{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/46599"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/46599","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Saliency detection via divergence analysis: a unified perspective","abstract":"Computational modeling of visual attention has been a very active area over the past few decades. Numerous models and algorithms have been proposed to detect salient regions in images and videos. We present a unified view of various bottom-up saliency detection algorithms. As these methods were proposed from intuition and principles inspired from psychophysical studies of human vision, the theoretical relations among them are unclear. In this thesis, we provide such a bridge. The saliency is defined in terms of divergence between feature distributions estimated using samples from center and surround, respectively. We explicitly show that these seemingly different algorithms are in fact closely related and derive conditions under which the methods are equivalent. We also discuss some commonly-used center-surround selection strategies. Comparative experiments on two benchmark datasets are presented to provide further insights on relative advantages of these algorithms.","abstract_html":"Computational modeling of visual attention has been a very active area over the past few decades. Numerous models and algorithms have been proposed to detect salient regions in images and videos. We present a unified view of various bottom-up saliency detection algorithms. As these methods were proposed from intuition and principles inspired from psychophysical studies of human vision, the theoretical relations among them are unclear. In this thesis, we provide such a bridge. The saliency is defined in terms of divergence between feature distributions estimated using samples from center and surround, respectively. We explicitly show that these seemingly different algorithms are in fact closely related and derive conditions under which the methods are equivalent. We also discuss some commonly-used center-surround selection strategies. Comparative experiments on two benchmark datasets are presented to provide further insights on relative advantages of these algorithms.","abstract_has_math":false,"creators":["Huang, Jia-Bin"],"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":["Ahuja, Narendra"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-01-16T17:55:39Z","date_published":"2014-01-16T17:55:39Z","updated_at":"2026-07-22T22:25:36Z","subjects":["Saliency Detection","Object detection","Visual Attention","Divergence"],"languages":["en"],"rights":["Copyright 2013 Jia-Bin Huang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/46599","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":["Huang, Jia-Bin"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2014-01-16T17:55:39Z","2013-12"]},{"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":["Saliency Detection","Object detection","Visual Attention","Divergence"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2013 Jia-Bin Huang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/46599"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Computational modeling of visual attention has been a very active area over the past few decades. Numerous models and algorithms have been proposed to detect salient regions in images and videos. We present a unified view of various bottom-up saliency detection algorithms. As these methods were proposed from intuition and principles inspired from psychophysical studies of human vision, the theoretical relations among them are unclear. In this thesis, we provide such a bridge. The saliency is defined in terms of divergence between feature distributions estimated using samples from center and surround, respectively. We explicitly show that these seemingly different algorithms are in fact closely related and derive conditions under which the methods are equivalent. We also discuss some commonly-used center-surround selection strategies. Comparative experiments on two benchmark datasets are presented to provide further insights on relative advantages of these algorithms.","Item withdrawn by Laura Spradlin (lspradl2@illinois.edu) on 2013-11-25T15:09:08Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 2 UIUC MS Thesis.rar: 2760660 bytes, checksum: 26508453356f62ca1506cd04d49138d6 (MD5) Huang_Jia-Bin.pdf: 1150827 bytes, checksum: 2cfcaf086a6ac727751c019abe5563ad (MD5)","Made available in DSpace on 2014-01-16T17:55:39Z (GMT). No. of bitstreams: 3 Jia-Bin_Huang.pdf: 1150827 bytes, checksum: 2cfcaf086a6ac727751c019abe5563ad (MD5) UIUC MS Thesis.rar: 2760660 bytes, checksum: 26508453356f62ca1506cd04d49138d6 (MD5) license.txt: 4063 bytes, checksum: 93004850c8cd6d78f3e6deaba16308b2 (MD5)"]},{"key":"dc:title","label":"Title","values":["Saliency detection via divergence analysis: a unified perspective"]}]}],"canonical_facts":{"dc:contributor":["Ahuja, Narendra"],"dc:creator":["Huang, Jia-Bin"],"dc:date":["2014-01-16T17:55:39Z","2013-12"],"dc:description":["Computational modeling of visual attention has been a very active area over the past few decades. Numerous models and algorithms have been proposed to detect salient regions in images and videos. We present a unified view of various bottom-up saliency detection algorithms. As these methods were proposed from intuition and principles inspired from psychophysical studies of human vision, the theoretical relations among them are unclear. In this thesis, we provide such a bridge. The saliency is defined in terms of divergence between feature distributions estimated using samples from center and surround, respectively. We explicitly show that these seemingly different algorithms are in fact closely related and derive conditions under which the methods are equivalent. We also discuss some commonly-used center-surround selection strategies. Comparative experiments on two benchmark datasets are presented to provide further insights on relative advantages of these algorithms.","Item withdrawn by Laura Spradlin (lspradl2@illinois.edu) on 2013-11-25T15:09:08Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 2 UIUC MS Thesis.rar: 2760660 bytes, checksum: 26508453356f62ca1506cd04d49138d6 (MD5) Huang_Jia-Bin.pdf: 1150827 bytes, checksum: 2cfcaf086a6ac727751c019abe5563ad (MD5)","Made available in DSpace on 2014-01-16T17:55:39Z (GMT). No. of bitstreams: 3 Jia-Bin_Huang.pdf: 1150827 bytes, checksum: 2cfcaf086a6ac727751c019abe5563ad (MD5) UIUC MS Thesis.rar: 2760660 bytes, checksum: 26508453356f62ca1506cd04d49138d6 (MD5) license.txt: 4063 bytes, checksum: 93004850c8cd6d78f3e6deaba16308b2 (MD5)"],"dc:identifier":["http://hdl.handle.net/2142/46599"],"dc:language":["en"],"dc:rights":["Copyright 2013 Jia-Bin Huang"],"dc:subject":["Saliency Detection","Object detection","Visual Attention","Divergence"],"dc:title":["Saliency detection via divergence analysis: a unified perspective"],"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":"2026-07-22T22:25:36Z"}