Full Description
Biometric authentication is increasingly gaining popularity in a large spectrum ofapplications,rangingfromgovernmentprograms(e. g. ,nationalIDcards,visas for international travel,and the ?ght against terrorism) to personal applications such as logical and physical access control. Although a number of e?ective - lutions are currently available, new approaches and techniques are necessary to overcomesomeofthelimitationsofcurrentsystemsandtoopenupnewfrontiers in biometric research and development. The 30 papers presented at Biometric Authentication Workshop 2004 (BioAW 2004) provided a snapshot of current research in biometrics, and identify some new trends. This volume is composed of?vesections:facerecognition,?ngerprintrecognition,templateprotectionand security, other biometrics, and fusion and multimodal biometrics. For classical biometrics like ?ngerprint and face recognition, most of the papers in Sect. 1 and 2 address robustness issues in order to make the biometric systems work in suboptimal conditions: examples include face detection and recognition - der uncontrolled lighting and pose variations, and ?ngerprint matching in the case of severe skin distortion.
Benchmarking and interoperability of sensors and liveness detection are also topics of primary interest for ?ngerprint-based s- tems. Biometrics alone is not the solution for complex security problems. Some of the papers in Sect. 3 focus on designing secure systems; this requires dealing with safe template storage, checking data integrity, and implementing solutions in a privacy-preserving fashion. The match-on-tokens approach, provided that current accuracy and cost limitations can be satisfactorily solved by using new algorithms and hardware, is certainly a promising alternative. The use of new biometric indicators like eye movement, 3D ?nger shape, and soft traits (e. g.
Contents
Face Recognition.- Face Recognition Based on Locally Salient ICA Information.- Pose Invariant Face Recognition Under Arbitrary Unknown Lighting Using Spherical Harmonics.- Biometric Face Authentication Using Pixel-Based Weak Classifiers.- Null Space Approach of Fisher Discriminant Analysis for Face Recognition.- Statistical Learning of Evaluation Function for ASM/AAM Image Alignment.- Towards a Robust Face Detector.- Automatic Detection of the Optimal Acceptance Threshold in a Face Verification System.- Fingerprint Recognition.- Registration and Modeling of Elastic Deformations of Fingerprints.- Benchmarking of Fingerprint Sensors.- Detecting Liveness in Fingerprint Scanners Using Wavelets: Results of the Test Dataset.- Fingerprint Distortion Measurement.- Study of the Distinctiveness of Level 2 and Level 3 Features in Fragmentary Fingerprint Comparison.- Biometric Sensor Interoperability: A Case Study in Fingerprints.- Efficient Fingerprint Image Enhancement for Mobile Embedded Systems.- Template Protection and Security.- Capacity and Examples of Template-Protecting Biometric Authentication Systems.- Toward Ubiquitous Acceptance of Biometric Authentication: Template Protection Techniques.- Approximate Confidence Intervals for Estimation of Matching Error Rates of Biometric Identification Devices.- Architectures for Biometric Match-on-Token Solutions.- A Secure Protocol for Data Hiding in Compressed Fingerprint Images.- Other Biometrics.- Palmprint Authentication System for Civil Applications.- Writer Identification Using Finger-Bend in Writing Signature.- 3D Finger Biometrics.- Eye Movements in Biometrics.- Integrating Faces, Fingerprints, and Soft Biometric Traits for User Recognition.- Robust Encoding of Local Ordinal Measures: A General Framework of Iris Recognition.- A Novel Digitizing Pen for the Analysis of Pen Pressure and Inclination in Handwriting Biometrics.- An Off-line Signature Verification System Based on Fusion of Local and Global Information.- Fusion and Multimodal Biometrics.- Fingerprint Verification by Decision-Level Fusion of Optical and Capacitive Sensors.- Fusion of HMM's Likelihood and Viterbi Path for On-line Signature Verification.- A New Approach on Multimodal Biometrics Based on Combining Neural Networks Using AdaBoost.
