{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/81054"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/81054","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Modeling Objects Using Interest Points, Edges, and Regions","abstract":"This dissertation explores the application of different low level image features for the task of object category recognition and segmentation. In particular, it proposes novel fast and efficient models to represent object categories using interest points, edges, and regions. For interest points, a part based generate object template is proposed, which models object categories as a joint occurrence of appearance and location of texture patches around interest points. The model makes novel independence assumptions and proposes variational learning techniques which make learning and inference faster. The model is shown to have good detection and localization performance on standard datasets. This template model is enhanced for automatic object segmentation by incorporating image edge information. A model edge response which encodes the position of object edges with respect to the template is learned from image edges. Object segmentation is obtained by integrating the edge and interest point cues in a random field model. Towards object representation using regions, this thesis first presents a multiscale image segmentation algorithm which represents the image as a hierarchical tree of regions, i.e., a segmentation tree. The algorithm models edges between regions as rapidly varying ramp discontinuities, for which parameters are estimated and used to obtain the final segmentation. The thesis then proposes a model that represents object categories in terms of individual regions and their arrangement in the above segmentation tree. The performance of the model is tested with respect to its localization and segmentation accuracy on standard datasets.","abstract_html":"This dissertation explores the application of different low level image features for the task of object category recognition and segmentation. In particular, it proposes novel fast and efficient models to represent object categories using interest points, edges, and regions. For interest points, a part based generate object template is proposed, which models object categories as a joint occurrence of appearance and location of texture patches around interest points. The model makes novel independence assumptions and proposes variational learning techniques which make learning and inference faster. The model is shown to have good detection and localization performance on standard datasets. This template model is enhanced for automatic object segmentation by incorporating image edge information. A model edge response which encodes the position of object edges with respect to the template is learned from image edges. Object segmentation is obtained by integrating the edge and interest point cues in a random field model. Towards object representation using regions, this thesis first presents a multiscale image segmentation algorithm which represents the image as a hierarchical tree of regions, i.e., a segmentation tree. The algorithm models edges between regions as rapidly varying ramp discontinuities, for which parameters are estimated and used to obtain the final segmentation. The thesis then proposes a model that represents object categories in terms of individual regions and their arrangement in the above segmentation tree. The performance of the model is tested with respect to its localization and segmentation accuracy on standard datasets.","abstract_has_math":false,"creators":["Arora, Himanshu"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":["Ahuja, Narendra"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-09-25T20:09:25Z","date_published":"2015-09-25T20:09:25Z","updated_at":"2026-07-22T22:26:15Z","subjects":["Computer Science"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["(MiAaPQ)AAI3301100"],"render_values":[{"text":"(MiAaPQ)AAI3301100","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/2142/81054","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Ahuja, Narendra"]},{"key":"dc:creator","label":"Author","values":["Arora, Himanshu"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2015-09-25T20:09:25Z","10000-01-01","2007"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/81054","(MiAaPQ)AAI3301100"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This dissertation explores the application of different low level image features for the task of object category recognition and segmentation. In particular, it proposes novel fast and efficient models to represent object categories using interest points, edges, and regions. For interest points, a part based generate object template is proposed, which models object categories as a joint occurrence of appearance and location of texture patches around interest points. The model makes novel independence assumptions and proposes variational learning techniques which make learning and inference faster. The model is shown to have good detection and localization performance on standard datasets. This template model is enhanced for automatic object segmentation by incorporating image edge information. A model edge response which encodes the position of object edges with respect to the template is learned from image edges. Object segmentation is obtained by integrating the edge and interest point cues in a random field model. Towards object representation using regions, this thesis first presents a multiscale image segmentation algorithm which represents the image as a hierarchical tree of regions, i.e., a segmentation tree. The algorithm models edges between regions as rapidly varying ramp discontinuities, for which parameters are estimated and used to obtain the final segmentation. The thesis then proposes a model that represents object categories in terms of individual regions and their arrangement in the above segmentation tree. The performance of the model is tested with respect to its localization and segmentation accuracy on standard datasets.","Made available in DSpace on 2015-09-25T20:09:25Z (GMT). No. of bitstreams: 2 license.txt: 4848 bytes, checksum: 96035ab3f5e1c23cc7138a224ce498bd (MD5) 3301100.pdf: 2825790 bytes, checksum: a65dfbcb02a47e52b826ec47e6159efb (MD5) Previous issue date: 2007","Embargo set by: Seth Robbins for item 82336 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","U of I Only","92 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2007."]},{"key":"dc:title","label":"Title","values":["Modeling Objects Using Interest Points, Edges, and Regions"]}]}],"canonical_facts":{"dc:contributor":["Ahuja, Narendra"],"dc:creator":["Arora, Himanshu"],"dc:date":["2015-09-25T20:09:25Z","10000-01-01","2007"],"dc:description":["This dissertation explores the application of different low level image features for the task of object category recognition and segmentation. In particular, it proposes novel fast and efficient models to represent object categories using interest points, edges, and regions. For interest points, a part based generate object template is proposed, which models object categories as a joint occurrence of appearance and location of texture patches around interest points. The model makes novel independence assumptions and proposes variational learning techniques which make learning and inference faster. The model is shown to have good detection and localization performance on standard datasets. This template model is enhanced for automatic object segmentation by incorporating image edge information. A model edge response which encodes the position of object edges with respect to the template is learned from image edges. Object segmentation is obtained by integrating the edge and interest point cues in a random field model. Towards object representation using regions, this thesis first presents a multiscale image segmentation algorithm which represents the image as a hierarchical tree of regions, i.e., a segmentation tree. The algorithm models edges between regions as rapidly varying ramp discontinuities, for which parameters are estimated and used to obtain the final segmentation. The thesis then proposes a model that represents object categories in terms of individual regions and their arrangement in the above segmentation tree. The performance of the model is tested with respect to its localization and segmentation accuracy on standard datasets.","Made available in DSpace on 2015-09-25T20:09:25Z (GMT). No. of bitstreams: 2 license.txt: 4848 bytes, checksum: 96035ab3f5e1c23cc7138a224ce498bd (MD5) 3301100.pdf: 2825790 bytes, checksum: a65dfbcb02a47e52b826ec47e6159efb (MD5) Previous issue date: 2007","Embargo set by: Seth Robbins for item 82336 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","U of I Only","92 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2007."],"dc:identifier":["http://hdl.handle.net/2142/81054","(MiAaPQ)AAI3301100"],"dc:language":["eng"],"dc:subject":["Computer Science"],"dc:title":["Modeling Objects Using Interest Points, Edges, and Regions"],"dc:type":["text"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:15Z"}