Nikolaos G. Bourbakis, Ph. D.

Director, Information Technology Research Institute
OBR Distinguished Professor of Information Technology

Dr. Bourbakis received his B.S. degree in mathematics from the National University of Athens, Greece, and his Ph.D. in computer science and computer engineering from the Department of Computer Engineering & Informatics, University of Patras, Greece.
Previous academic positions include Associate Director of the Center on Intelligent Systems, Director of the Image-Video-Vision & Applied AI Research Laboratory, Professor of Electrical Engineering with joint appointment to the Computer Science Department at SUNY-Binghamton, Professor and Laboratory Director at the Technical University of Crete, Greece, and Assistant Professor at George Mason University.

Dr. Bourbakis’ industrial experience includes service at IBM, CA and Soft Sight, NY. He is founder and Vice President of AIIS, Inc., NY. He pursues research in Applied AI, Machine Vision, Bioinformatics/Bioengineering, Information Security, and Parallel/ Distributed Processing funded by USA and European government and industry. His research work has been internationally recognized and has won several prestigious awards.

He is the founder and EIC of the International Journal on AI Tools, the Editor-in-Charge of a Research Series of Books in AI (WS Publisher), Founder and EIC of the International Journal on Bioinformatics and Bioengineering, (KAP upcoming), and the Founder and General Chair of several International IEEE Computer Society Conferences, Symposia and Workshops. He is an IEEE Fellow, a Distinguished IEEE Computer Society Speaker, an NSF University Research Programs Evaluator, an IEEE Computer Society Golden Core Member, and an Official Nominator of the National Academy of Achievements for Computer Science Programs. He is also listed in WHO’S WHO in Engineering, in Science, in Education, in Intellectuals, and in Computer Engineering.

Dr. Bourbakis’ Publications
Koutsougeras, C. and Bourbakis, N, “A 3-D visual inspection, diagnosis and analysis system of PCBs,” Int. Journal Intelligent Systems Engineering, accepted 2002.

Bourbakis, N., and Mortazavi, M., “A VLSI design-synthesis methodology at the transistor layout level,” VLSI Design Journal, accepted to appear 2002.

Bourbakis, N., Koutsougeras, C. and Mertoguno, S., “A knowledge based image tool for VLSI reverse engineering: the layout version,” IEEE Trans on SMC, to appear in 2002.

Bourbakis, N., “Emulating human visual perception for measuring differences in images using an SPN graph approach,” IEEE T-SMC, vol. 32, 2, pp. 191-201, 2002.

Bourbakis, N., “Low resolution target tracking and recognition from a sequence of images,” Int. Journal AIT, vol. 11, 4, 2002.

Sikolski, R. and Bourbakis, N, “A parallel, pipeline image transformations system,” Int. Journal on Computer & EE, vol. 28, pp. 279-310, 2002.

Goldman, D. and Bourbakis, N., “Well-shaped skeletons & fast computation of the (3, 4) distance transformation,” SPIE Journal Electronic Imaging, vol. 11, June 2002.

Mannicam, S. and Bourbakis, N, “Image lossless compression and encryption using SCAN fractals,” PR Society J. Pattern Recognition, vol. 34, 6, 2001.

Yang, Y., Bourbakis, N. and Mertoguno, S., “Design of the Kydon’s RISC processor,” Journal Microprocessor & Microsystems, vol. 25, 1, pp.1-18, 2001.

Dorst, G. and Bourbakis, N., “A hybrid hardware system for real-time image lossless compression,” Int. Journal Micro processor and Microsystems, vol. 25, 1, pp.19-31, 2001.

Zong, L. and Bourbakis, N., “Digital video & digital TV: Comparison and future directions, Int. J. Real-Time Imaging,” vol. 7, pp. 545-556, 2001.

Bourbakis, N, “A fusion based method for 3-D perceived representation of images,” SPIE Society Optical Engineering Journal, vol. 40, 4, pp. 618-626, April 2001.

Bourbakis, N., “A document processing methodology: separating text from images,” IFAC, IJEAAI, vol. 14, pp. 35-42, 2001.

Spano, S. and Bourbakis, N., “A fuzzy-like controlled multi-fingered robotic hand,” Int. Journal IS&R, vol. 30, pp. 209-226, 2001.

Yuan, X., Mogzadeh, A., Goldman, D. and Bourbakis, N., “A fuzzy-like approach to edge detection in colored images,” IAPR Pattern Analysis and Applications, vol. 4, 4, pp. 272-282, 2001.

Bourbakis, N., Editor, IEEE Bioinformatics and Bioengineering Proceedings, IEEE Computer Society Press, 2001, 280 pages.

ITRI Research Projects

Bourbakis, N., Co-PI, “Intelligent Computerized Embroidery Design Automation for the Textile Insustry,” NSF-STTR, February 2001 – August 2002.

Research proposed here focuses on two distinct problems, the first being the segmentation of color images. This is a problem that has been widely studied since machine vision first evolved as a research area. However, the vast majority of this research has predominantly focused on segmentation as a means of preprocessing to enhance the performance of subsequent recognition mechanisms. Thus, the needs of applications such as OCR (optical character recognition) or handwriting recognition as well as other recognition applications have largely shaped the requirements and targeted performance of segmentation mechanisms. However, for the application proposed here, the artwork being scanned is often quite unique and does not usually conform to specific predefined recognizable objects. Additionally, since the ultimate goal is to produce an accurate reproduction of the scanned image, the aesthetic accuracy of the segmentation approach is very important. The second area of research proposed pertains to the interpretation of singular locations within thin “stroke-like” regions of an image. Numerous researchers have studied this problem with a specific focus being placed on applications that require the interpretation of overlapping handwritten strokes. Here again, the targeted applications have shaped much of the research that has occurred on this subject. As a result, research proposed here suggests a new approach that would provide a more robust solution better suited to the problem at hand. More specifically, past work has predominantly focused on using template based feature matching and other heuristic based methods to interpret parts of a region where multiple regular regions (i.e. strokes) overlap or intersect. These approaches have tended to generalize much of the context surrounding the singularity to enhance recognition performance. Unfortunately this generalization will cause problems when preserving and interpreting the artistic detail of a singularity, which is paramount.