BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.4//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:����ԭ��
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:STANDARD
DTSTART:20181104T020000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RDATE:20191103T020000
TZNAME:EST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20190310T020000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.358801.field_event_date.0@www.wright.edu
DTSTAMP:20260220T000921Z
CREATED:20190425T173930Z
DESCRIPTION:Ph.D. Committee:  Drs. Nikolaos Bourbakis\, Advisor\, Soon Chun
 g\, Yong Pei\, and Arnab Shaw (EE) ABSTRACTThe recognition of single objec
 ts is an old research field with many techniques and robust results. The p
 robabilistic recognition of incomplete objects\, however\, remains an acti
 ve field with challenging issues associated to shadows\, illumination and 
 other visual characteristics. This dissertation presents a suite of high-l
 evel\, model-based computer vision techniques encompassing both geometric 
 and machine learning approaches to generate probabilistic matches of objec
 ts with varying degrees and forms of non-deformed incompleteness. The reco
 gnition of incomplete objects requires the formulation of a database of si
 x-sided exemplar images from which an identification can be made. The imag
 es are broken down by different algorithms followed by region and segment 
 isolation along with object level rotation and segment level synthesis fro
 m which geometric and characteristic properties are generated in a process
  known as the Local-Global (L-G) Graph method. The properties are then sto
 red into a database for processing against sample images featuring various
  missing features or non-deformed distortions in a multithreaded manner. T
 he multi-factor matching procedure uses weighted measures to determine the
  likelihood of a sample image matching one of the exemplars. The ability t
 o find a match is extensible in the future by adding additional detection 
 methods.Overall\, the results\, while promising\, show that there is still
  much work to be done. It is evident that there are many additional avenue
 s to explore related to different detection methodologies along with perfo
 rmance enhancements to be employed across both computational and memory co
 nstrained resources to drive the recognition of incomplete objects in prod
 uction systems.
DTSTART;TZID=America/New_York:20190430T120000
DTEND;TZID=America/New_York:20190430T140000
LAST-MODIFIED:20190425T181039Z
LOCATION:467 Joshi Research Center
SUMMARY:Ph.D. Dissertation Defense “Recognition and Synthesis of Incomplete
  Objects Using a Geometric Based Local-Global Graph Description” By Michae
 l Christopher Robbeloth
URL;TYPE=URI:/events/phd-dissertation-defense-%E2%80%
 9Crecognition-synthesis-incomplete-objects-using-geometric-based
END:VEVENT
END:VCALENDAR