News
Simplicity and Complexity of Digital Content Comparison
The School of Computing, College of Arts, Architecture and Humanities, Computing and Information Technology, and the Clemson University Cyberinstitute are pleased to host Peter Bajcsy, Ph.D., a leader who brings computer science into humanities, arts and social science fields. Bajcsy will speak on "Simplicity and Complexity of Digital Content Comparison" Wednesday, February 23, from 4:00-5:30 PM at the Student Senate Chambers.
Dr. Bajcsy's talk will address the problem of modeling digital content comparisons in the context of information preservation and integration. Content comparison is the basic operation in data searching, grouping, classification, change detection, matching, verification, validation and many data integration activities. Content comparisons depend on the type of digital content, complexity of the content, application specific comparison criteria, and variables associated with comparison software/hardware configurations.
Bajcsy will present a general approach to a comprehensive content-based file-to-file comparison as well as the methodology for data integration using several comparison methods. Within this general approach, the modeling effort involves (a) decomposing any comparison into primitive operations, (b) identifying the modeling space of generic file data representations, content characteristics and comparison measures, (c) accommodating comparisons that require content alignment, and (d) designing computational time prediction models in order to support computational scalability in a computer cloud. In his presentation, Bajcsy will demonstrate the use of theoretical models in on-line services and desktop solutions.
Bio: Peter Bajcsy has earned his Ph.D. degree from the Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, IL, 1997, and M.S. degree from the Electrical Engineering Department, University of Pennsylvania, Philadelphia, PA, 1994. He is currently with the National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign, Illinois, leading the Image Spatial Data Analysis group. Peter has been working on problems related to (1) theoretical modeling and experimental understanding of multi-instrument measurement systems generating multi-dimensional multi-variate data, (2) automation of common image pre-processing and analysis tasks in bio-medical, geo-spatial and humanity domains, and (3) development of archival preservation frameworks and novel cyber-environments. In the past, he worked on real-time machine vision problems for semiconductor industry and synthetic aperture radar (SAR) technology for government contracting industry.
