Show simple item record

dc.contributor.advisorBoult, Terrance
dc.contributor.authorBendale, Abhijit
dc.contributor.committeememberKalita, Jugal
dc.contributor.committeememberLewis, Rory
dc.contributor.committeememberMarcel, Sebastien
dc.contributor.committeememberZhou, Xiaobo
dc.date.accessioned2016-01-26T17:41:26Z
dc.date.available2016-01-26T17:41:26Z
dc.date.submitted2015-12
dc.descriptionIncludes bibliographical references.
dc.description.abstractAs humans, we encounter countless objects daily. We effortlessly recognize object across variations despite the fact that the objects might vary in size, scale, translation or rotation. Humans can identify previously seen objects and posses the ability to learn new instances with minimal or no supervision. Human visual system continues to learn and adapt to ever changing surroundings. In recent years, there have been significant advances in the field of computer based recognition systems. While significant strides have been made towards building automated recognition systems, these systems face multiple challenges when operating in evolving environments. Operational issues such as changing data distributions, perturbations in input/output conditions and ever changing requirements of the system users, pose challenges in operational environments. In this work we highlight specific operational challenges such as handling partial information, incremental model adaptation, large-scale classification and propose solutions towards addressing these challenges
dc.identifierBendale_uccs_0892D_10110.pdf
dc.identifier.urihttp://hdl.handle.net/10976/166538
dc.languageEnglish
dc.publisherUniversity of Colorado Colorado Springs. Kraemer Family Library
dc.rightsCopyright of the original work is retained by the author.
dc.titleOpen World Recognition
dc.typeThesis
thesis.degree.disciplineCollege of Engineering and Applied Science-Computer Science
thesis.degree.grantorUniversity of Colorado Colorado Springs
thesis.degree.levelDoctoral
thesis.degree.nameDoctor of Philosophy (Ph.D.)


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record