Plenary Lecture
Handwritten Digit Recognition Algorithms
Professor Milan Tuba
John Naisbitt University
Graduate School of Computer Science
Belgrade, Serbia
E-mail: tuba@ieee.org
Abstract: Object recognition is an important and active research field in the area of image processing and computer vision. Optical character recognition is one subfield of object recognition while digit recognition is a widely studied part of that subfield. Digit recognition is used in post offices for sorting the mail, in banks for reading checks, for license plate recognition, street number recognition, etc. Digit recognition can be done from images of printed digits or handwritten digits. Recognition of printed digits is easier because printed digits have regular shape while the same handwritten digit can be written in many different ways. Template matching is an old object recognition technique which is not suitable for handwritten digit recognition due to numerous variants in writing style, angle of writing, etc. Supervised learning methods are used with more success for handwritten digit recognition where support vector machines are among the latest and most successful methods. Feature extraction is a very important step and success of the classification strongly depends on it. Sometimes it is possible to get a very good classification even with rather simple feature set by using an appropriate support vector machine. However, tuning support vector machine can introduce some hard optimization problems for which swarm intelligence optimization algorithms were proven to be adequate tools. In this plenary lecture some successful handwritten digit recognition algorithms will be presented.
Brief Biography of the Speaker: Milan Tuba is the Dean of Graduate School of Computer Science and Provost for mathematical and technical sciences at John Naisbitt University of Belgrade. He received B. S. in Mathematics, M. S. in Mathematics, M. S. in Computer Science, M. Ph. in Computer Science, Ph. D. in Computer Science from University of Belgrade and New York University. From 1983 to 1994 he was in the U.S.A. first as a graduate student and teaching and research assistant at Vanderbilt University in Nashville and Courant Institute of Mathematical Sciences, New York University and later as Assistant Professor of Electrical Engineering at Cooper Union School of Engineering, New York. During that time he was the founder and director of Microprocessor Lab and VLSI Lab, leader of scientific projects and theses supervisor. From 1994 he was Assistant Professor of Computer Science and Director of Computer Center at University of Belgrade, from 2001 Associate Professor, Faculty of Mathematics, University of Belgrade, and from 2004 also a Professor of Computer Science and Dean of the College of Computer Science, Megatrend University Belgrade. He was teaching more than 20 graduate and undergraduate courses, from VLSI Design and Computer Architecture to Computer Networks, Operating Systems, Image Processing, Calculus and Queuing Theory. His research interest includes mathematical, queuing theory and heuristic optimizations applied to computer networks, image processing and combinatorial problems. Prof. Tuba is the author or coauthor of more than 150 scientific papers and coeditor or member of the editorial board or scientific committee of number of scientific journals and conferences. Member of the ACM, IEEE, AMS, SIAM, IFNA.