Scharcanski J., Proença H., Du E. (eds.) Signal and Image Processing for Biometrics

Springer, 2014. — 336 p.The development of machines able to autonomously and covertly perform reliable recognition of human beings is a long-term goal in the biometrics field. Some of the biological traits used to perform biometric recognition support contactless data acquisition and can be acquired covertly. Thus, at least theoretically, the subsequent biometric recognition procedure can be performed without the subjects being aware or have knowledge of it, and can take place in uncontrolled scenarios (e.g., banks, airports, public areas, etc.). This real-world scenario brings many challenges to the pattern recognition process, essentially because the quality of the acquired data may vary depending on the acquisition conditions. The feasibility of this type of recognition has received increasing attention and is of particular interest in visual surveillance, computer forensics, threat assessment, and other security areas. There is a growing interest in the development of biometric recognition systems that operate in unconstrained conditions, and important advances have been recently been achieved in this field, in the various aspects covered in this book, ranging from the recognition of ears, eyes, faces, gait, fingerprint, handwritten signatures, altered appearances, and pattern detection and recognition issues arising in biometrics applications.
The goal of this volume is to summarize the state-of-the-art in signal and image processing techniques to newcomers to the field of biometrics and for more experienced practitioners, and to provide future directions for this exciting area. It offers a guide to the state-of-the-art, and the mainstream research work in this field is presented in an organized manner, so the reader can easily follow the trends that best suits her/his interests in this growing field.Data and Information Dimensionality in Non-cooperative Face Recognition
Remote Identification of Faces
Biometric Identification from Facial Sketches of Poor Reliability: Comparison of Human and Machine Performance
Recognizing Altered Facial Appearances Due to Aging and Disguise
Using Score Fusion for Improving the Performance of Multispectral Face Recognition
Unconstrained Ear Processing: What is Possible and What Must Be Done
Feature Quality-Based Unconstrained Eye Recognition
Speed-Invariant Gait Recognition
Quality Induced Multiclassifier Fingerprint Verification Using Extended Feature Set
Quality Measures for Online Handwritten Signatures
Human Tracking in Non-cooperative Scenarios