Multimodal Fusion --- p.5 / Chapter 1.3 --- Audio-Visual Bi-modal Authentication --- p.6 / Chapter 1.4 --- Focus of This Research --- p.7 / Chapter 1.5 --- Organization of This Thesis --- p.8 / Chapter 2 --- Audio-Visual Bi-modal Authentication --- p.10 / Chapter 2.1 --- Audio-visual Authentication System --- p.10 / Chapter 2.1.1 --- Why Audio and Mouth? --- p.10 / Chapter 2.1.2 --- System Overview --- p.11 / Chapter 2.2 --- XM2VTS Database --- p.12 / Chapter 2.3 --- Visual Feature Extraction --- p.14 / Chapter 2.3.1 --- Locating the Mouth --- p.14 / Chapter 2.3.2 --- Averaged Mouth Images --- p.17 / Chapter 2.3.3 --- Averaged Optical Flow Images --- p.21 / Chapter 2.4 --- Audio Features --- p.23 / Chapter 2.5 --- Video Stream Classification --- p.23 / Chapter 2.6 --- Audio Stream Classification --- p.25 / Chapter 2.7 --- Simple Fusion --- p.26 / Chapter 3 --- Weighted Sum Rules for Multi-modal Fusion --- p.27 / Chapter 3.1 --- Measurement-Level Fusion --- p.27 / Chapter 3.2 --- Product Rule and Sum Rule --- p.28 / Chapter 3.2.1 --- Product Rule --- p.28 / Chapter 3.2.2 --- Naive Sum Rule (NS) --- p.29 / Chapter 3.2.3 --- Linear Weighted Sum Rule (WS) --- p.30 / Chapter 3.3 --- Optimal Weights Selection for WS --- p.31 / Chapter 3.3.1 --- Independent Case --- p.31 / Chapter 3.3.2 --- Identical Case --- p.33 / Chapter 3.4 --- Confidence Measure Based Fusion Weights --- p.35 / Chapter 4 --- Regularized k-Nearest Neighbor Classifier --- p.39 / Chapter 4.1 --- Motivations --- p.39 / Chapter 4.1.1 --- Conventional k-NN Classifier --- p.39 / Chapter 4.1.2 --- Bayesian Formulation of kNN --- p.40 / Chapter 4.1.3 --- Pitfalls and Drawbacks of kNN Classifiers --- p.41 / Chapter 4.1.4 --- Metric Learning Methods --- p.43 / Chapter 4.2 --- Regularized k-Nearest Neighbor Classifier --- p.46 / Chapter 4.2.1 --- Metric or Not Metric? --- p.46 / Chapter 4.2.2 --- Proposed Classifier: RkNN --- p.47 / Chapter 4.2.3 --- Hyperkernels and Hyper-RKHS --- p.49 / Chapter 4.2.4 --- Convex Optimization of RkNN --- p.52 / Chapter 4.2.5 --- Hyper kernel Construction --- p.53 / Chapter 4.2.6 --- Speeding up RkNN --- p.56 / Chapter 4.3 --- Experimental Evaluation --- p.57 / Chapter 4.3.1 --- Synthetic Data Sets --- p.57 / Chapter 4.3.2 --- Benchmark Data Sets --- p.64 / Chapter 5 --- Audio-Visual Authentication Experiments --- p.68 / Chapter 5.1 --- Effectiveness of Visual Features --- p.68 / Chapter 5.2 --- Performance of Simple Sum Rule --- p.71 / Chapter 5.3 --- Performances of Individual Modalities --- p.73 / Chapter 5.4 --- Identification Tasks Using Confidence-based Weighted Sum Rule --- p.74 / Chapter 5.4.1 --- Effectiveness of WS_M_C Rule --- p.75 / Chapter 5.4.2 --- WS_M_C v.s. WS_M --- p.76 / Chapter 5.5 --- Speaker Identification Using RkNN --- p.77 / Chapter 6 --- Conclusions and Future Work --- p.78 / Chapter 6.1 --- Conclusions --- p.78 / Chapter 6.2 --- Important Follow-up Works --- p.80 / Bibliography --- p.81 / Chapter A --- Proof of Proposition 3.1 --- p.90 / Chapter B --- Proof of Proposition 3.2 --- p.93

Thesis (M.S.)--West Virginia University, 2006. / Title from document title page. Document formatted into pages; contains vii, 73 p. : ill. (some col.). Includes abstract. Includes bibliographical references (p. 70-73).

Thesis (M.S.)--Brigham Young University. Dept. of Technology, 2005. / Includes bibliographical references (p. 141-144).

The use of biometrics is an evolving component in today's society. Fingerprint recognition continues to be one of the most widely used biometric systems. This thesis explores the various steps present in a fingerprint recognition system. The study develops a working algorithm to extract fingerprint minutiae from an input fingerprint image. This stage incorporates a variety of image pre-processing steps necessary for accurate minutiae extraction and includes two different methods of ridge thinning. Next, it implements a procedure for matching sets of minutiae data. This process goes through all possible alignments of the datasets and returns the matching score for the best possible alignment. Finally, it conducts a series of matching experiments to compare the performance of the two different thinning methods considered. Results show that thinning by the central line method produces better False Non-match Rates and False Match Rates than those obtained through thinning by the block filter method. / US Navy (USN) author.

Thesis (M.S.)--West Virginia University, 2007. / Title from document title page. Document formatted into pages; contains x, 102 p. : ill. (some col.). Includes abstract. Includes bibliographical references (p. 66-67).

<p>The identification of laboratory mice has been an important issue in pharmaceutical applications ever since tests have been performed on animals. As biometric identification has become an increasingly important issue over the past decade, attempts are underway to replace traditional identification methods, which are mostly invasive and limited in code space. This thesis discusses a project that aims at identifying mice by biometrically examining the blood vessel patterns in their ears.</p><p>In the proposed algorithm, firstly, the blood vessel structure within the obtained images got enhanced before segmenting the image in blood vessel and non-blood vessel portions. In the next step a sufficient amount of unique feature points got extracted from the segmented image. The obtained feature points were afterwards used for the actual identification procedure.</p><p>Out of 20 mice, 18 could be identified successfully using the proposed algorithm.</p>

M. Tech. Computer System Engineering / A single biometric trait for authentication is widely used in some application areas where security is of high importance. However, biometric systems are susceptible to noise, intraclass variation, non-universality and spoof attacks. Thus, there is need to use algorithms that overcome all these limitations found in biometric systems. The use of multimodal biometrics can improve the performance of authentication system. This study proposed using both fingerprint and face for authentication in access system.

The identification of laboratory mice has been an important issue in pharmaceutical applications ever since tests have been performed on animals. As biometric identification has become an increasingly important issue over the past decade, attempts are underway to replace traditional identification methods, which are mostly invasive and limited in code space. This thesis discusses a project that aims at identifying mice by biometrically examining the blood vessel patterns in their ears. In the proposed algorithm, firstly, the blood vessel structure within the obtained images got enhanced before segmenting the image in blood vessel and non-blood vessel portions. In the next step a sufficient amount of unique feature points got extracted from the segmented image. The obtained feature points were afterwards used for the actual identification procedure. Out of 20 mice, 18 could be identified successfully using the proposed algorithm.