Overview
- Focuses on an area of recent research interest, namely human-centric pattern recognition
- Brings to light open issues in moment-based visual pattern recognition
- Written in an easy-to-understand way without assuming prior knowledge of the theory of moments
- Includes application-oriented contexts with minimum emphasis on mathematical properties
Part of the book series: Cognitive Intelligence and Robotics (CIR)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
Table of contents (7 chapters)
Keywords
About this book
The usefulness of moments and their invariants in pattern recognition is well known. What is less well known is how orthogonal moments may be applied to specific problems in human-centric visual pattern recognition. Unlike previous books, this work highlights the fundamental issues involved in moment-based pattern recognition, from the selection of discriminative features in a high-dimensional setting, to addressing the question of how to classify a large number of patterns based on small training samples. In addition to offering new concepts that illustrate the use of statistical methods in addressing some of these issues, the book presents recent results and provides guidance on implementing the methods. Accordingly, it will be of interest to researchers and graduate students working in the broad areas of computer vision and visual pattern recognition.
Authors and Affiliations
About the authors
Tamanna Howlader received her Ph.D. in Mathematics from Concordia University, Canada. Currently, she is a Professor of Applied Statistics at the Institute of Statistical Research and Training (ISRT), University of Dhaka, Bangladesh. She is a statistician who enjoys interdisciplinary research. The articles and book chapters that she has published demonstrate novel statistical applications in the areas of image processing, computer vision, pattern recognition and public health. Tamanna has received several prestigious awards including the Sydney R. Parker Best Paper Award from the Journal of Circuits, Systems and Signal Processing published by Springer Nature. She is a member of the International Statistical Institute.
Dimitrios Hatzinakos received his Ph.D. in Electrical Engineering from Northeastern University, Boston, MA, in 1990, and currently serves as a Professor at the Department of Electrical and Computer Engineering, University of Toronto (UofT), Toronto, Canada. He is the co-founder and since 2009 the Director and the Chair of the management committee of the Identity, Privacy and Security Institute (IPSI) at the UofT. His research interests and expertise are in the areas of multimedia signal processing, multimedia security, multimedia communications and biometric systems. He is the author/co-author of more than 300 papers in technical journals and conference proceedings; he has contributed to 18 books, and he holds seven patents in his areas of interest. He is a Fellow of the IEEE, a Fellow of the Engineering Institute of Canada, and a member of the Professional Engineers of Ontario, and the Technical Chamber of Greece.
Bibliographic Information
Book Title: Orthogonal Image Moments for Human-Centric Visual Pattern Recognition
Authors: S. M. Mahbubur Rahman, Tamanna Howlader, Dimitrios Hatzinakos
Series Title: Cognitive Intelligence and Robotics
DOI: https://doi.org/10.1007/978-981-32-9945-0
Publisher: Springer Singapore
eBook Packages: Computer Science, Computer Science (R0)
Copyright Information: Springer Nature Singapore Pte Ltd. 2019
Hardcover ISBN: 978-981-32-9944-3Published: 24 October 2019
Softcover ISBN: 978-981-32-9947-4Published: 24 October 2020
eBook ISBN: 978-981-32-9945-0Published: 11 October 2019
Series ISSN: 2520-1956
Series E-ISSN: 2520-1964
Edition Number: 1
Number of Pages: XII, 149
Number of Illustrations: 16 b/w illustrations, 42 illustrations in colour
Topics: Computer Imaging, Vision, Pattern Recognition and Graphics