Biometric security and privacy : opportunities & challenges in the big data era

• Other Authors: Jiang, Richard (Editor), Al-madeed, Somaya (Editor), Bouridane, Ahmed (Editor), Crookes, Danny, 1956- (Editor), Beghdadi, A. (Editor)
• Format: Electronic eBook
• Language: English
• Published: Cham, Switzerland : Springer, 2017.
• Series: Signal processing for security technologies.
• Subjects: Biometric identification.; Big data.; Artificial intelligence.; elektronické knihy; electronic books
• ISBN: 9783319473017; 9783319473000
• Physical Description: 1 online resource

This book highlights recent research advances on biometrics using new methods such as deep learning, nonlinear graph embedding, fuzzy approaches, and ensemble learning. Included are special biometric technologies related to privacy and security issues, such as quality issue, biometric template prote...

Table of Contents:

• Preface; Contents; 1 Fingerprint Quality Assessment: Matching Performance and Image Quality; 1.1 Introduction; 1.2 Background; 1.3 Trial Measures; 1.3.1 Metrics with Single Feature; 1.3.2 Segmentation-Based Metrics; 1.3.2.1 FQA via Informative Region; 1.3.2.2 FQA via Pixel-Pruning; 1.3.3 FQA via Multi-feature; 1.4 Experimental Results; 1.4.1 Software; 1.4.2 Database et Protocol; 1.4.3 Results; 1.4.3.1 ES with Quality; 1.4.3.2 Isometric Bins; 1.4.4 Discussion via Sample Utility; 1.5 Conclusion; References.
• 2 A Novel Perspective on Hand Vein Patterns for Biometric Recognition: Problems, Challenges, and Implementations2.1 Introduction; 2.2 Vein Pattern Scanning Using Optical Methods; 2.2.1 Vein Pattern Visualization; 2.2.2 Structure of a Hand Vein Recognition Device; 2.3 Problems and Challenges in Vein Pattern Applications; 2.4 Modern Perspectives on Vein Structure Recognition; 2.4.1 Ergonomics and Hand Pose Assessment in Vein pattern Identification; 2.4.2 Synthetic Vein Pattern Generation; 2.4.3 Vein Biometrics in a Connected World; 2.5 Conclusions; References.
• 3 Improving Biometric Identification Performance Using PCANet Deep Learning and Multispectral Palmprint3.1 Introduction; 3.2 Image Features; 3.3 Proposed Methodology; 3.3.1 Feature Extraction; 3.3.1.1 PCANet Deep Learning; 3.3.1.2 Flexibility Property; 3.3.2 Classification; 3.4 Experimental Results and Discussion; 3.4.1 Experimental Databases; 3.4.2 Identification Test Results; 3.4.2.1 Performance of the Unimodal Systems; 3.4.2.2 Performance of the Multimodal Systems; 3.4.3 Comparison Study; 3.5 Conclusion and Further Work; References; 4 Biometric Acoustic Ear Recognition; 4.1 Introduction.
• 4.2 Ear Biometrics and Acoustics4.2.1 The Ear as a Biometric; 4.2.2 Image Based Ear Recognition; 4.2.3 Acoustic Based Ear Recognition; 4.2.4 Acoustic Properties of The Ear; 4.2.5 Ears Coupled to Headphones; 4.3 Measuring Device; 4.4 Experiments; 4.4.1 Design Considerations; 4.4.2 Data Collection; 4.5 Data Analysis; 4.5.1 Preprocessing; 4.5.2 Initial Data Analysis; 4.5.3 Statistical Attributes; 4.5.4 Feature Selection and Extraction; 4.5.4.1 All Frequency Components; 4.5.4.2 Octave Bands; 4.5.4.3 Acoustic Properties of The Outer Ear; 4.6 Results; 4.6.1 Performance of All Frequency Components.
• 4.6.2 Performance of PCA4.6.3 Performance of Octave Bands; 4.6.4 Performance of Ear Characteristic Bands and Peaks; 4.7 Discussion and Future Work; 4.8 Conclusion; References; 5 Eye Blinking EOG Signals as Biometrics; 5.1 Introduction; 5.2 Origin of Eye Blinking EOG Signals; 5.3 Proposed Approach for Eye Blinking EOG Biometric System; 5.3.1 Data Acquisition; 5.3.2 Pre-processing; 5.3.3 Feature Extraction; 5.3.4 Feature Selection; 5.3.5 Classification; 5.3.5.1 Linear Decision Rule; 5.3.5.2 Mahalanobis Decision Rule; 5.4 Experimental Setup and Results; 5.4.1 Identification Mode.