Handbook of Vascular Biometrics.

• Superior document: Advances in Computer Vision and Pattern Recognition Series
• Author: Uhl, Andreas.
• TeilnehmendeR: Busch, Christoph.; Marcel, Sébastien.; Veldhuis, Raymond.
• Place / Publishing House: Cham : : Springer International Publishing AG,, 2019.; ©2020.
• Year of Publication: 2019
• Edition: 1st ed.
• Language: English
• Series: Advances in Computer Vision and Pattern Recognition Series
• Physical Description: 1 online resource (535 pages)

Table of Contents

Intro -- Foreword -- Preface -- Objectives -- Audience -- Organisation -- Part I: Introduction -- Part II: Hand and Finger Vein Biometrics -- Part III: Sclera and Retina Biometrics -- Part IV: Security and Privacy in Vascular Biometrics -- Acknowledgements -- Contents -- Part I Introduction -- 1 State of the Art in Vascular Biometrics -- 1.1 Introduction -- 1.1.1 Imaging Hand-Based Vascular Biometric Traits -- 1.1.2 Imaging Eye-Based Vascular Biometric Traits -- 1.1.3 Pros and Cons of Vascular Biometric Traits -- 1.2 Commercial Sensors and Systems -- 1.2.1 Hand-Based Vascular Traits -- 1.2.2 Eye-Based Vascular Traits -- 1.3 Algorithms in the Recognition Toolchain -- 1.3.1 Finger Vein Recognition Toolchain -- 1.3.2 Palm Vein Recognition Toolchain -- 1.3.3 (Dorsal) Hand Vein Recognition Toolchain -- 1.3.4 Wrist Vein Recognition Toolchain -- 1.3.5 Retina Recognition Toolchain -- 1.3.6 Sclera Recognition Toolchain -- 1.4 Datasets, Competitions and Open-Source Software -- 1.4.1 Hand-Based Vascular Traits -- 1.4.2 Eye-Based Vascular Traits -- 1.5 Template Protection -- 1.5.1 Hand-Based Vascular Traits -- 1.5.2 Eye-Based Vascular Traits -- 1.6 Presentation Attacks and Detection, and Sample Quality -- 1.6.1 Presentation Attack Detection -- 1.6.2 Biometric Sample Quality-Hand-Based Vascular Traits -- 1.6.3 Biometric Sample Quality-Eye-Based Vascular Traits -- 1.7 Mobile and On-the-Move Acquisition -- 1.7.1 Hand-Based Vascular Traits -- 1.7.2 Eye-Based Vascular Traits -- 1.8 Disease Impact on Recognition and (Template) Privacy -- 1.9 Conclusion and Outlook -- References -- 2 A High-Quality Finger Vein Dataset Collected Using a Custom-Designed Capture Device -- 2.1 Introduction -- 2.2 Overview of Finger Vein Acquisition Systems -- 2.2.1 Types of Sensors -- 2.2.2 Commercial Sensors -- 2.2.3 Sensors Developed by Academics.

2.3 University of Twente Finger Vein Capture Device -- 2.4 Description of Dataset -- 2.5 Results -- 2.5.1 Performance Analysis -- 2.6 Next-Generation Finger Vein Scanner -- 2.6.1 Overview -- 2.6.2 Illumination Control -- 2.6.3 3D Reconstruction -- 2.7 Conclusions -- 2.8 Future Work -- References -- 3 OpenVein-An Open-Source Modular Multipurpose Finger Vein Scanner Design -- 3.1 Introduction -- 3.2 Finger Vein Scanners -- 3.2.1 Light Source Positioning -- 3.2.2 Two Main Perspectives of the Finger-Dorsal and Palmar -- 3.2.3 Commercial Finger Vein Scanners -- 3.2.4 Finger Vein Prototype Scanners and Datasets in Research -- 3.3 PLUS OpenVein Finger Vein Scanner -- 3.3.1 Advantages and Differences to Existing Designs -- 3.3.2 Image Sensor, Lens and Additional Filter -- 3.3.3 Light Transmission Illuminator -- 3.3.4 Reflected Light Illuminator -- 3.3.5 Illuminator Brightness Control Board -- 3.3.6 Finger Placement Unit -- 3.3.7 Housing Parts -- 3.3.8 Capturing Software -- 3.4 PLUSVein-FV3 Finger Vein Dataset -- 3.5 Conclusion -- 3.5.1 Future Work -- References -- 4 An Available Open-Source Vein Recognition Framework -- 4.1 Introduction -- 4.2 Related Work -- 4.3 PLUS OpenVein Toolkit -- 4.3.1 Directory Structure -- 4.3.2 Settings Files -- 4.3.3 External Dependencies -- 4.4 Included Vein Recognition Schemes -- 4.4.1 Input File Handling/Supported Datasets -- 4.4.2 Preprocessing -- 4.4.3 Feature Extraction -- 4.4.4 Comparison -- 4.4.5 Comparison/Evaluation Protocols -- 4.4.6 Performance Evaluation Tools -- 4.4.7 Feature and Score-Level Fusion -- 4.5 Experimental Example -- 4.5.1 Dataset and Experimental Set-Up -- 4.5.2 Experimental Results -- 4.6 Conclusion and Future Work -- References -- Part II Hand and Finger Vein Biometrics -- 5 Use Case of Palm Vein Authentication -- 5.1 Introduction -- 5.2 Palm Vein Sensing -- 5.3 Sensor Products with Reflection Method.

5.4 Matching Performance -- 5.5 Use Cases of Palm Vein Authentication -- 5.5.1 Usage Situation -- 5.5.2 Login Authentication -- 5.5.3 Physical Access Control Systems -- 5.5.4 Payment Systems -- 5.5.5 Financial Services -- 5.5.6 Health Care -- 5.5.7 Airport Security -- 5.5.8 Government and Municipal -- 5.6 Conclusion -- References -- 6 Evolution of Finger Vein Biometric Devices in Terms of Usability -- 6.1 Introduction -- 6.1.1 Early Implementation -- 6.1.2 Commercialisation -- 6.1.3 Evolutions of the Finger Vein Biometric Devices -- 6.2 Compliance with Regulations -- 6.2.1 Use Case/Background -- 6.2.2 Usability Requirement Details -- 6.2.3 Challenges -- 6.2.4 Implementation -- 6.3 Compactness -- 6.3.1 Use Case/Background -- 6.3.2 Usability Requirement Details -- 6.3.3 Challenges -- 6.3.4 Implementation -- 6.4 Portability and Mobility -- 6.4.1 Use Case/Background -- 6.4.2 Usability Requirement Details -- 6.4.3 Challenges -- 6.4.4 Implementation -- 6.5 Universal Design -- 6.5.1 Use Case/Background -- 6.5.2 Usability Requirement Details -- 6.5.3 Challenges -- 6.5.4 Implementation -- 6.6 Durability and Anti-vandalism -- 6.6.1 Use Case/Background -- 6.6.2 Usability Requirement Details -- 6.6.3 Challenges -- 6.6.4 Implementation -- 6.7 High Throughput -- 6.7.1 Use Case/Background -- 6.7.2 Usability Requirement Details -- 6.7.3 Challenges -- 6.7.4 Implementation -- 6.8 Universality/Availability -- 6.8.1 Use Case/Background -- 6.8.2 Usability Requirement Details -- 6.8.3 Challenges -- 6.8.4 Implementation -- 6.9 Summary -- References -- 7 Towards Understanding Acquisition Conditions Influencing Finger Vein Recognition -- 7.1 Introduction -- 7.2 Varying Acquisition Conditions-A Challenging Aspect in Research and Practical Applications -- 7.3 Deployed Scanner Devices -- 7.4 Finger Vein Acquisition Conditions Dataset.

7.5 Finger Vein Recognition Toolchain and Evaluation Protocol -- 7.6 Experimental Results Analysis -- 7.7 Conclusion -- References -- 8 Improved CNN-Segmentation-Based Finger Vein Recognition Using Automatically Generated and Fused Training Labels -- 8.1 Introduction -- 8.2 Related Works -- 8.2.1 Classical Finger Vein Recognition Techniques -- 8.2.2 CNN-Based Finger Vein Recognition -- 8.2.3 Automated Generation of CNN Training Data -- 8.3 Finger Vein Pattern Extraction Using CNNs -- 8.4 Training Label Generation and Setups -- 8.5 Experimental Framework -- 8.6 Results -- 8.7 Discussion -- 8.8 Conclusion -- References -- 9 Efficient Identification in Large-Scale Vein Recognition Systems Using Spectral Minutiae Representations -- 9.1 Introduction -- 9.1.1 Organisation -- 9.1.2 Workload Reduction in Vein Identification Systems -- 9.1.3 Concept Focus -- 9.2 Workload Reduction Concepts -- 9.2.1 Efficient Data Representation -- 9.2.2 Serial Combination of SMR -- 9.2.3 Indexing Methods -- 9.2.4 Hardware Acceleration -- 9.2.5 Fusion of Concepts -- 9.3 Experiments -- 9.3.1 Experimental Setup -- 9.3.2 Performance Evaluation -- 9.3.3 Experiments Overview -- 9.4 Results -- 9.4.1 Spectral Minutiae Representation -- 9.4.2 Binary Spectral Minutiae Representation -- 9.4.3 Serial Combination of SMR -- 9.4.4 Indexing Methods -- 9.4.5 Fusion of Concepts -- 9.4.6 Discussion -- 9.5 Summary -- References -- 10 Different Views on the Finger--- Score-Level Fusion in Multi-Perspective Finger Vein Recognition -- 10.1 Introduction -- 10.2 Multi-perspective Finger Vein Biometrics -- 10.3 Multi-perspective Finger Vein Capture Device -- 10.4 Multi-perspective Finger Vein Dataset -- 10.5 Biometric Fusion -- 10.5.1 Fusion in Finger Vein Recognition -- 10.6 Experimental Analysis -- 10.6.1 Finger Vein Dataset -- 10.6.2 Finger Vein Recognition Tool chain.

10.6.3 Score-Level Fusion Strategy and Toolkit -- 10.6.4 Evaluation Protocol -- 10.6.5 Single Perspective Performance Results -- 10.6.6 Multi-perspective Fusion Results -- 10.6.7 Multi-algorithm Fusion Results -- 10.6.8 Combined Multi-perspective and Multi-algorithm Fusion -- 10.6.9 Results Discussion -- 10.7 Conclusion and Future Work -- References -- Part III Sclera and Retina Biometrics -- 11 Retinal Vascular Characteristics -- 11.1 Introduction -- 11.1.1 Anatomy of the Retina -- 11.1.2 History of Retinal Recognition -- 11.1.3 Medical and Biometric Examination and Acquisition Tools -- 11.1.4 Recognition Schemes -- 11.1.5 Achieved Results Using Our Scheme -- 11.1.6 Limitations -- 11.2 Eye Diseases -- 11.2.1 Automatic Detection of Druses and Exudates -- 11.2.2 Testing -- 11.3 Biometric Information Amounts in the Retina -- 11.3.1 Theoretical Determination of Biometric Information in Retina -- 11.3.2 Used Databases and Applications -- 11.3.3 Results -- 11.4 Synthetic Retinal Images -- 11.4.1 Vascular Bed Layer -- 11.4.2 Layers -- 11.4.3 Background Layers -- 11.4.4 Generating a Vascular Bed -- 11.4.5 Testing -- 11.4.6 Generating Synthetic Images Via Neural Network -- References -- 12 Vascular Biometric Graph Comparison: Theory and Performance -- 12.1 Introduction -- 12.2 The Biometric Graph -- 12.2.1 The Biometric Graph -- 12.2.2 Biometric Graph Extraction -- 12.3 The Biometric Graph Comparison Algorithm -- 12.3.1 BGR-Biometric Graph Registration -- 12.3.2 BGC-Biometric Graph Comparison -- 12.4 Results -- 12.4.1 Vascular Databases -- 12.4.2 Comparison of Graph Topology Across Databases -- 12.4.3 Comparison of MCS Topology in BGC -- 12.4.4 Comparison of BGC Performance Across Databases -- 12.5 Anchors for a BGC Approach to Template Protection -- 12.5.1 Dissimilarity Vector Templates for Biometric Graphs -- 12.5.2 Anchors for Registration.

12.5.3 The Search for Anchors.