Samuel Kozaitis

Samuel Kozaitis}

Contact Information

Professor
Electrical and Computer Engineering
College of Engineering
F.W. Olin Engineering, 348
Phone: 8060
Email: kozaitis@fit.edu

Web & Social Networking

Visit My Website

Publications

S. P. Kozaitis, and T. Young, Denoising using Adaptive Thresholding and Higher Order Statistics, in Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering VII, , H. H. Szu, F. J. Agee, Eds., Proc. SPIE 7343, (2009), DOI: 7343OF

S. P. Kozaitis, Improved feature detection in ECG signals through denoising, Journal of Signal and Imaging Systems Engineering, vol. 1(2), 108-114 (2008)

M. Ouendeno, and S. P. Kozaitis, Using denoising to improve image fusion performance, Journal of Signal and Imaging Systems vol. 1(2), 127-134 (2008)

M. Ouendeno, and S. P. Kozaitis, Wavelet-based fusion approach using unique reconstruction approach, in Independent Component Analyses, Wavelets, Unsupervised Nano-Biomimetic Sensors and Neural Networks V, H. H. Szu, Ed., Proc. SPIE 6576, 65760G-1 - 65760G-7 (2007)

S. P. Kozaitis, Denoising of aerial imagery using higher-order statistics, In proceeding of the Third IASTED International Conference on Signal Processing, Pattern Recognition, Pattern Recognition, and Applications, SPPRA 2006, February 15 17, Innsbruck, Austria, paper 520-155 (2006)

S. Kozaitis, and R.H. Cofer, Lineal feature detection using multiresolution wavelet filters, Photogrammetric Engineering & Remote Sensing, vol. 71, No. 6, 689-697 (2005)

T. Ostrem, and S.P. Kozaitis, Product-based Multiresolution Image Fusion, in, Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2005, B. V. Dasarathy, Ed., Proc. SPIE 5813, 173-179 (2005)

S. P. Kozaitis, and A. Ingun, Speckle denoising using wavelet transforms and higher-order statistics, in Visual Information Processing XIII, Z. Rahman, R. A. Schowengerdt, and S. E. Reichenbach, Eds., Proc. SPIE 5438, 222-228 (2004)

Research & Project Interests

Much of his work involves wavelet-based processing or higher-order correlations to, reduce noise, fuse, or automatically detect features, in signals and images. For example, a new method has been developed to fuse imagery from disparate sensors, road detection has been performed in aerial imagery using a method based on linear feature detection, and features have been recovered from heavily degraded signals corrupted by noise.

Keywords

Image Fusion
Signal Denoising
Automated Feature Extraction

Professor
Electrical and Computer Engineering , College of Engineering

Professional Experience

Dr. Kozaitis is currently a professor in the Department of Electrical and Computer Engineering, where he supervises research in image fusion and signal detection related to pattern recognition. He graduated with a Ph.D in electrical engineering from Wayne State University in 1986 and worked for the General Motors Research Laboratory, Wayne State University, and Digital Optics Inc. From 1988 - 1997, he spent summers at the U.S. Air Force Photonics Center of Rome Laboratory. In addition, he worked the Summers of 2000 – 2001 at NASA, Kennedy Space Center, FL. He also performed consulting for government and industry and is on the program committee of the Technical Committee on Pattern Recognition of IASTED (International Association of Science and Technology Development) and the advisory board of the Journal of Engineering Research. He also served as chairman of the SPIE Conference, “Geo-Spatial Image and Data Exploitation Developments and Applications,” and IASTED conferences on Image Processing.

Educational Background

B.S. Wayne State University 1982
M.S. Wayne State University 1983
Ph.D. Wayne State University 1986

Current Research

Denoising of signals and images

Automated feature extraction

Image sensor fusion