Biometrics is the science and technology of measuring and analyzing biological data for authentication purposes. Its progress has brought in a large number of civilian and government applications. The candidate modalities used in biometrics include retinas, fingerprints, signatures, audio, faces, etc. There are two types of biometric system: single modal systems and multiple modal systems. Single modal systems perform person recognition based on a single biometric modality and are affected by problems like noisy sensor data, intra-class variations, distinctiveness and non-universality. Applying multiple modal systems that consolidate evidence from multiple biometric modalities can alleviate those problems of single modal ones. Integration of evidence obtained from multiple cues, also known as fusion, is a critical part in multiple modal systems, and it may be consolidated at several levels like feature fusion level, matching score fusion level and decision fusion level. Among biometric modalities, both audio and face modalities are easy to use and generally acceptable by users. Furthermore, the increasing availability and the low cost of audio and visual instruments make it feasible to apply such Audio-Visual (AV) systems for security applications. Therefore, this dissertation proposes an algorithm of face recognition. In addition, it has developed some novel algorithms of fusion in different levels for multiple modal biometrics, which have been tested by a virtual database and proved to be more reliable and robust than systems that rely on a single modality. / by Lin Huang. / Thesis (Ph.D.)--Florida Atlantic University, 2010. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2010. Mode of access: World Wide Web.

In this study, we investigated what informational aspects of faces could account for the ability to match an individual’s face to their voice, using only static images. In each of the first six experiments, we simultaneously presented one voice recording along with two manipulated images of faces (e.g. top half of the face, bottom half of the face, etc.), a target face and distractor face. The participant’s task was to choose which of the images they thought belonged to the same individual as the voice recording. The voices remained un-manipulated. In Experiment 7 we used eye tracking in order to determine which informational aspects of the model’s faces people are fixating while performing the matching task, as compared to where they fixate when there are no immediate task demands. We presented a voice recording followed by two static images, a target and distractor face. The participant’s task was to choose which of the images they thought belonged to the same individual as the voice recording, while we tracked their total fixation duration. In the no-task, passive viewing condition, we presented a male’s voice recording followed sequentially by two static images of female models, or vice versa, counterbalanced across participants. Participant’s results revealed significantly better than chance performance in the matching task when the images presented were the bottom half of the face, the top half of the face, the images inverted upside down, when presented with a low pass filtered image of the face, and when the inner face was completely blurred out. In Experiment 7 we found that when completing the matching task, the time spent looking at the outer area of the face increased, as compared to when the images and voice recordings were passively viewed. When the images were passively viewed, the time spend looking at the inner area of the face increased. We concluded that the inner facial features (i.e. eyes, nose, and mouth) are not necessary informational aspects of the face which allow for the matching ability. The ability likely relies on global features such as the face shape and size. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2016. / FAU Electronic Theses and Dissertations Collection

Video signature techniques based on tomography images address the problem of video identification. This method relies on temporal segmentation and sampling strategies to build and determine the unique elements that will form the signature. In this thesis an extension for these methods is presented; first a new feature extraction method, derived from the previously proposed sampling pattern, is implemented and tested, resulting in a highly distinctive set of signature elements, second a robust temporal video segmentation system is used to replace the original method applied to determine shot changes more accurately. Under a very exhaustive set of tests the system was able to achieve 99.58% of recall, 100% of precision and 99.35% of prediction precision. / by Sebastian Possos Medellin. / Thesis (M.S.C.S.)--Florida Atlantic University, 2010. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2010. Mode of access: World Wide Web.

This dissertation introduces our work on face recognition using a novel approach based on creating 3D face model from 2D face images. Together with the pose angle estimation and illumination compensation, this method can be used successfully to recognize 2D faces with 3D recognition algorithms. The results reported here were obtained partially with our own face image database, which had 2D and 3D face images of 50 subjects, with 9 different pose angles. It is shown that by applying even the simple PCA algorithm, this new approach can yield successful recognition rates using 2D probing images and 3D gallery images. The insight gained from the 2D/3D face recognition study was also extended to the case of involving 2D probing and 2D gallery images, which offers a more flexible approach since it is much easier and practical to acquire 2D photos for recognition. To test the effectiveness of the proposed approach, the public AT&T face database, which had 2D only face photos of 40 subjects, with 10 different images each, was utilized in the experimental study. The results from this investigation show that with our approach, the 3D recognition algorithm can be successfully applied to 2D only images. The performance of the proposed approach was further compared with some of the existing face recognition techniques. Studies on imperfect conditions such as domain and pose/illumination variations were also carried out. Additionally, the performance of the algorithms on noisy photos was evaluated. Pros and cons of the proposed face recognition technique along with suggestions for future studies are also given in the dissertation. / by Guan Xin. / Thesis (Ph.D.)--Florida Atlantic University, 2012. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2012. Mode of access: World Wide Web.

Video identification or copy detection is a challenging problem and is becoming increasingly important with the popularity of online video services. The problem addressed in this thesis is the identification of a given video clip in a given set of videos. For a given query video, the system returns all the instance of the video in the data set. This identification system uses video signatures based on video tomography. A robust and low complexity video signature is designed and implemented. The nature of the signature makes it independent to the most commonly video transformations. The signatures are generated for video shots and not individual frames, resulting in a compact signature of 64 bytes per video shot. The signatures are matched using simple Euclidean distance metric. The results show that videos can be identified with 100% recall and over 93% precision. The experiments included several transformations on videos. / by Gustavo A. Leon. / Thesis (M.S.C.S.)--Florida Atlantic University, 2008. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2008. Mode of access: World Wide Web.

The literature regarding biological motion suggests that people may accurately identify and recognize the gender of others using movement cues in the absence of typical identifiers. This study compared identification and gender judgments of traditional point-light stimuli to skeleton stimuli. Controlling for previous experience and execution of actions, the frequency and familiarity of movements was also considered. Watching action clips, participants learned to identify 4 male and 4 female actors. Participants then identified the corresponding point-light or skeleton displays. Although results indicate higher than chance performance, no difference was observed between stimuli conditions. Analyses did show better gender recognition for common as well as previously viewed actions. This suggests that visual experience influences extraction and application of biological motion. Thus insufficient practice in relying on movement cues for identification could explain the significant yet poor performance in biological motion point-light research. / by Sara Manuel. / Thesis (M.A.)--Florida Atlantic University, 2012. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2012. Mode of access: World Wide Web. / Mode of access: World Wide Web. / System requirements: Adobe Reader.

Underwater vehicles often use acoustics or dead reckoning for global positioning, which is impractical for low cost, high proximity applications. An optical based positional feedback system for a wave tank operated biomimetic station-keeping vehicle was made using an extended Kalman filter and a model of a nearby light source. After physical light model verification, the filter estimated surge, sway, and heading with 6 irradiance sensors and a low cost inertial measurement unit (~$15). Physical testing with video feedback suggests an average error of ~2cm in surge and sway, and ~3deg in yaw, over a 1200 cm2 operational area. This is 2-3 times better, and more consistent, than adaptations of prior art tested alongside the extended Kalman filter feedback system. The physical performance of the biomimetic platform was also tested. It has a repeatable forward velocity response with a max of 0.3 m/s and fair stability in surface testing conditions. / Includes bibliography. / Thesis (M.S.)--Florida Atlantic University, 2015. / FAU Electronic Theses and Dissertations Collection

by Meng Xiaoning. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2006. / Includes bibliographical references (leaves 99-106). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Motivation --- p.1 / Chapter 1.2 --- Overview --- p.2 / Chapter 1.3 --- Organization of the Thesis --- p.3 / Chapter 2 --- Related Research --- p.6 / Chapter 2.1 --- Information Technology in Cars --- p.6 / Chapter 2.2 --- Anti-theft Protection --- p.8 / Chapter 2.3 --- Learning Human Behaviors --- p.10 / Chapter 2.4 --- Neural Network Learning --- p.11 / Chapter 3 --- Experimental Design --- p.14 / Chapter 3.1 --- Overview --- p.14 / Chapter 3.2 --- Driving Simulation Subsystem --- p.14 / Chapter 3.3 --- Data Sensing and Capturing Subsystem --- p.15 / Chapter 3.4 --- Data Analysis Subsystem --- p.17 / Chapter 4 --- Data Preprocessing for Feature Selection --- p.23 / Chapter 4.1 --- Introduction --- p.23 / Chapter 4.2 --- Fast Fourier Transform --- p.23 / Chapter 4.3 --- Principal Component Analysis --- p.24 / Chapter 4.4 --- Independent Component Analysis --- p.26 / Chapter 5 --- Classification via Support Vector Machine --- p.28 / Chapter 5.1 --- Introduction --- p.28 / Chapter 5.1.1 --- Why Using Support Vector Machine --- p.28 / Chapter 5.1.2 --- Mathematic Description --- p.29 / Chapter 5.2 --- Problem Formulation --- p.31 / Chapter 5.3 --- Approach --- p.31 / Chapter 5.4 --- Experimental Results --- p.34 / Chapter 5.4.1 --- Preprocess Data Analysis --- p.34 / Chapter 5.4.2 --- Models Design --- p.37 / Chapter 5.5 --- Discussion --- p.44 / Chapter 6 --- Evaluation via Hidden Markov Model --- p.47 / Chapter 6.1 --- Introduction --- p.47 / Chapter 6.1.1 --- Why Using Hidden Markov Model --- p.48 / Chapter 6.1.2 --- Mathematic Description --- p.50 / Chapter 6.2 --- Problem Formulation --- p.51 / Chapter 6.3 --- Approach --- p.53 / Chapter 6.4 --- Experimental Results --- p.56 / Chapter 6.4.1 --- Model-to-model Measure --- p.56 / Chapter 6.4.2 --- Human-to-model Measure --- p.63 / Chapter 6.4.3 --- Parameters Optimization --- p.66 / Chapter 6.5 --- Discussion --- p.69 / Chapter 7 --- System Design and Implementation --- p.71 / Chapter 7.1 --- Introduction --- p.71 / Chapter 7.2 --- Hardware --- p.72 / Chapter 7.3 --- Software --- p.78 / Chapter 7.4 --- System Demonstration --- p.80 / Chapter 8 --- Conclusion and Future Work --- p.82 / Chapter 8.1 --- Contributions --- p.82 / Chapter 8.2 --- Future Work --- p.84 / Chapter A --- Hidden Markov Model Training --- p.87 / Chapter A.1 --- Forward-backward Algorithm --- p.87 / Chapter A.2 --- Baum-Welch Algorithm --- p.87 / Chapter B --- Human Driving Behavior Data --- p.90 / Chapter C --- Publications Resulted from the Study --- p.98

Cheng Po Sum. / Thesis submitted in: July 2003. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (leaves 64-67). / Abstracts in English and Chinese. / List of Figures --- p.i / List of Tables --- p.iii / Acknowledgments --- p.iv / 摘要 --- p.v / Thesis Abstract --- p.vi / Chapter 1. --- Mobile Commerce --- p.1 / Chapter 1.1 --- Introduction to Mobile Commerce --- p.1 / Chapter 1.2 --- Mobile commence payment systems --- p.2 / Chapter 1.3 --- Security in mobile commerce --- p.5 / Chapter 2. --- Mobile authentication using Fingerprint --- p.10 / Chapter 2.1 --- Authentication basics --- p.10 / Chapter 2.2 --- Fingerprint basics --- p.12 / Chapter 2.3 --- Fingerprint authentication using mobile device --- p.15 / Chapter 3. --- Design of Mobile Fingerprint Authentication Device --- p.19 / Chapter 3.1 --- Objectives --- p.19 / Chapter 3.2 --- Hardware and software design --- p.21 / Chapter 3.2.1 --- Choice of hardware platform --- p.21 / Chapter 3.3 --- Experiments --- p.25 / Chapter 3.3.1 --- Design methodology I - DSP --- p.25 / Chapter 3.3.1.1 --- Hardware platform --- p.25 / Chapter 3.3.1.2 --- Software platform --- p.26 / Chapter 3.3.1.3 --- Implementation --- p.26 / Chapter 3.3.1.4 --- Experiment and result --- p.27 / Chapter 3.3.2 --- Design methodology II ´ؤ SoC --- p.28 / Chapter 3.3.2.1 --- Hardware components --- p.28 / Chapter 3.3.2.2 --- Software components --- p.29 / Chapter 3.3.2.3 --- Implementation Department of Computer Science and Engineering --- p.29 / Chapter 3.3.2.4 --- Experiment and result --- p.30 / Chapter 3.4 --- Observation --- p.30 / Chapter 4. --- Implementation of the Device --- p.31 / Chapter 4.1 --- Choice of platforms --- p.31 / Chapter 4.2 --- Implementation Details --- p.31 / Chapter 4.2.1 --- Hardware implementation --- p.31 / Chapter 4.2.1.1 --- Atmel FingerChip --- p.32 / Chapter 4.2.1.2 --- Gemplus smart card and reader --- p.33 / Chapter 4.2.2 --- Software implementation --- p.33 / Chapter 4.2.2.1 --- Operating System --- p.33 / Chapter 4.2.2.2 --- File System --- p.33 / Chapter 4.2.2.3 --- Device Driver --- p.35 / Chapter 4.2.2.4 --- Smart card --- p.38 / Chapter 4.2.2.5 --- Fingerprint software --- p.41 / Chapter 4.2.2.6 --- Graphical user interface --- p.41 / Chapter 4.3 --- Results and observations --- p.44 / Chapter 5. --- An Application Example 一 A Penalty Ticket Payment System (PTPS) --- p.47 / Chapter 5.1 --- Requirement --- p.47 / Chapter 5.2 --- Design Principles --- p.48 / Chapter 5.3 --- Implementation --- p.52 / Chapter 5.4 --- Results and Observation --- p.57 / Chapter 6. --- Conclusions and future work --- p.62 / Chapter 7. --- References --- p.64

Pun Kwok Ho. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 106-111). / Abstracts in English and Chinese. / Chapter 1. --- Introduction --- p.1 / Chapter 1.1 --- Background --- p.1 / Chapter 1.1.1 --- Introduction to Biometrics --- p.1 / Chapter 1.1.2 --- Face Recognition in General --- p.2 / Chapter 1.1.3 --- Typical Face Recognition Systems --- p.4 / Chapter 1.1.4 --- Face Database and Evaluation Protocol --- p.5 / Chapter 1.1.5 --- Evaluation Metrics --- p.7 / Chapter 1.1.6 --- Characteristics of Mobile Devices --- p.10 / Chapter 1.2 --- Motivation and Objectives --- p.12 / Chapter 1.3 --- Major Contributions --- p.13 / Chapter 1.3.1 --- Optimization Framework --- p.13 / Chapter 1.3.2 --- Real Time Principal Component Analysis --- p.14 / Chapter 1.3.3 --- Real Time Elastic Bunch Graph Matching --- p.14 / Chapter 1.4 --- Thesis Organization --- p.15 / Chapter 2. --- Related Work --- p.16 / Chapter 2.1 --- Face Recognition for Desktop Computers --- p.16 / Chapter 2.1.1 --- Global Feature Based Systems --- p.16 / Chapter 2.1.2 --- Local Feature Based Systems --- p.18 / Chapter 2.1.3 --- Commercial Systems --- p.20 / Chapter 2.2 --- Biometrics on Mobile Devices --- p.22 / Chapter 3. --- Optimization Framework --- p.24 / Chapter 3.1 --- Introduction --- p.24 / Chapter 3.2 --- Levels of Optimization --- p.25 / Chapter 3.2.1 --- Algorithm Level --- p.25 / Chapter 3.2.2 --- Code Level --- p.26 / Chapter 3.2.3 --- Instruction Level --- p.27 / Chapter 3.2.4 --- Architecture Level --- p.28 / Chapter 3.3 --- General Optimization Workflow --- p.29 / Chapter 3.4 --- Summary --- p.31 / Chapter 4. --- Real Time Principal Component Analysis --- p.32 / Chapter 4.1 --- Introduction --- p.32 / Chapter 4.2 --- System Overview --- p.33 / Chapter 4.2.1 --- Image Preprocessing --- p.33 / Chapter 4.2.2 --- PCA Subspace Training --- p.34 / Chapter 4.2.3 --- PCA Subspace Projection --- p.36 / Chapter 4.2.4 --- Template Matching --- p.36 / Chapter 4.3 --- Optimization using Fixed-point Arithmetic --- p.37 / Chapter 4.3.1 --- Profiling Analysis --- p.37 / Chapter 4.3.2 --- Fixed-point Representation --- p.38 / Chapter 4.3.3 --- Range Estimation --- p.39 / Chapter 4.3.4 --- Code Conversion --- p.42 / Chapter 4.4 --- Experiments and Discussions --- p.43 / Chapter 4.4.1 --- Experiment Setup --- p.43 / Chapter 4.4.2 --- Execution Time --- p.44 / Chapter 4.4.3 --- Space Requirement --- p.45 / Chapter 4.4.4 --- Verification Accuracy --- p.45 / Chapter 5. --- Real Time Elastic Bunch Graph Matching --- p.49 / Chapter 5.1 --- Introduction --- p.49 / Chapter 5.2 --- System Overview --- p.50 / Chapter 5.2.1 --- Image Preprocessing --- p.50 / Chapter 5.2.2 --- Landmark Localization --- p.51 / Chapter 5.2.3 --- Feature Extraction --- p.52 / Chapter 5.2.4 --- Template Matching --- p.53 / Chapter 5.3 --- Optimization Overview --- p.54 / Chapter 5.3.1 --- Computation Optimization --- p.55 / Chapter 5.3.2 --- Memory Optimization --- p.56 / Chapter 5.4 --- Optimization Strategies --- p.58 / Chapter 5.4.1 --- Fixed-point Arithmetic --- p.60 / Chapter 5.4.2 --- Gabor Masks and Bunch Graphs Precomputation --- p.66 / Chapter 5.4.3 --- Improving Array Access Efficiency using ID array --- p.68 / Chapter 5.4.4 --- Efficient Gabor Filter Selection --- p.75 / Chapter 5.4.5 --- Fine Tuning System Cache Policy --- p.79 / Chapter 5.4.6 --- Reducing Redundant Memory Access by Loop Merging --- p.80 / Chapter 5.4.7 --- Maximizing Cache Reuse by Array Merging --- p.90 / Chapter 5.4.8 --- Optimization of Trigonometric Functions using Table Lookup. --- p.97 / Chapter 5.5 --- Summary --- p.99 / Chapter 6. --- Conclusions --- p.103 / Chapter 7. --- Bibliography --- p.106