{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/32069"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/32069","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Visual detection and recognition using local features","abstract":"Detection and recognition of objects in images is one of the most impor- tant problems in computer vision. In this thesis we adhere to a traditional bottom–up detection and recognition framework, where the objects are first localized with a sliding window detector before being identified. We make multiple contributions along this path. All of the contributions pertain to the central theme of local image features. We demonstrate improved object detection performance with our proposed feature extraction process, which generalizes the traditional feature extrac- tion methodology of pooling atomic appearance information (e.g., image gra- dients) around pixels in localized histograms. In addition, we propose a method to fuse two types of information sources in a locally discriminative manner by leveraging local class-dependent correlations. For the recognition task, we adopt a state–of–the–art metric learning method and modify it to handle unknown identities. Lastly, the computational improvements achieved through leveraging par- allelism are brought together by the Vision Video Library (ViVid), which we release as open source to the research community.","abstract_html":"Detection and recognition of objects in images is one of the most impor- tant problems in computer vision. In this thesis we adhere to a traditional bottom–up detection and recognition framework, where the objects are first localized with a sliding window detector before being identified. We make multiple contributions along this path. All of the contributions pertain to the central theme of local image features. We demonstrate improved object detection performance with our proposed feature extraction process, which generalizes the traditional feature extrac- tion methodology of pooling atomic appearance information (e.g., image gra- dients) around pixels in localized histograms. In addition, we propose a method to fuse two types of information sources in a locally discriminative manner by leveraging local class-dependent correlations. For the recognition task, we adopt a state–of–the–art metric learning method and modify it to handle unknown identities. Lastly, the computational improvements achieved through leveraging par- allelism are brought together by the Vision Video Library (ViVid), which we release as open source to the research community.","abstract_has_math":false,"creators":["Dikmen, Mert"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Huang, Thomas S.","Ahuja, Narendra","Hoiem, Derek W.","Parel, Sanjay J."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2012,"date_issued":"2012-06-27T21:31:25Z","date_published":"2012-06-27T21:31:25Z","updated_at":"2026-07-22T22:25:30Z","subjects":["Computer Vision","Image Representation","Object Detection","Object Recognition","Parallel Programming","GPU Programming","graphics processing unit (GPU)"],"languages":["en"],"rights":["Copyright 2012 Mert Dikmen"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/32069","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Huang, Thomas S.","Ahuja, Narendra","Hoiem, Derek W.","Parel, Sanjay J."]},{"key":"dc:creator","label":"Author","values":["Dikmen, Mert"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2012-06-27T21:31:25Z","2014-06-28T10:00:28Z","2012-05"]},{"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":["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 Vision","Image Representation","Object Detection","Object Recognition","Parallel Programming","GPU Programming","graphics processing unit (GPU)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2012 Mert Dikmen"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/32069"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Detection and recognition of objects in images is one of the most impor- tant problems in computer vision. In this thesis we adhere to a traditional bottom–up detection and recognition framework, where the objects are first localized with a sliding window detector before being identified. We make multiple contributions along this path. All of the contributions pertain to the central theme of local image features. We demonstrate improved object detection performance with our proposed feature extraction process, which generalizes the traditional feature extrac- tion methodology of pooling atomic appearance information (e.g., image gra- dients) around pixels in localized histograms. In addition, we propose a method to fuse two types of information sources in a locally discriminative manner by leveraging local class-dependent correlations. For the recognition task, we adopt a state–of–the–art metric learning method and modify it to handle unknown identities. Lastly, the computational improvements achieved through leveraging par- allelism are brought together by the Vision Video Library (ViVid), which we release as open source to the research community.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2012-01-12T19:15:56Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Dikmen_Mert.pdf: 1298206 bytes, checksum: 292ab30e74775522d0469d01c66f493e (MD5)","Made available in DSpace on 2012-06-27T21:31:25Z (GMT). No. of bitstreams: 2 Dikmen_Mert.pdf: 1298206 bytes, checksum: 292ab30e74775522d0469d01c66f493e (MD5) license.txt: 4060 bytes, checksum: a02518944eb03085e00da31a08c9653b (MD5)","Item marked as restricted to the 'Administrator' Group (id=1) by William Ingram (wingram2@illinois.edu) on 2012-06-27T21:32:48Z Item is restricted until 2014-06-27T21:32:23Z","Item reinstated by Sarah Shreeves (sshreeve@illinois.edu) on 2014-06-28T10:00:28Z Item was in collections: Dissertations and Theses - Electrical and Computer Engineering (ID: 446) Graduate Theses and Dissertations at Illinois (ID: 204) No. of bitstreams: 2 Dikmen_Mert.pdf: 1298206 bytes, checksum: 292ab30e74775522d0469d01c66f493e (MD5) license.txt: 4060 bytes, checksum: a02518944eb03085e00da31a08c9653b (MD5)","Item released from any restrictions by Sarah Shreeves (sshreeve@illinois.edu) on 2014-06-28T10:00:28Z"]},{"key":"dc:title","label":"Title","values":["Visual detection and recognition using local features"]}]}],"canonical_facts":{"dc:contributor":["Huang, Thomas S.","Ahuja, Narendra","Hoiem, Derek W.","Parel, Sanjay J."],"dc:creator":["Dikmen, Mert"],"dc:date":["2012-06-27T21:31:25Z","2014-06-28T10:00:28Z","2012-05"],"dc:description":["Detection and recognition of objects in images is one of the most impor- tant problems in computer vision. In this thesis we adhere to a traditional bottom–up detection and recognition framework, where the objects are first localized with a sliding window detector before being identified. We make multiple contributions along this path. All of the contributions pertain to the central theme of local image features. We demonstrate improved object detection performance with our proposed feature extraction process, which generalizes the traditional feature extrac- tion methodology of pooling atomic appearance information (e.g., image gra- dients) around pixels in localized histograms. In addition, we propose a method to fuse two types of information sources in a locally discriminative manner by leveraging local class-dependent correlations. For the recognition task, we adopt a state–of–the–art metric learning method and modify it to handle unknown identities. Lastly, the computational improvements achieved through leveraging par- allelism are brought together by the Vision Video Library (ViVid), which we release as open source to the research community.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2012-01-12T19:15:56Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Dikmen_Mert.pdf: 1298206 bytes, checksum: 292ab30e74775522d0469d01c66f493e (MD5)","Made available in DSpace on 2012-06-27T21:31:25Z (GMT). No. of bitstreams: 2 Dikmen_Mert.pdf: 1298206 bytes, checksum: 292ab30e74775522d0469d01c66f493e (MD5) license.txt: 4060 bytes, checksum: a02518944eb03085e00da31a08c9653b (MD5)","Item marked as restricted to the 'Administrator' Group (id=1) by William Ingram (wingram2@illinois.edu) on 2012-06-27T21:32:48Z Item is restricted until 2014-06-27T21:32:23Z","Item reinstated by Sarah Shreeves (sshreeve@illinois.edu) on 2014-06-28T10:00:28Z Item was in collections: Dissertations and Theses - Electrical and Computer Engineering (ID: 446) Graduate Theses and Dissertations at Illinois (ID: 204) No. of bitstreams: 2 Dikmen_Mert.pdf: 1298206 bytes, checksum: 292ab30e74775522d0469d01c66f493e (MD5) license.txt: 4060 bytes, checksum: a02518944eb03085e00da31a08c9653b (MD5)","Item released from any restrictions by Sarah Shreeves (sshreeve@illinois.edu) on 2014-06-28T10:00:28Z"],"dc:identifier":["http://hdl.handle.net/2142/32069"],"dc:language":["en"],"dc:rights":["Copyright 2012 Mert Dikmen"],"dc:subject":["Computer Vision","Image Representation","Object Detection","Object Recognition","Parallel Programming","GPU Programming","graphics processing unit (GPU)"],"dc:title":["Visual detection and recognition using local features"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:30Z"}