Deep Learning for Biometrics

Deep Learning Book

The first dedicated work on advances in biometric identification capabilities using deep learning techniques Covers a broad range of deep learning.

 

Table of contents (12 chapters)

  • The Functional Neuroanatomy of Face Processing: Insights from Neuroimaging and Implications for Deep Learning

    Grill-Spector, Kalanit (et al.)

    Pages 3-31

  • Real-Time Face Identification via Multi-convolutional Neural Network and Boosted Hashing Forest

    Vizilter, Yury (et al.)

    Pages 33-55

  • CMS-RCNN: Contextual Multi-Scale Region-Based CNN for Unconstrained Face Detection

    Zhu, Chenchen (et al.)

    Pages 57-79

  • Latent Fingerprint Image Segmentation Using Deep Neural Network

    Ezeobiejesi, Jude (et al.)

    Pages 83-107

  • Finger Vein Identification Using Convolutional Neural Network and Supervised Discrete Hashing

    Xie, Cihui (et al.)

    Pages 109-132

  • Iris Segmentation Using Fully Convolutional Encoder–Decoder Networks

    Jalilian, Ehsaneddin (et al.)

    Pages 133-155

  • Two-Stream CNNs for Gesture-Based Verification and Identification: Learning User Style

    Wu, Jonathan (et al.)

    Pages 159-182

  • DeepGender2: A Generative Approach Toward Occlusion and Low-Resolution Robust Facial Gender Classification via Progressively Trained Attention Shift Convolutional Neural Networks (PTAS-CNN) and Deep Convolutional Generative Adversarial Networks (DCGAN)

    Juefei-Xu, Felix (et al.)

    Pages 183-218

  • Gender Classification from NIR Iris Images Using Deep Learning.

    Tapia, Juan (et al.)

    Pages 219-239

    Gender classification from NIR iris image is a new topic with only a few papers published. All previous work on gender-from-iris tried to find the best feature extraction techniques to represent the information of the iris texture for gender classification using normalized, encoded or periocular images. However this is a new topic in deep-learning application with soft biometric. In this chapter, we show that learning gender-iris representations through the use of deep neural networks may increase the performance obtained on these tasks. To this end, we propose the application of deep-learning methods to separate the gender-from-iris images even when the amount of learning data is limited, using an unsupervised stage with Restricted Boltzmann Machine (RBM) and a supervised stage using a Convolutional Neural Network (CNN).

  • Deep Learning for Tattoo Recognition

    Di, Xing (et al.)

    Pages 241-256

  • Learning Representations for Cryptographic Hash Based Face Template Protection

    Pandey, Rohit Kumar (et al.)

    Pages 259-285

  • Deep Triplet Embedding Representations for Liveness Detection

    Pala, Federico (et al.)

    Pages 287-307

 

Advertisements

New equipment

New sensor from Iris Recognition:

Currently, the Faculty of Engineering of the Universidad Andrés Bello, has received a new Biometric Sensor iCAM TD-1OO for the capture of irises in the range near the Infrared.

We starting to build the first biometric database in Chile using iris images. This allows to develop new projects and research initiatives in the artificial intelligence group of the Faculty of Engineering (GIAAB). In addition to teaching this type of methodologies to the students through thesis of pre-degree, postgraduate, courses of computer vision and recognition of patterns.

IRIS iCAM TD-100

PROS

  • Working very fine.
  • The quality of the images.
  • Capture the iris photo automatically.
  • Capture the face manually.

CONS

  • Working only in Windows OS.
  • There is not drivers for Linux or MAC.
  • The information is very poor as well as the technical support. Link
  • You can get only information by the dealer such has Fullcrum biometrics. (recommended) link.
  • The company did not answer the request information. Link
  • The sensor did not capture video from NIR images.
  • This sensor is not supported by VeryEye SDK. (There is not diver available)

Fitness For Duty.

Fitness For Duty. “Measuring the Capability to Work”.

How the irises change after alcohol drink?

Today, many people going to work without controlling the quantities of alcohol, drugs, fatigue or sleepiness in previous days. These factors reduce the state of alert to accomplish the duties. These actions can produce enormous damage through errors.

Truck or bus drivers, plant operators, medics or healthcare workers annually cost all companies billions of dollars in reduced productivity, accidents and injuries. The insurance companies might not paid the damages because the accidents by external factors are very different to accidents produce by influence of alcohol, drugs etc.

The goal of this project is to create an equipment based on Iris measurement using dynamic or static pupillometry as a preventive control before to start the duties.

This work is developing by Dr. Juan Tapia at Universidad Andrés Bello and Optimal Solutions. Santiago, Chile.

Iris and Periocular Biometric Recognition

New Book! Iris and Periocular Biometric Recognition

Editors:Dr. Christian Rathgeb and Dr. Christoph Busch.

Biometric recognition represents an integral component of Identity Science providing a meaningful way of recognising individuals. Iris recognition has already received significant attention and is widely deployed in several large-scale-country-wide projects. More recently, periocular (the area around the eyeball) recognition has been employed to augment the biometric performance of the iris in unconstrained environments where only the ocular region is present in the image, paving the way for multi-spectral biometric recognition on mobile devices.

This book provides an overview of scientific fundamentals and principles of iris and periocular biometric recognition. It covers a wide spectrum of current research topics over six broad areas: an introduction to iris and periocular recognition; a selective overview of issues and challenges; soft biometric classification; security aspects; privacy protection and forensics; and future trends.

Book contents

Part 1) Introduction to Iris and Periocular Recognition
1* Fundamentals of Iris Biometric Recognition – Christian Rathgeb and Christoph Busch
2* An Overview of Periocular Biometrics – Fernando Alonso-Fernandez, Josef Bigun

Part 2) Issues and Challenges
3 * Robust Iris Segmentation – Peter Wild, Heinz Hofbauer, James Ferryman, Andreas Uhl
4* Iris Image Quality Metrics with Veto Power and nonlinear Importance Tailoring – John Daugman, Cathryn Downing
5 * Iris Biometric Indexing – H. Proenc¸a and J. C. Neves,
6* Identifying the Best Periocular Region for Biometric Recognition – Jonathon M. Smereka and B.V.K. Vijaya Kumar
7 * Light field cameras for presentation attack resistant robust biometric ocular system – R. Raghavendra, Kiran B. Raja, Christoph Busch

Part 3) Soft Biometric Classification
8 * Gender Classification from Near Infrared Iris Images – Juan Tapia
9 * Periocular-Based Soft Biometric Classification – Damon L. Woodard, Kalaivani Sundararajan, Nicole Tobias, and Jamie Lyle
10 * Age predictive biometrics: predicting age from iris characteristics – M´arjory Da Costa-Abreu, Michael Fairhurst and Meryem Erbilek

Part 4) Security Aspects
11 * Presentation Attack Detection in Iris Recognition – Javier Galbally and Marta Gomez-Barrero
12 * Contact lens detection in iris images – Jukka Komulainen, Abdenour Hadid and Matti Pietik¨ainen
13 * Software Attacks on Iris Recognition Systems – Marta Gomez-Barrero and Javier Galbally

Part 5) Privacy Protection and Forensics
14* Iris Biometric Template Protection – Christian Rathgeb, Johannes Wagner and Christoph Busch
15 * Privacy-Preserving Distance Computation for IrisCodes – Julien Bringer , Herv´e Chabanne, Constance Morel
16* Identifying Iris Sensors from Iris Images – Luca Debiasi, Christof Kauba and Andreas Uhl
17* Matching Iris Images Against Face Images Using a Joint Dictionary-based Sparse Representation Scheme – Raghavender Jillela and Arun Ross

Part 6) Future Trends
18* Iris Biometrics for Embedded Systems – Judith Liu-Jimenez, Raul Sanchez-Reillo
19* Mobile Iris Recognition – Akira Yonenaga, Takashi Shinzaki
20* Future Trends in Iris Recognition: An Industry Perspective – Daniel Hartung, Ji-Young Lim, Sven Utcke, Gunther Mull

Editors

Dr. Christian Rathgeb is a senior researcher with the Faculty of Computer Science, Hochschule Darmstadt, Germany. His research includes pattern recognition, iris biometrics, and privacy enhancing technologies for biometric systems. He has co-authored over 50 technical papers and a book in the field of iris biometrics. He is a principal investigator in the Center for Research in Security and Privacy (CRISP). He is a member of the European Association for Biometrics (EAB) and a Program Chair of the International Conference of the Biometrics Special Interest Group (BIOSIG).
Dr. Christoph Busch is a member of the the Department of Information Security and Communication Technology (IIK) at the Norwegian University of Science and Technology (NTNU), Norway, and holds a joint appointment with the Faculty of Computer Science, Hochschule Darmstadt, Germany. His research includes pattern recognition, multimodal and mobile biometrics, and privacy enhancing technologies for biometric systems. He is a principal investigator in the Center for Research in Security and Privacy (CRISP), a co-Founder of the European Association for Biometrics (EAB) and convener of WG3 in ISO/IEC JTC1 SC37 on Biometrics. He is a member of the steering committee of the Biometrics Special Interest Group (BIOSIG) and serves on the editorial board of IET Biometrics.

More Info: Here

Blog at WordPress.com.

Up ↑