Lecture Series in Pattern Recognition
题 目（TITLE）:Applications of Graph Based Pattern Recognition
讲 座 人（SPEAKER）:Prof. Horst Bunke (University of Bern)
主 持 人 (CHAIR):Prof. Chenglin Liu
时 间 (TIME):10:00AM, May 10 (Thursday), 2012
地 点 (VENUE):The Second Meeting Room, 13th floor
The discipline of Pattern Recognition is traditionally divided into the statistical and the structural approach. While statistical pattern recognition is characterized by the use of feature vectors for pattern representation, structural pattern recognition is based on symbolic data structures, such as strings trees and graphs. In this talk we will focus on graphs exclusively, which include strings and trees as special cases.
Structural pattern recognition possesses, on the one hand, a great degree of flexibility and power. But it suffers, on the other hand, from the high computational complexity of many of its algorithms. In this talk we review some applications where this problem was overcome. In particular, we address the fields of document analysis, handwriting recognition, human action recognition from video data, brain state decoding based on functional magnetic imaging data, and computer network monitoring, where methods from graph based pattern recognition have been successfully applied.
Horst Bunke joined the University of Bern as a Professor of Computer Science in 1984. He is now a Professor Emeritus. Horst Bunke served as 1st Vice-President and Acting President of the International Association for Pattern Recognition (IAPR). He is a Fellow of the IAPR, former Editor-in-Charge of the International Journal of Pattern Recognition and Artificial Intelligence, former Editor-in-Chief of the journal Electronic Letters of Computer Vision and Image Analysis, Editor-in-Chief of the book series Machine Perception and Artificial Intelligence by World Scientific Publ. Co., former Advisory Editor of Pattern Recognition, Associate Editor of Acta Cybernetica and Frontiers of Computer Science, and former Associate Editor of the International Journal of Document Analysis and Recognition, and Pattern Analysis and Applications.
Horst Bunke is the recipient of the 2010 KS Fu Prize, awarded by the IAPR. Moreover, he received the IAPR/ICDAR Outstanding Achievements Award in 2009 and an honorary doctor degree from the University of Szeged, Hungary, in 2007. He held visiting positions at the Chinese Academy of Science, Beijing (1987, and currently in 2012), the IBM Los Angeles Scientific Center (1989), the University of Szeged, Hungary (1991), the University of South Florida at Tampa (1991, 1996, 1998-2007 yearly), the University of Nevada at Las Vegas (1994), Kagawa University, Takamatsu, Japan (1995), Curtin University, Perth, Australia (1999), Australian National University, Canberra (2005), Autonomous University, Barcelona (2005, 2012), and NICTA, Brisbane (2009) and Melbourne (2011). Horst Bunke has close to 700 publications, including over 40 authored, co-authored, edited or co-edited books and special editions of journals. His h-index is 53, as determined by Google Scholar and harzing.com software. In the DBLP Computer Science Bibliography, which captures more than 1.9 million papers from the whole discipline of Computer Science, Horst Bunke ranks among the 90 most prolific authors in Computer Science.