Chan Ka Cheong. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (leaves 77-85). / Abstracts in English and Chinese. / Chapter 1. --- Introduction --- p.1 / Chapter 1.1 --- Introduction to Fingerprint Verification --- p.1 / Chapter 1.1.1 --- Biometrics --- p.1 / Chapter 1.1.2 --- Fingerprint History --- p.2 / Chapter 1.1.3 --- Fingerprint characteristics --- p.4 / Chapter 1.1.4 --- A Generic Fingerprint Matching System Architecture --- p.6 / Chapter 1.1.5 --- Fingerprint Verification and Identification --- p.8 / Chapter 1.1.7 --- Biometric metrics --- p.10 / Chapter 1.2 --- Embedded system --- p.12 / Chapter 1.2.1 --- Introduction to embedded systems --- p.12 / Chapter 1.2.2 --- Embedded systems characteristics --- p.12 / Chapter 1.2.3 --- Performance evaluation of a StrongARM processor --- p.13 / Chapter 1.3 --- Objective -An embedded fingerprint verification system --- p.16 / Chapter 1.4 --- Organization of the Thesis --- p.17 / Chapter 2 --- Literature Reviews --- p.18 / Chapter 2.1 --- Fingerprint matching overviews --- p.18 / Chapter 2.1.1 --- Minutiae-based fingerprint matching --- p.20 / Chapter 2.2 --- Fingerprint image enhancement --- p.21 / Chapter 2.3 --- Orientation field Computation --- p.22 / Chapter 2.4 --- Fingerprint Segmentation --- p.24 / Chapter 2.5 --- Singularity Detection --- p.25 / Chapter 2.6 --- Fingerprint Classification --- p.27 / Chapter 2.7 --- Minutia extraction --- p.30 / Chapter 2.7.1 --- Binarization and thinning --- p.30 / Chapter 2.7.2 --- Direct gray scale approach --- p.32 / Chapter 2.7.3 --- Comparison of the minutiae extraction approaches --- p.35 / Chapter 2.8 --- Minutiae matching --- p.37 / Chapter 2.8.1 --- Point matching --- p.37 / Chapter 2.8.2 --- Structural matching technique --- p.38 / Chapter 2.9 --- Summary --- p.40 / Chapter 3. --- Implementation --- p.41 / Chapter 3.1 --- Fast Fingerprint Matching System Overview --- p.41 / Chapter 3.1.1 --- Typical Fingerprint Matching System --- p.41 / Chapter 3.1.2. --- Fast Fingerprint Matching System Overview --- p.41 / Chapter 3.2 --- Orientation computation --- p.43 / Chapter 3.21 --- Orientation computation --- p.43 / Chapter 3.22 --- Smooth orientation field --- p.43 / Chapter 3.3 --- Fingerprint image segmentation --- p.45 / Chapter 3.4 --- Reference Point Extraction --- p.46 / Chapter 3.5 --- A Classification Scheme --- p.51 / Chapter 3.6 --- Finding A Small Fingerprint Matching Area --- p.54 / Chapter 3.7 --- Fingerprint Matching --- p.57 / Chapter 3.8 --- Minutiae extraction --- p.59 / Chapter 3.8.1 --- Ridge tracing --- p.59 / Chapter 3.8.2 --- cross sectioning --- p.60 / Chapter 3.8.3 --- local maximum determination --- p.61 / Chapter 3.8.4 --- Ridge tracing marking --- p.62 / Chapter 3.8.5 --- Ridge tracing stop criteria --- p.63 / Chapter 3.9 --- Optimization technique --- p.65 / Chapter 3.10 --- Summary --- p.66 / Chapter 4. --- Experimental results --- p.67 / Chapter 4.1 --- Experimental setup --- p.67 / Chapter 4.2 --- Fingerprint database --- p.67 / Chapter 4.3 --- Reference point accuracy --- p.67 / Chapter 4.4 --- Variable number of matching minutiae results --- p.68 / Chapter 4.5 --- Contribution of the verification prototype --- p.72 / Chapter 5. --- Conclusion and Future Research --- p.74 / Chapter 5.1 --- Conclusion --- p.74 / Chapter 5.2 --- Future Research --- p.74 / Bibliography --- p.77

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.

M.Ing. (Electrical and Electronic Engineering Technology) / Automated Fingerprint Recognition Systems (AFRSs) have not been very effective so far in matching poor quality fingerprints because the challenges involved in low quality fingerprint matching are quite different from high quality fingerprint matching. The difficulty is due to three main reasons: (i) poor quality of fingerprints in terms of the clarity of ridge information due to harsh working conditions, diseases and aging, (ii) failure to acquire adequate minutiae points after segmentation and (iii) large non-linear distortion due to pressure variations which causes ridges to deform. Thus, low quality fingerprint recognition is a difficult problem which still needs more attention. This is because the accuracy of a fingerprint matching module heavily depends on the quality of the fingerprint probe image. Poor quality fingerprints lead to maximization of False Acceptance Rate (FAR) instead of True Acceptance Rate (TAR). As a result, researchers have suggested that extended features must be incorporated to improve accuracy. These features have been successfully used by Latent Print Experts (LPEs) for crime investigation purposes to increase matching accuracy for fingerprints collected from crime scenes with those stored in the national or international databases. There are three categories of fingerprint features: (i) level 1 (e.g. delta), (ii) level 2 (e.g. minutiae) and (iii) level 3 or extended features (e.g. pores). In this work, improvements have been made through fusion of minutiae and extended feature scores together with the fingerprint image quality. However, fusion algorithms designed so far are not adaptive, i.e. they assume that the effect of the quality of the image on the matching score is the same for different matchers based on different features. To test this assumption, this work adopted an algorithm from the literature that first assigns quality score to different regions of a fingerprint. Quality scores assigned to each region of the segmented fingerprint was mapped to extracted minutiae and extended features (pores). The overall quality rating of each of these were calculated as the sum of all quality scores assigned to regions. This procedure helped the designed fusion algorithm to assign more weight on highly reliable features and less weight on unreliable features. Two experiments conducted for rating minutiae and pore features that are based on this procedure, showed that quality scores for features under study do not stay constant. An adaptive weighted sum fusion algorithm was designed, implemented, tested and compared to non-adaptive algorithms, namely, simple sum and weighted sum fusion. The proposed adaptive weighted sum differs from traditional weighted sum fusion algorithm in that it uses weights assigned to each feature based on the quality map of each region of the fingerprint as opposed to the whole image. The performance of the system was tested using PlyU High Resolution Fingerprint (HRF) Database. Two performance measures were used to rate the proposed algorithm in comparison with simple sum and traditional weighted sum, namely, Area Under the Curve (AUC) and Equal Error Rate (EER). Both these performance measures showed that the algorithm proposed in this work outperforms both simple sum and traditional weighted sum fusion approaches. The proposed algorithm yields an improvement of 8% and 13.33% in EER and AUC, respectively for weighted sum fusion and 2% and 4.8% in EER and AUC, respectively for simple sum fusion.

A dissertation submitted to the Faculty of Science, University of the Witwatersrand, Johannesburg, in fulfilment of requirements for the degree of Master of Science, School of Computer Science and Applied Mathematics. May 2017. / Biometric features have been widely implemented to be utilized for forensic and civil applications. Amongst many different kinds of biometric characteristics, the fingerprint is globally accepted and remains the mostly used biometric characteristic by commercial and industrial societies due to its easy acquisition, uniqueness, stability and reliability. There are currently various effective solutions available, however the fingerprint identification is still not considered a fully solved problem mainly due to accuracy and computational time requirements. Although many of the fingerprint recognition systems based on minutiae provide good accuracy, the systems with very large databases require fast and real time comparison of fingerprints, they often either fail to meet the high performance speed requirements or compromise the accuracy. For fingerprint matching that involves databases containing millions of fingerprints, real time identification can only be obtained through the implementation of optimal algorithms that may utilize the given hardware as robustly and efficiently as possible. There are currently no known distributed database and computing framework available that deal with real time solution for fingerprint recognition problem involving databases containing as many as sixty million fingerprints, the size which is close to the size of the South African population. This research proposal intends to serve two main purposes: 1) exploit and scale the best known minutiae matching algorithm for a minimum of sixty million fingerprints; and 2) design a framework for distributed database to deal with large fingerprint databases based on the results obtained in the former item. / GR2018

published_or_final_version / abstract / Computer Science / Doctoral / Doctor of Philosophy

by Zhao Feng. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2002. / Includes bibliographical references (leaves 64-68). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgments --- p.vi / Table of Contents --- p.vii / List of Figures --- p.ix / List of Tables --- p.x / Chapter Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Automatic Personal Identification --- p.1 / Chapter 1.2 --- Biometrics --- p.2 / Chapter 1.2.1 --- Objectives --- p.2 / Chapter 1.2.2 --- Operational Mode --- p.3 / Chapter 1.2.3 --- Requirements --- p.3 / Chapter 1.2.4 --- Performance Evaluation --- p.4 / Chapter 1.2.5 --- Biometric Technologies --- p.4 / Chapter 1.3 --- Fingerprint --- p.6 / Chapter 1.3.1 --- Applications --- p.6 / Chapter 1.3.2 --- Advantages of Fingerprint Identification --- p.7 / Chapter 1.3.3 --- Permanence and Uniqueness --- p.8 / Chapter 1.4 --- Thesis Overview --- p.8 / Chapter 1.5 --- Summary --- p.9 / Chapter Chapter 2 --- Fingerprint Identification --- p.10 / Chapter 2.1 --- History of Fingerprints --- p.10 / Chapter 2.2 --- AFIS Architecture --- p.12 / Chapter 2.3 --- Fingerprint Acquisition --- p.15 / Chapter 2.4 --- Fingerprint Representation --- p.16 / Chapter 2.5 --- Fingerprint Classification --- p.18 / Chapter 2.6 --- Fingerprint Matching --- p.20 / Chapter 2.7 --- Challenges --- p.21 / Chapter 2.8 --- Combination Schemes --- p.22 / Chapter 2.9 --- Summary --- p.23 / Chapter Chapter 3 --- Live-Scan Fingerprint Database --- p.24 / Chapter 3.1 --- Live-Scan Fingerprint Sensors --- p.24 / Chapter 3.2 --- Database Features --- p.24 / Chapter 3.3 --- Filename Description --- p.28 / Chapter Chapter 4 --- Preprocessing for Skeleton-Based Minutiae Extraction --- p.30 / Chapter 4.1 --- Review of Minutiae-based Methods --- p.31 / Chapter 4.2 --- Skeleton-based Minutiae Extraction --- p.32 / Chapter 4.2.1 --- Preprocessing --- p.33 / Chapter 4.2.2 --- Validation of Bug Pixels and Minutiae Extraction --- p.40 / Chapter 4.3 --- Experimental Results --- p.42 / Chapter 4.4 --- Summary --- p.44 / Chapter Chapter 5 --- Post-Processing --- p.46 / Chapter 5.1 --- Review of Post-Processing Methods --- p.46 / Chapter 5.2 --- Post-Processing Algorithms --- p.47 / Chapter 5.2.1 --- H-Point --- p.47 / Chapter 5.2.2 --- Termination/Bifurcation Duality --- p.48 / Chapter 5.2.3 --- Post-Processing Procedure --- p.49 / Chapter 5.3 --- Experimental Results --- p.52 / Chapter 5.4 --- Summary --- p.54 / Chapter Chapter 6 --- Conclusions and Future Work --- p.58 / Chapter 6.1 --- Conclusions --- p.58 / Chapter 6.2 --- Problems and Future Works --- p.59 / Chapter 6.2.1 --- Problem 1 --- p.59 / Chapter 6.2.2 --- Problem 2 --- p.61 / Chapter 6.2.3 --- Problem 3 --- p.61 / Chapter 6.2.4 --- Future Works --- p.62 / Bibliography --- p.64

M.Ing. (Electrical and Electronic Engineering) / Please refer to full text to view abstract

Yeung Hoi Wo. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 81-88). / Abstracts in English and Chinese. / Chapter 1. --- Introduction --- p.10 / Chapter 1.1 --- Biometric Systems --- p.1 / Chapter 1.2 --- Comparison of Biometrics --- p.2 / Chapter 1.3 --- Introduction of Fingerprint --- p.6 / Chapter 1.3.1 --- History of Fingerprint --- p.6 / Chapter 1.3.2 --- Fingerprint Analysis --- p.8 / Chapter 1.4 --- Fingerprint Verification --- p.13 / Chapter 1.4.1 --- Correlation Based Verification: --- p.13 / Chapter 1.4.2 --- Minutiae Based Verification: --- p.15 / Chapter 1.4.3 --- Ridge Feature-Based Verification: --- p.16 / Chapter 1.5 --- Evaluation of Verification Systems --- p.17 / Chapter 1.6 --- Difficulties of Fingerprint Verification --- p.22 / Chapter 1.7 --- Contributions --- p.25 / Chapter 1.8 --- Organization of the Thesis --- p.26 / Chapter 2. --- Two-Pass Direct Gray-Scale for Minutiae Detection --- p.28 / Chapter 2.1 --- Introduction --- p.28 / Chapter 2.2 --- Background Information --- p.29 / Chapter 2.3 --- Two-Pass Direct Gray Scale --- p.34 / Chapter 2.3.1 --- First Pass of TPD --- p.38 / Chapter 2.3.2 --- Second Pass of TPD --- p.41 / Chapter 2.4 --- Other Implementation Details --- p.44 / Chapter 2.4.1 --- Foreground Detection --- p.45 / Chapter 2.4.2 --- Region of Interest Detection --- p.48 / Chapter 2.4.3 --- Matching Methodology --- p.52 / Chapter 2.5 --- Experimental Results --- p.58 / Chapter 2.6 --- Summary --- p.62 / Chapter 3. --- Image Mosaicking and Template Synthesis --- p.63 / Chapter 3.1 --- Introduction --- p.63 / Chapter 3.2 --- Background Information --- p.65 / Chapter 3.3 --- Template Synthesis and Image Mosaicking --- p.66 / Chapter 3.3.1 --- Template Alignment --- p.66 / Chapter 3.3.2 --- Template Synthesis --- p.68 / Chapter 3.3.3 --- Image Mosaicking --- p.70 / Chapter 3.4 --- Experiments --- p.72 / Chapter 3.5 --- Summary --- p.75 / Chapter 4. --- Conclusion and Future Investigations --- p.77 / References --- p.81

Sha Lifeng. / "December 2004." / Thesis (Ph.D.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (p. 115-122) / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. Ann Arbor, MI : ProQuest Information and Learning Company, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Mode of access: World Wide Web. / Abstracts in English and Chinese.

M.Sc. (Information Technology) / Biometrics is a unique method used to identify humans by distinct biological characterises. In recent years biometrics are showing up everywhere from homes, workplaces, schools and banks. This identification method is rapidly replacing existing methods such as passwords since it offers a higher level of security compared to existing methods. Fingerprints are the most common biometric choice. However fingerprint biometrics is showing limitations. Since fingerprints are an external trait, it can be exposed to many situations (cuts, dirt, wear and tear, and skin conditions) that may impact the biometric captured. These factors can cause security and usability issues. There have been a number of successful attempts such as alteration of fingerprints and gummy fingers which are used to bypass fingerprint readers. An emerging biometric called finger-vein recognition was invented to overcome the issues that fingerprint biometrics have. Finger-vein recognition which is based on the vascular patterns that exist inside the finger, claim to have superior usability characteristics where less false acceptance or rejections occur. Since the finger-vein recognition is based on an internal trait it is assumed that external factors such as scars or even dirt will not affect the biometric collected. This dissertation aims to investigate the limitations of fingerprints and to determine whether finger-vein recognition can address these limitations. During the course of the dissertation applicable fields such as construction and mining will be identified for finger-vein recognition where fingerprint recognition has shown weakness. Together, fingerprint and finger-vein technologies will be used in a mining industry to perform minor experiments. The results of these experiments will be used to determine if finger-vein addresses the fundamental limitations of fingerprint biometrics in these industries. The main purposes of the dissertation will be to investigate finger-vein technology, the applicable fields and whether finger-vein recognition can solve the problems fingerprint recognition imposes in certain industries.