| |
|
|
| |
| | Toshiro Kubota is an assistant professor in the Department of Mathematical Sciences, Susquehanna University, Selinsgrove, PA. He has been a reviewer for Computing Reviews since 1997, and has written over 30 reviews. He was born in Japan and grew up there. Eventually, he moved to the US to pursue his graduate studies and ended up staying there. He received a BS degree in instrumentation engineering from Keio University, Japan in 1988, and MS and PhD degrees in electrical engineering from the Georgia Institute of Technology, Atlanta, GA in 1989 and 1995, respectively. At Georgia Tech, he worked at the Computer Engineering Research Laboratory and designed ASIC chips for the Guidance Navigation and Control Project funded by the US Army. For his dissertation work, he developed a biologically inspired image filter design method, which has been awarded a US patent.
From 1996 until 2004, he was at the University of South Carolina, Columbia, SC. He worked on a number of research projects, including wavelet-based image analysis, funded by the Office of Naval Research, and a graph-based image segmentation project, funded by the National Science Foundation. He served as an assistant professor in the Computer Science and Engineering Department.
From 2004 to 2006, he worked as a scientist for Siemens Medical Solutions, Malvern, PA. He was a member of the Computer-Aided Diagnosis and Knowledge Solutions Group, and worked on the detection of pulmonary nodules from CT data. His work resulted in eight provisional patent applications.
From 2006 to 2010, he has been at Susquehanna University, providing a liberal arts education in mathematics and computer science to undergraduate students. His current research interests include computer vision, neural networks (both biological and artificial), medical imaging, and remote sensing. He has over 50 technical publications in these fields. He is a member of IEEE, ACM and MAA.
He also has experience in software development, and seeks to commercialize some of his research works. He started Hyperacuity.com to pursue the venture in 2004, and developed a webcam-based intruder detection program sold as shareware. He is always searching for spare time to engage in this venture. To his disappointment, he has not been able to find such time in recent years. |
| |
| |
|
Date Reviewed |
|
| |
1 - 10 of 40
reviews
|
|
|
 |
 |
 |
 |
|
Illumination invariant foreground detection using multi-subspace learning Dong Y., Han T., Desouza G. International Journal of Knowledge-based and Intelligent Engineering Systems 14(1): 31-41, 2010. Type: Article Video surveillance has become ubiquitous in our lives, causing both beneficial and harmful results. However, the trend of increasing video surveillance will continue as long as the technology for automated processing of video streams improves....
|
Jul 27 2010 |
|
 |
 |
 |
 |
|
Bayesian nonlinear principal component analysis using random fields Lian H. IEEE Transactions on Pattern Analysis and Machine Intelligence 31(4): 749-754, 2009. Type: Article The complexity of data involved in business and scientific applications has increased tremendously recently, and this trend appears to be continuing. Thus, there is an urgent need for tools that can analyze and characterize large high-dimensional ...
|
Aug 19 2009 |
|
 |
 |
 |
 |
|
Markov models for pattern recognition: from theory to applications Fink G., Springer-Verlag New York, Inc., Secaucus, NJ, 2007. 248 pp. Type: Book Our perception can extract and recognize patterns with little effort. However, after many years of research, we still can’t feasibly grant the same ability to a machine. One of the most promising and successful approaches to pattern...
|
Jul 9 2008 |
|
 |
 |
 |
 |
|
Color image segmentation for objects of interest with modified geodesic active contour method Pi L., Fan J., Shen C. Journal of Mathematical Imaging and Vision 27(1): 51-57, 2007. Type: Article The paper describes a problem of semiautomatically delineating an object of interest (OOI) from a color image, an open problem in image processing that has increased in importance as the number of color images and videos on hard drives has...
|
Sep 7 2007 |
|
 |
 |
 |
 |
|
Handbook of biomedical image analysis: volume 3: registration models (International Topics in Biomedical Engineering) Suri J., Wilson D., Laxminarayan S., Springer-Verlag New York, Inc., Secaucus, NJ, 2005. 574 pp. Type: Book, Reviews: (1 of 2) Medical imaging technologies have become indispensable for the detection, diagnosis, treatment, and prevention of a wide range of diseases. They have also proven useful in understanding the functional and anatomical organization of the brain. One ...
|
Aug 14 2006 |
|
 |
 |
 |
 |
|
Automatic Writer Identification Using Connected-Component Contours and Edge-Based Features of Uppercase Western Script Schomaker L., Bulacu M. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(6): 787-798, 2004. Type: Article Automatic writer identification is difficult, and its importance has increased as identification theft and credit card fraud have become a serious concern. Although manual writer verification and forgery detection techniques have been employed in ...
|
Jul 6 2005 |
|
 |
 |
 |
 |
|
Content driven dimensionality reduction at block level in the design of an efficient classifier for spatial multi spectral imagesĀ Rangarajan L., Nagabhushan P. Pattern Recognition Letters 25(16): 1833-1844, 2004. Type: Article The automated classification of remotely sensed data is an important research topic, as more and more such data is becoming available for scientific, military, and commercial purposes. This paper describes a new algorithm to automatically segment ...
|
Jul 5 2005 |
|
 |
 |
 |
 |
|
Quantitative computer image analysis of serum &agr;-fetoprotein rapid gold immunochromatographic dipstick assay Bioinformatics and bioengineering (Proceedings of the 4th IEEE Symposium on Bioinformatics and Bioengineering, May 19-21, 2004) 1082004. Type: Proceedings Image processing and pattern recognition offer many tools to the scientific community. However, scientists sometimes use the techniques without fully understanding their strengths and limitations, resulting in a suboptimal design. I see this...
|
Jun 24 2005 |
|
 |
 |
 |
 |
|
A variational framework for retinex Kimmel R., Elad M., Shaked D., Keshet (Kresch) R., Sobel I. International Journal of Computer Vision 52(1): 7-23, 2003. Type: Article This paper discusses the problem of decomposing a given image into its reflectance and illumination components, also called the retinex problem. The authors take the reconstruction problem into a variational setting, which has been quite popular...
|
Mar 4 2005 |
|
 |
 |
 |
 |
|
Kernel methods for pattern analysis Shawe-Taylor J., Cristianini N., Cambridge University Press, New York, NY, 2004.Type: Book “Kernel methods” refers to a set of techniques for pattern analysis that became quite popular after the introduction of the support vector machine (SVM) in the 1990s. One of the most important pattern analysis problems is...
|
Mar 4 2005 |
|
 |
 |
 |
 |
| |
|
|
| |
|
|