Face Recognition Across the Imaging Spectrum

This authoritative text/reference presents a comprehensive review of algorithms and techniques for face recognition (FR), with an emphasis on systems that can be reliably used in operational environments. Insights are provided by an international team of pre-eminent experts into the processing of multispectral and hyperspectral face images captured under uncontrolled environments. These discussions cover a variety of imaging sensors ranging from state-of-the-art visible and infrared imaging sensors, to RGB-D and mobile phone image sensors. A range of different biometric modalities are also examined, including face, periocular and iris. This timely volume is a mine of useful information for researchers, practitioners and students involved in image processing, computer vision, biometrics and security.

Reviews the major operational problems and current solutions in the area of human identification Presents a specific focus on face biometrics using sensors that cover the electromagnetic spectrum more broadly than visible-band cameras Demonstrates how multi-spectral facial recognition technology can be used in a real-world setting Includes supplementary material: sn.pub/extras

Inhalt

An Overview of Spectral Imaging of Human Skin toward Face Recognition.- Collection of Multi-Spectral Biometric Data for Cross-Spectral Identification Applications.- Hyperspectral Face Databases for Facial Recognition Research.- MWIR-to-Visible and LWIR-to-Visible Face Recognition Using Partial Least Squares and Dictionary Learning.- Local Operators and Measures for Heterogeneous Face Recognition.- Assessment of Facial Recognition System Performance in Realistic Operating Environments.- Understanding Thermal Face Detection: Challenges and Evaluation.- Face Recognition Systems under Spoofing Attacks.- for Biometric Applications.- Multispectral Ocular Biometrics.