| Document Type
|
:
|
BL
|
| Record Number
|
:
|
862761
|
| Title & Author
|
:
|
Selfie biometrics : : advances and challenges /\ Ajita Rattani, Reza Derakhshani, Arun Ross, editors.
|
| Publication Statement
|
:
|
Cham, Switzerland :: Springer,, 2019.
|
| Series Statement
|
:
|
Advances in computer vision and pattern recognition,
|
| Page. NO
|
:
|
1 online resource (ix, 380 pages) :: illustrations (some color)
|
| ISBN
|
:
|
303026971X
|
|
|
:
|
: 3030269728
|
|
|
:
|
: 3030269736
|
|
|
:
|
: 3030269744
|
|
|
:
|
: 9783030269715
|
|
|
:
|
: 9783030269722
|
|
|
:
|
: 9783030269739
|
|
|
:
|
: 9783030269746
|
|
|
:
|
9783030269715
|
| Notes
|
:
|
Includes index.
|
| Bibliographies/Indexes
|
:
|
Includes bibliographical references and index.
|
| Contents
|
:
|
Intro; Preface; Unique Features; Audience; Organization; Contents; About the Editors; 1 Introduction to Selfie Biometrics; 1.1 Mobile Biometrics; 1.2 Selfie Biometrics; 1.2.1 Types of Selfie Biometrics; 1.2.2 Selfie Biometrics and Spoof Attacks; 1.2.3 Selfie and Cloud-Based Services; 1.2.4 Selfie and Soft Biometrics; 1.3 Challenges and Future Directions; 1.4 Conclusion; References; Selfie Finger, Ocular and Face Biometrics; 2 User Authentication via Finger-Selfies; 2.1 Introduction; 2.2 Related Work; 2.2.1 Existing Databases; 2.2.2 Finger-Selfie Recognition Techniques
|
|
|
:
|
2.3 UNconstrained FingerPhoto (UNFIT) Dataset2.3.1 Database Acquisition; 2.3.2 Database Statistics; 2.3.3 Challenges; 2.3.4 Ground-Truth Annotation; 2.3.5 Experimental Protocol; 2.4 Segmentation Framework; 2.4.1 Segmentation Using VGG SegNet; 2.4.2 Implementation Details; 2.4.3 Performance Evaluation Metrics; 2.4.4 Segmentation Performance; 2.5 Finger-Selfie Recognition; 2.5.1 Feature Representations; 2.5.2 Finger-Selfie Recognition Performance; 2.6 Conclusion; References; 3 A Scheme for Fingerphoto Recognition in Smartphones; 3.1 Introduction; 3.2 Biometric Recognition Process
|
|
|
:
|
3.2.1 Acquisition3.2.2 Segmentation; 3.2.3 Enhancement; 3.2.4 Feature Extraction and Matching; 3.2.5 Quality Assessment; 3.2.6 Liveness Detection; 3.2.7 Mitigation of Nonidealities of Touchless Fingerprint Sensors; 3.3 Performance Analysis; 3.4 Conclusions; References; 4 MICHE Competitions: A Realistic Experience with Uncontrolled Eye Region Acquisition; 4.1 Introduction; 4.2 Iris Recognition and MICHE Challenges; 4.3 Challenge Setup and MICHE Dataset; 4.4 MICHE-I Challenge: Iris Segmentation; 4.4.1 Metrics Used to Evaluate the Segmentation Quality; 4.4.2 Methods Participating in MICHE-I
|
|
|
:
|
4.4.3 Some Interesting Notes on Achieved Results4.4.4 Recombination of Segmentation and Recognition Modules; 4.5 MICHE-II Challenge: Iris Recognition; 4.5.1 Methods Participating in MICHE-II; 4.5.2 Some Interesting Notes on Achieved Results; 4.6 MICHE After the Challenges; 4.7 Conclusions; References; 5 Super-resolution for Selfie Biometrics: Introduction and Application to Face and Iris; 5.1 Image Super-Resolution; 5.1.1 Reconstruction-Based Methods; 5.1.2 Learning-Based Methods; 5.1.3 Performance Metrics; 5.2 Face Super-Resolution; 5.2.1 Face Eigentransformation
|
|
|
:
|
5.2.2 Local Iterative Neighbour Embedding5.2.3 Linear Model of Coupled Sparse Support; 5.2.4 Results; 5.3 Iris Super-Resolution; 5.3.1 Iris Eigen-Patches; 5.3.2 Local Iterative Neighbour Embedding; 5.3.3 Results; 5.4 Summary and Future Trends; References; 6 Foveated Vision for Biologically Inspired Continuous Face Authentication; 6.1 Introduction; 6.2 Related Work; 6.3 Face Recognition on Mobile Devices; 6.3.1 Detection of the Face, Ocular Regions and the Landmarks; 6.3.2 Foveal and Peripheral Vision; 6.3.3 The Original HMAX Model; 6.3.4 Classification with the Softmax Layer
|
| Abstract
|
:
|
This book highlights the field of selfie biometrics, providing a clear overview and presenting recent advances and challenges. It also discusses numerous selfie authentication techniques on mobile devices. Biometric authentication using mobile devices is becoming a convenient and important means of verifying identity for secured access and services such as telebanking and electronic transactions. In this context, face and ocular biometrics in the visible spectrum has gained increased attention from the research community. However, device mobility and operation in uncontrolled environments mean that facial and ocular images captured with mobile devices exhibit substantial degradation as a result of adverse lighting conditions, specular reflections and motion and defocus blur. In addition, low spatial resolution and the small sensor of front-facing mobile cameras further degrade the sample quality, reducing the recognition accuracy of face and ocular recognition technology when integrated into smartphones. Presenting the state of the art in mobile biometric research and technology, and offering an overview of the potential problems in real-time integration of biometrics in mobile devices, this book is a valuable resource for final-year undergraduate students, postgraduate students, engineers, researchers and academics in various fields of computer engineering.
|
| Subject
|
:
|
Biometric identification.
|
| Subject
|
:
|
Biometric identification.
|
| Dewey Classification
|
:
|
006.2/48
|
| LC Classification
|
:
|
TK7882.B56
|
| Added Entry
|
:
|
Derakhshani, Reza
|
|
|
:
|
Rattani, Ajita
|
|
|
:
|
Ross, Arun A., (Arun Abraham)
|