AI and Deep Learning in Biometric Security

Trends, Potential, and Challenges

Gaurav Jaswal, Vivek Kanhangad, Raghavendra Ramachandra, Gaurav Jaswal, Vivek Kanhangad, Raghavendra Ramachandra

• Publisher: CRC Press
• Year: 2021
• Print ISBN: 9780367422448
• eBook ISBN: 9781000291667
• Edition: 1
• Topic: Computer Science
• Subtopic: Cyber Security
• Index: Computer Science

This book provides an in-depth overview of artificial intelligence and deep learning approaches with case studies to solve problems associated with biometric security such as authentication, indexing, template protection, spoofing attack detection, ROI detection, gender classification etc.

This text highlights a showcase of cutting-edge research on the use of convolution neural networks, autoencoders, recurrent convolutional neural networks in face, hand, iris, gait, fingerprint, vein, and medical biometric traits. It also provides a step-by-step guide to understanding deep learning concepts for biometrics authentication approaches and presents an analysis of biometric images under various environmental conditions.

This book is sure to catch the attention of scholars, researchers, practitioners, and technology aspirants who are willing to research in the field of AI and biometric security.

1

Deep Learning-Based Hyperspectral Multimodal Biometric Authentication System Using Palmprint and Dorsal Hand Vein

Shuping Zhao, Wei Nie, and Bob Zhang

University of Macau

Contents

1.1 Introduction

1.2 Device Design

1.3 System Implementation

1.3.1 ROI Extraction

1.3.1.1 Hyperspectral Palmprint ROI Extraction

1.3.1.2 Hyperspectral Dorsal Hand Vein ROI Extraction

1.3.2 Feature Extraction

1.3.3 Feature Fusion and Matching

1.4 Experiments

1.4.1 Multimodal Hyperspectral Palmprint and Dorsal Hand Vein Dataset

1.4.2 Optimal Pattern and Band Selection

1.4.3 Multimodal Identification

1.4.4 Multimodal Verification

1.4.5 Computational Complexity Analysis

1.5 Conclusions

Acknowledgements

References

1.1 Introduction

Biometric recognition system has been widely used in the construction of a smart society. Many types of biometric systems, including face, iris, palmprint, palm vein, dorsal hand vein, and fingerprint, currently exist in security authentication. Palmprint recognition system is a kind of reliable authentication technology, due to the fact that palmprint has stable and rich characteristics, such as textures, local orientation features, and lines. In addition, a palmprint is user-friendly and cannot be easily captured by a hidden camera device without cooperation from the users. However, palmprint images captured using a conventional camera cannot be used in liveness detection. Palm vein is a good remedy for the weakness of palmprint acquired using a near-infrared (NIR) camera. The vein pattern is the vessel network underneath human skin. It can successfully protect against spoofing attacks and impersonation. Similar to palm vein, dorsal hand vein also has stable vein structures that do not change with age. Besides vein networks, some related characteristics to palmprint such as textures and local direction features can also be acquired.

Up to now, palmprint and dorsal hand vein-based recognition methods have achieved competitive performances in the literature. Huang et al. [1] put forward a method for robust principal line detection from the palmprint image, even if the image contained long wrinkles. Guo et al. [2] presented a binary palmprint direction encoding schedule for multiple orientation representation. Sun et al. [3] presented a framework to achieve three orthogonal line ordinal codes. Zhao et al. [4] constructed a deep neural network for palmprint feature extraction, where a convolutional neural network (CNN)-stack was constructed for hyperspectral palmprint recognition. Jia et al. presented palmprint-oriented lines in [5]. Khan et al. [6] applied the principle component analysis (PCA) to achieve a low-dimensionality feature in dorsal hand vein recognition. Khan et al. [7] obtained a low-dimensionality feature representation with Cholesky decomposition in dorsal hand vein recognition. Lee et al. [8] encoded multiple orientations using an adaptive two-dimensional (2D) Gabor filter in dorsal hand vein feature extraction.

The palmprint and dorsal hand vein recognition is usually carried out by conventional and deep learning-based methods. The conventional methods need to design a filter to extract the corresponding feature, i.e., local direction, local line, principal line, and texture. These hand-crafted algorithms usually require rich prior knowledge based on the specific application scenario. PalmCode [9] encoded palmprint features on a fixed direction by using a Gabor filter. Competitive code [10] extracted the dominant direction feature by using six Gabor filters. Xu et al. [11] encoded a competitive code aiming to achieve the accurate palmprint dominant ...

Table of contents

• Cover
• Half Title
• Series Page
• Title Page
• Copyright Page
• Table of Contents
• Preface
• Editors
• Contributors
• Chapter 1 Deep Learning-Based Hyperspectral Multimodal Biometric Authentication System Using Palmprint and Dorsal Hand Vein
• Chapter 2 Cancelable Biometrics for Template Protection: Future Directives with Deep Learning
• Chapter 3 On Training Generative Adversarial Network for Enhancement of Latent Fingerprints
• Chapter 4 DeepFake Face Video Detection Using Hybrid Deep Residual Networks and LSTM Architecture
• Chapter 5 Multi-spectral Short-Wave Infrared Sensors and Convolutional Neural Networks for Biometric Presentation Attack Detection
• Chapter 6 AI-Based Approach for Person Identification Using ECG Biometric
• Chapter 7 Cancelable Biometric Systems from Research to Reality: The Road Less Travelled
• Chapter 8 Gender Classification under Eyeglass Occluded Ocular Region: An Extensive Study Using Multi-spectral Imaging
• Chapter 9 Investigation of the Fingernail Plate for Biometric Authentication using Deep Neural Networks
• Chapter 10 Fraud Attack Detection in Remote Verification Systems for Non-enrolled Users
• Chapter 11 Indexing on Biometric Databases
• Chapter 12 Iris Segmentation in the Wild Using Encoder-Decoder-Based Deep Learning Techniques
• Chapter 13 PPG-Based Biometric Recognition: Opportunities with Machine and Deep Learning
• Chapter 14 Current Trends of Machine Learning Techniques in Biometrics and its Applications
• Index