{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/73014"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/73014","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Ontology-based image categorization","abstract":"In this thesis, we study how semantics can improve image categorization. Previous image categorization approaches mostly neglect semantics, which has two major limitations. First, object classes have semantic overlaps. For example, “sedan” is a specific kind of “car”. However, previous approaches treat “sedan” and “car” as independent and train a classifier to distinguish them, which is unreasonable. Second, image features used for classification are unified for different object classes. But this is at odds with the human perception system, which is believed to use different features for distinct objects. For example, the features used for differentiating “sedan” from “bike” should be distinct from the features used for differentiating “sedan” from “hatchback”. In this thesis, we leverage semantic ontologies to solve the aforementioned problems. We propose a Random Forest based algorithm in which the splitting of tree nodes is first determined by semantic relations among categories. Then weak attributes are automatically learned by multiple-instance learning to capture visual similarities in a hierarchical way; i.e., different local features are learned to classify objects at different semantic levels. Overall, our approach imitates the human visual system and is more advanced than previous non-ontology based approaches. We test our approach on two fine-grained image categorization datasets. The experimental results demonstrate that our approach not only outperforms the state-of-the-art approaches but also identifies semantically meaningful visual features.","abstract_html":"In this thesis, we study how semantics can improve image categorization. Previous image categorization approaches mostly neglect semantics, which has two major limitations. First, object classes have semantic overlaps. For example, “sedan” is a specific kind of “car”. However, previous approaches treat “sedan” and “car” as independent and train a classifier to distinguish them, which is unreasonable. Second, image features used for classification are unified for different object classes. But this is at odds with the human perception system, which is believed to use different features for distinct objects. For example, the features used for differentiating “sedan” from “bike” should be distinct from the features used for differentiating “sedan” from “hatchback”. In this thesis, we leverage semantic ontologies to solve the aforementioned problems. We propose a Random Forest based algorithm in which the splitting of tree nodes is first determined by semantic relations among categories. Then weak attributes are automatically learned by multiple-instance learning to capture visual similarities in a hierarchical way; i.e., different local features are learned to classify objects at different semantic levels. Overall, our approach imitates the human visual system and is more advanced than previous non-ontology based approaches. We test our approach on two fine-grained image categorization datasets. The experimental results demonstrate that our approach not only outperforms the state-of-the-art approaches but also identifies semantically meaningful visual features.","abstract_has_math":false,"creators":["Xu, Ning"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Huang, Thomas"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-01-21T19:56:03Z","date_published":"2015-01-21T19:56:03Z","updated_at":"2026-07-22T22:26:07Z","subjects":["Ontology","weak attributes","semantics","image categorization","semantic splitting","multiple-instance learning"],"languages":["en"],"rights":["Copyright 2014 Ning Xu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/73014","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Huang, Thomas"]},{"key":"dc:creator","label":"Author","values":["Xu, Ning"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2015-01-21T19:56:03Z","2017-01-22T10:15:20Z","2014-12","2015-01-21"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"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":["Ontology","weak attributes","semantics","image categorization","semantic splitting","multiple-instance learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2014 Ning Xu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/73014"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["In this thesis, we study how semantics can improve image categorization. Previous image categorization approaches mostly neglect semantics, which has two major limitations. First, object classes have semantic overlaps. For example, “sedan” is a specific kind of “car”. However, previous approaches treat “sedan” and “car” as independent and train a classifier to distinguish them, which is unreasonable. Second, image features used for classification are unified for different object classes. But this is at odds with the human perception system, which is believed to use different features for distinct objects. For example, the features used for differentiating “sedan” from “bike” should be distinct from the features used for differentiating “sedan” from “hatchback”. In this thesis, we leverage semantic ontologies to solve the aforementioned problems. We propose a Random Forest based algorithm in which the splitting of tree nodes is first determined by semantic relations among categories. Then weak attributes are automatically learned by multiple-instance learning to capture visual similarities in a hierarchical way; i.e., different local features are learned to classify objects at different semantic levels. Overall, our approach imitates the human visual system and is more advanced than previous non-ontology based approaches. We test our approach on two fine-grained image categorization datasets. The experimental results demonstrate that our approach not only outperforms the state-of-the-art approaches but also identifies semantically meaningful visual features.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2014-12-04T20:29:21Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Xu_Ning.pdf: 1051506 bytes, checksum: bcce20757581da84f25ffd1c9ffbb823 (MD5)","Made available in DSpace on 2015-01-21T19:56:03Z (GMT). No. of bitstreams: 1 Ning_Xu.pdf: 1051506 bytes, checksum: bcce20757581da84f25ffd1c9ffbb823 (MD5)","Embargo set by: Seth Robbins for item 73203 Lift date: 2017-01-21T19:56:18Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 73203 on 2017-01-22T10:15:20Z."]},{"key":"dc:title","label":"Title","values":["Ontology-based image categorization"]}]}],"canonical_facts":{"dc:contributor":["Huang, Thomas"],"dc:creator":["Xu, Ning"],"dc:date":["2015-01-21T19:56:03Z","2017-01-22T10:15:20Z","2014-12","2015-01-21"],"dc:description":["In this thesis, we study how semantics can improve image categorization. Previous image categorization approaches mostly neglect semantics, which has two major limitations. First, object classes have semantic overlaps. For example, “sedan” is a specific kind of “car”. However, previous approaches treat “sedan” and “car” as independent and train a classifier to distinguish them, which is unreasonable. Second, image features used for classification are unified for different object classes. But this is at odds with the human perception system, which is believed to use different features for distinct objects. For example, the features used for differentiating “sedan” from “bike” should be distinct from the features used for differentiating “sedan” from “hatchback”. In this thesis, we leverage semantic ontologies to solve the aforementioned problems. We propose a Random Forest based algorithm in which the splitting of tree nodes is first determined by semantic relations among categories. Then weak attributes are automatically learned by multiple-instance learning to capture visual similarities in a hierarchical way; i.e., different local features are learned to classify objects at different semantic levels. Overall, our approach imitates the human visual system and is more advanced than previous non-ontology based approaches. We test our approach on two fine-grained image categorization datasets. The experimental results demonstrate that our approach not only outperforms the state-of-the-art approaches but also identifies semantically meaningful visual features.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2014-12-04T20:29:21Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Xu_Ning.pdf: 1051506 bytes, checksum: bcce20757581da84f25ffd1c9ffbb823 (MD5)","Made available in DSpace on 2015-01-21T19:56:03Z (GMT). No. of bitstreams: 1 Ning_Xu.pdf: 1051506 bytes, checksum: bcce20757581da84f25ffd1c9ffbb823 (MD5)","Embargo set by: Seth Robbins for item 73203 Lift date: 2017-01-21T19:56:18Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 73203 on 2017-01-22T10:15:20Z."],"dc:identifier":["http://hdl.handle.net/2142/73014"],"dc:language":["en"],"dc:rights":["Copyright 2014 Ning Xu"],"dc:subject":["Ontology","weak attributes","semantics","image categorization","semantic splitting","multiple-instance learning"],"dc:title":["Ontology-based image categorization"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:07Z"}