Pattern recognition, image processing and computer vision are closely linked areas which have seen enormous progress in the last fifty years. Their applications in our daily life, commerce and industry are growing even more rapidly than theoretical advances. Hence, the need for a new handbook in pattern recognition and computer vision every five or six years as envisioned in 1990 is fully justified and valid.
The book consists of three parts: (1) Pattern recognition methods and applications; (2) Computer vision and image processing; and (3) Systems, architecture and technology. This book is intended to capture the major developments in pattern recognition and computer vision though it is impossible to cover all topics.
The chapters are written by experts from many countries, fully reflecting the strong international research interests in the areas. This fifth edition will complement the previous four editions of the book.
- Pattern Recognition Methods and Applications:
- Syntactic Pattern Recognition: Paradigm Issues and Open Problems (Mariusz Flasinski)
- Deep Discriminative and Generative Models for Speech Pattern Recognition (Li Deng and Navdeep Jaitly)
- On Measuring and Quantifying Performance: Error Rates, Surrogate Loss, and An Example in Semi-supervised Learning (Marco Loog, Jesse H Krijthe, and Are C Jensen)
- Information Theoretic Clustering Using a k-Nearest Neighbors-based Divergence Measure (Vidar V Vikjord and Robert Jenssen)
- Pruning Trees in Random Forests for Minimizing Non Detection in Medical Imaging (Laurent Heutte, Caroline Petitjean, and Chesner Désir)
- Recent Advances on Optimum-path Forest for Data Classification: Supervised, Semi-supervised, and Unsupervised Learning (João Paulo Papa, Willian Paraguassu Amorim, Alexandre Xavier Falcão, and João Manuel R S Tavares)
- On Curvelet-based Texture Features for Pattern Classification (Ching-Chung Li and Wen-Chyi Lin)
- Computer Recognition and Evaluation of Coins (Bo-Yuan Feng, Ke Sun, Parmida Atighechian, and Ching Y Suen)
- Supervised and Unsupervised Feature Descriptors for Error-resilient Underwater Live Fish Recognition (Meng-Che Chuang, Jeng-Neng Hwang, and Kresimir Willimans)
- Model Adaptation for Personalized Music Emotion Recognition (Yi-Hsuan Yang, Ju-Chiang Wang, Yu-An Chen, and Homer H Chen)
- Computer Vision and Image Processing:
- Context Assisted Person Identification for Images and Videos (Liyan Zhang, Dmitri V Kalashnikov, and Sharad Mehrotra)
- Statistical Shape Spaces for 3D Data: A Review (Alan Brunton, Augusto Salazar, Timo Bolkart, and Stefanie Wuhrer)
- Tracking Without Appearance Descriptors (Mehrsan Javan Roshtkari and Martin D Levine)
- Knowledge Augmented Visual Learning (Ziheng Wang and Qiang Ji)
- Graph Edit Distance — Novel Approximation Algorithms (Kaspar Riesen and Horst Bunke)
- Latest Developments of LSTM Neural Networks with Applications of Document Image Analysis (Marcus Liwicki, Volkmar Frinken, and Muhammad Zeshan Afzal)
- Analyzing Remote Sensing Images with Hierarchial Morphological Representations (Gabriele Cavallaro, Mauro Dalla Mura and Jón Atli Benediktsson)
- Manifold-Based Sparse Representation for Hyperspectral Image Classification (Yuan Yan Tang and Haoliang Yuan)
- A Review of Texture Classification Methods and Their Applications in Medical Image Analysis of the Brain (Rouzbeh Maani, Sanjay Kalra, and Yee-Hong Yang)
- 3D Tomosynthesis to Detect Breast Cancer (Yanbin Lu, Mina Yousefi, John Ellenberger, Richard H Moore, Daniel B Kopans, Adam Krzyzak, and Ching Y Suen)
- System, Architecture, and Technology:
- Combining Representations for Improved Sketch Recognition (Sonya Cates)
- Visual Object Recognition with Image Retrieval (Sedat Ozer)
- Efficient Identification of Faces in Video Streams Using Low-power Multi-core Devices (Donavan Prieur, Eric Granger, Yvon Savaria, and Claude Thibeault)
- Kernel-based Learning for Fault Detection and Identification in Fuel Cell Systems (Gabriele Moser, Paola Costamagna, Andrea De Giorgi, Lissy Pellaco, Andrea Trucco, and Sebastiano B Serpico)
- Outdoor Shadow Modelling and its Applications (Lin Gu and Antonio Robles-Kelly)
- Fast Structured Tracker with Improved Motion Model Using Robust Kalman Filter (Ivan Bogun and Eraldo Ribeiro)
- Using 3D Vision for Automated Industrial Inspection (David J Michael)
- Vision Challenges in Image-based Barcode Readers (Xianju Wang and Xiangyun (Mary) Ye)
- Parallel Pattern Matching Using the Automata Processor (Matt Tanner, Matt Grimm, and Harold B Noyes)
Readership: Graduate students, academics, practitioners, researchers, computer scientists, electrical and medical engineers.
Chi Hau Chen received his PhD in electrical engineering from Purdue University in 1965, MSEE degree from University of Tennessee, Knoxville in 1962 and BSEE degree from National Taiwan University in 1959. He is currently Chancellor Professor and Professor Emeriti of electrical and computer engineering, at the University of Massachusetts Dartmouth, where he has taught since 1968. His research areas are in statistical pattern recognition and signal/image processing with applications to remote sensing, geophysical, underwater acoustics & nondestructive testing problems; as well computer vision for video surveillance; time series analysis; and neural networks.
Dr Chen has published (edited and authored) 30 books in his areas of research, including a number of books published by World Scientific Publishing. He was Associate Editor for International Journal of Pattern Recognition and Artificial Intelligence from 1986–2008. Since 2008 he has been an Editorial Board Member of Pattern Recognition Journal. Currently he is also the Series Editor in Computer Vision for World Scientific Publishing.
Dr Chen has been a Fellow of the Institute of Electrical and Electronic Engineers (IEEE) since 1988, a Life Fellow of the IEEE since 2003, Fellow of the International Association of Pattern Recognition (IAPR) since 1996, full member of the Academia NDT International since 200 and on the Fulbright Specialist Program since 2008.