{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/81819"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/81819","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Learning to Segment Images Into Material and Object Classes","abstract":"This dissertation addresses the task of learning to segment images into meaningful material and object categories. With regards to materials we consider the difficult task of segmenting objects made of transparent materials such as glass. To do this we consider information in the form binary features. Unlike more traditional unary features which consider information contained within a single location, binary features which consider information between pairs of locations are used to capture the notion of transparency (i.e. being able to see through something). We begin by using this in an edge based approach to locate the edges of glass objects. Segmenting transparent regions, which is desirable in order to locate objects, is ambiguous with this binary information alone. We deal with this by treating this information as a measure of discrepancy, relating how different two regions are from one another. We then combine this with a complimentary affinity measure which relates how well two regions belong together. These two measures are then combined within a single energy function which can be optimized to segment regions of transparent material. With regards to opaque objects an initial segmentation can be constructed using local features within regions produced from an over segmentation of the image. Our interest here is in improving these local segmentations by incorporating global information. Using global features (i.e. features that consider all regions simultaneously) and synthetically generated contrastive data an energy based model is constructed to estimate the quality of a given segmentation. Based on these segmentation quality estimates we attempt to improve a given segmentation.","abstract_html":"This dissertation addresses the task of learning to segment images into meaningful material and object categories. With regards to materials we consider the difficult task of segmenting objects made of transparent materials such as glass. To do this we consider information in the form binary features. Unlike more traditional unary features which consider information contained within a single location, binary features which consider information between pairs of locations are used to capture the notion of transparency (i.e. being able to see through something). We begin by using this in an edge based approach to locate the edges of glass objects. Segmenting transparent regions, which is desirable in order to locate objects, is ambiguous with this binary information alone. We deal with this by treating this information as a measure of discrepancy, relating how different two regions are from one another. We then combine this with a complimentary affinity measure which relates how well two regions belong together. These two measures are then combined within a single energy function which can be optimized to segment regions of transparent material. With regards to opaque objects an initial segmentation can be constructed using local features within regions produced from an over segmentation of the image. Our interest here is in improving these local segmentations by incorporating global information. Using global features (i.e. features that consider all regions simultaneously) and synthetically generated contrastive data an energy based model is constructed to estimate the quality of a given segmentation. Based on these segmentation quality estimates we attempt to improve a given segmentation.","abstract_has_math":false,"creators":["McHenry, Kenton Guadron"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Ponce, Jean"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-09-25T20:20:34Z","date_published":"2015-09-25T20:20:34Z","updated_at":"2026-07-22T22:26:17Z","subjects":["Computer Science"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["(MiAaPQ)AAI3314967"],"render_values":[{"text":"(MiAaPQ)AAI3314967","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/2142/81819","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Ponce, Jean"]},{"key":"dc:creator","label":"Author","values":["McHenry, Kenton Guadron"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2015-09-25T20:20:34Z","10000-01-01","2008"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"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/2142/81819","(MiAaPQ)AAI3314967"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This dissertation addresses the task of learning to segment images into meaningful material and object categories. With regards to materials we consider the difficult task of segmenting objects made of transparent materials such as glass. To do this we consider information in the form binary features. Unlike more traditional unary features which consider information contained within a single location, binary features which consider information between pairs of locations are used to capture the notion of transparency (i.e. being able to see through something). We begin by using this in an edge based approach to locate the edges of glass objects. Segmenting transparent regions, which is desirable in order to locate objects, is ambiguous with this binary information alone. We deal with this by treating this information as a measure of discrepancy, relating how different two regions are from one another. We then combine this with a complimentary affinity measure which relates how well two regions belong together. These two measures are then combined within a single energy function which can be optimized to segment regions of transparent material. With regards to opaque objects an initial segmentation can be constructed using local features within regions produced from an over segmentation of the image. Our interest here is in improving these local segmentations by incorporating global information. Using global features (i.e. features that consider all regions simultaneously) and synthetically generated contrastive data an energy based model is constructed to estimate the quality of a given segmentation. Based on these segmentation quality estimates we attempt to improve a given segmentation.","Made available in DSpace on 2015-09-25T20:20:34Z (GMT). No. of bitstreams: 2 license.txt: 4848 bytes, checksum: 96035ab3f5e1c23cc7138a224ce498bd (MD5) 3314967.pdf: 2159245 bytes, checksum: 3bc93d22b4fb5eac274f2383140653e8 (MD5) Previous issue date: 2008","Embargo set by: Seth Robbins for item 83100 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","104 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2008."]},{"key":"dc:title","label":"Title","values":["Learning to Segment Images Into Material and Object Classes"]}]}],"canonical_facts":{"dc:contributor":["Ponce, Jean"],"dc:creator":["McHenry, Kenton Guadron"],"dc:date":["2015-09-25T20:20:34Z","10000-01-01","2008"],"dc:description":["This dissertation addresses the task of learning to segment images into meaningful material and object categories. With regards to materials we consider the difficult task of segmenting objects made of transparent materials such as glass. To do this we consider information in the form binary features. Unlike more traditional unary features which consider information contained within a single location, binary features which consider information between pairs of locations are used to capture the notion of transparency (i.e. being able to see through something). We begin by using this in an edge based approach to locate the edges of glass objects. Segmenting transparent regions, which is desirable in order to locate objects, is ambiguous with this binary information alone. We deal with this by treating this information as a measure of discrepancy, relating how different two regions are from one another. We then combine this with a complimentary affinity measure which relates how well two regions belong together. These two measures are then combined within a single energy function which can be optimized to segment regions of transparent material. With regards to opaque objects an initial segmentation can be constructed using local features within regions produced from an over segmentation of the image. Our interest here is in improving these local segmentations by incorporating global information. Using global features (i.e. features that consider all regions simultaneously) and synthetically generated contrastive data an energy based model is constructed to estimate the quality of a given segmentation. Based on these segmentation quality estimates we attempt to improve a given segmentation.","Made available in DSpace on 2015-09-25T20:20:34Z (GMT). No. of bitstreams: 2 license.txt: 4848 bytes, checksum: 96035ab3f5e1c23cc7138a224ce498bd (MD5) 3314967.pdf: 2159245 bytes, checksum: 3bc93d22b4fb5eac274f2383140653e8 (MD5) Previous issue date: 2008","Embargo set by: Seth Robbins for item 83100 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","104 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2008."],"dc:identifier":["http://hdl.handle.net/2142/81819","(MiAaPQ)AAI3314967"],"dc:language":["eng"],"dc:subject":["Computer Science"],"dc:title":["Learning to Segment Images Into Material and Object Classes"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:17Z"}