|
|
|
|
| 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 49
reviews
|
|
|
|
|
|
|
|
Unsupervised regions based segmentation using object discovery Yang B., Yu H., Hu R. Journal of Visual Communication and Image Representation 31(C): 125-137, 2015. Type: Article
Delineating a prominent object in an image by computer is an important step toward fully automated image analysis. This segmentation problem has been elusive and no viable solution has been found. A recent trend is to provide multiple ...
|
Jan 12 2016 |
|
|
|
|
|
|
Random walks in directed hypergraphs and application to semi-supervised image segmentation Ducournau A., Bretto A. Computer Vision and Image Understanding 12091-102, 2014. Type: Article
Hypergraphs are generalizations of graphs. In conventional graphs, the vertex set is partitioned into a number of pairs called edges. In hypergraphs, the vertex set is partitioned into a number of hyperedges with possibly more than two...
|
Jul 14 2015 |
|
|
|
|
|
|
Learning semantic representations of objects and their parts Mesnil G., Bordes A., Weston J., Chechik G., Bengio Y. Machine Learning 94(2): 281-301, 2014. Type: Article
Digital images are everywhere. To make those images searchable, we laboriously annotate them with a list of contents. Ideally, we want a program that does the annotation for us, but this is still an unsolved problem in image analysis. ...
|
Jul 3 2014 |
|
|
|
|
|
|
Deep hierarchies in the primate visual cortex: What can we learn for computer vision? Kruger N., Janssen P., Kalkan S., Lappe M., Leonardis A., Piater J., Rodriguez-Sanchez A., Wiskott L. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(8): 1847-1871, 2013. Type: Article
Understanding human vision processing has been the ultimate goal for many vision researchers, including machine vision developers. However, successes in specific problem domains such as face detection and gait recognition have driven t...
|
Oct 23 2013 |
|
|
|
|
|
|
Affinity learning with diffusion on tensor product graph Yang X., Prasad L., Latecki L. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(1): 28-38, 2013. Type: Article
Automated pattern recognition is a difficult problem. One of the difficult issues is how to measure the similarity of a pair of patterns. A simple Euclidean distance type measure is often insufficient, and a more complex non-Euclidean ...
|
Feb 25 2013 |
|
|
|
|
|
|
Layered graphical models for tracking partially occluded objects Ablavsky V., Sclaroff S. IEEE Transactions on Pattern Analysis and Machine Intelligence 33(9): 1758-1775, 2011. Type: Article
Automated video analysis is a hot topic in computer vision research, and many technical obstacles remain for a system to reach the level of science fiction. This paper presents one approach to advance the state of the art and, at the s...
|
Aug 13 2012 |
|
|
|
|
|
|
Behavioral interpretations of intrinsic connectivity networks Laird A., Fox P., Eickhoff S., Turner J., Ray K., McKay D., Glahn D., Beckmann C., Smith S., Fox P. Journal of Cognitive Neuroscience 23(12): 4022-4037, 2011. Type: Article
The ability to decode the neural networks in the brain has long been one of the holy grails of science. Functional magnetic resonance imaging (fMRI) has emerged as a popular procedure to study the functional roles of various parts of t...
|
Jun 13 2012 |
|
|
|
|
|
|
Adaptive mesh refinement for stochastic reaction-diffusion processes Bayati B., Chatelain P., Koumoutsakos P. Journal of Computational Physics 230(1): 13-26, 2011. Type: Article
This research paper describes a new mesoscopic-level simulator for generating time trajectories of a chemical system governed by diffusion and chemical reactions. A mesoscopic-level simulator achieves good balance between computational...
|
Nov 30 2011 |
|
|
|
|
|
|
Sparse image and signal processing: wavelets, curvelets, morphological diversity Starck J., Murtagh F., Fadili J., Cambridge University Press, New York, NY, 2010. 336 pp. Type: Book (978-0-521119-13-9)
How do we encode and store information in the brain? How do we process rich visual inputs from the retina and send them to the brain? These are longstanding questions in neuroscience and artificial intelligence. Olshausen and Field [1]...
|
Jul 19 2011 |
|
|
|
|
|
|
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 i...
|
Jul 27 2010 |
|
|
|
|
|
|
|
|
|
|
|