{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/20282"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/20282","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Learning and feature selection in stereo matching","abstract":"A novel stereo matching algorithm is presented which integrates learning, feature, selection, and surface reconstruction. First, a new instance based learning (IBL) algorithm is used to generate an approximation to the optimal feature set for matching. In addition, the importance of two separate kinds of knowledge, image dependent knowledge and image independent knowledge, is discussed. Second, an adaptive method for refining the feature set is developed. This adaptive method analyzes the feature error to locate areas of the image which would lead to false matches. Then these areas are used to glide the search through feature space towards maximizing the class separation distance between the correct match and the false matches. Third, a self-diagnostic method is developed for determining when a priori knowledge is necessary for finding the correct match. If the a priori knowledge is necessary, then a surface reconstruction model is used to discriminate between match possibilities. The algorithm is comprehensively tested against fixed feature set algorithms and against a traditional pyramid algorithm. Finally, extensive empirical results based on a large set of real images are presented and discussed.","abstract_html":"A novel stereo matching algorithm is presented which integrates learning, feature, selection, and surface reconstruction. First, a new instance based learning (IBL) algorithm is used to generate an approximation to the optimal feature set for matching. In addition, the importance of two separate kinds of knowledge, image dependent knowledge and image independent knowledge, is discussed. Second, an adaptive method for refining the feature set is developed. This adaptive method analyzes the feature error to locate areas of the image which would lead to false matches. Then these areas are used to glide the search through feature space towards maximizing the class separation distance between the correct match and the false matches. Third, a self-diagnostic method is developed for determining when a priori knowledge is necessary for finding the correct match. If the a priori knowledge is necessary, then a surface reconstruction model is used to discriminate between match possibilities. The algorithm is comprehensively tested against fixed feature set algorithms and against a traditional pyramid algorithm. Finally, extensive empirical results based on a large set of real images are presented and discussed.","abstract_has_math":false,"creators":["Lew, Michael S."],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":["Huang, Thomas S."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2011,"date_issued":"2011-05-07T12:34:45Z","date_published":"2011-05-07T12:34:45Z","updated_at":"2026-07-22T22:25:15Z","subjects":["Engineering, Electronics and Electrical"],"languages":["eng"],"rights":["Copyright 1995 Lew, Michael S."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["AAI9543647","(UMI)AAI9543647"],"render_values":[{"text":"AAI9543647","href":null,"code":true},{"text":"(UMI)AAI9543647","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/2142/20282","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Huang, Thomas S."]},{"key":"dc:creator","label":"Author","values":["Lew, Michael S."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2011-05-07T12:34:45Z","10000-01-01","1995"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical 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":["Engineering, Electronics and Electrical"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 1995 Lew, Michael S."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["AAI9543647","(UMI)AAI9543647","http://hdl.handle.net/2142/20282"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["A novel stereo matching algorithm is presented which integrates learning, feature, selection, and surface reconstruction. First, a new instance based learning (IBL) algorithm is used to generate an approximation to the optimal feature set for matching. In addition, the importance of two separate kinds of knowledge, image dependent knowledge and image independent knowledge, is discussed. Second, an adaptive method for refining the feature set is developed. This adaptive method analyzes the feature error to locate areas of the image which would lead to false matches. Then these areas are used to glide the search through feature space towards maximizing the class separation distance between the correct match and the false matches. Third, a self-diagnostic method is developed for determining when a priori knowledge is necessary for finding the correct match. If the a priori knowledge is necessary, then a surface reconstruction model is used to discriminate between match possibilities. The algorithm is comprehensively tested against fixed feature set algorithms and against a traditional pyramid algorithm. Finally, extensive empirical results based on a large set of real images are presented and discussed.","Made available in DSpace on 2011-05-07T12:34:45Z (GMT). No. of bitstreams: 2 license.txt: 4922 bytes, checksum: 910b249b4beec47e7ab768910c8f966f (MD5) 9543647.pdf: 4429417 bytes, checksum: 24e4f3de97c4fd99744a5f0bb9b6f9c1 (MD5) Previous issue date: 1995","Item marked as restricted to the 'UIUC Users [automated]' Group (id=2) by Howard Ding (hding2@illinois.edu) on 2011-05-07T14:42:51Z Item is restricted indefinitely.","Restriction data tranferred 2014-07-01T11:18:40-05:00 Original Data Group with Access UIUC Users [automated] Release Date: none Reason: ETDs are only available to UIUC Users without author permission","ETDs are only available to UIUC Users without author permission","U of I Only"]},{"key":"dc:title","label":"Title","values":["Learning and feature selection in stereo matching"]}]}],"canonical_facts":{"dc:contributor":["Huang, Thomas S."],"dc:creator":["Lew, Michael S."],"dc:date":["2011-05-07T12:34:45Z","10000-01-01","1995"],"dc:description":["A novel stereo matching algorithm is presented which integrates learning, feature, selection, and surface reconstruction. First, a new instance based learning (IBL) algorithm is used to generate an approximation to the optimal feature set for matching. In addition, the importance of two separate kinds of knowledge, image dependent knowledge and image independent knowledge, is discussed. Second, an adaptive method for refining the feature set is developed. This adaptive method analyzes the feature error to locate areas of the image which would lead to false matches. Then these areas are used to glide the search through feature space towards maximizing the class separation distance between the correct match and the false matches. Third, a self-diagnostic method is developed for determining when a priori knowledge is necessary for finding the correct match. If the a priori knowledge is necessary, then a surface reconstruction model is used to discriminate between match possibilities. The algorithm is comprehensively tested against fixed feature set algorithms and against a traditional pyramid algorithm. Finally, extensive empirical results based on a large set of real images are presented and discussed.","Made available in DSpace on 2011-05-07T12:34:45Z (GMT). No. of bitstreams: 2 license.txt: 4922 bytes, checksum: 910b249b4beec47e7ab768910c8f966f (MD5) 9543647.pdf: 4429417 bytes, checksum: 24e4f3de97c4fd99744a5f0bb9b6f9c1 (MD5) Previous issue date: 1995","Item marked as restricted to the 'UIUC Users [automated]' Group (id=2) by Howard Ding (hding2@illinois.edu) on 2011-05-07T14:42:51Z Item is restricted indefinitely.","Restriction data tranferred 2014-07-01T11:18:40-05:00 Original Data Group with Access UIUC Users [automated] Release Date: none Reason: ETDs are only available to UIUC Users without author permission","ETDs are only available to UIUC Users without author permission","U of I Only"],"dc:identifier":["AAI9543647","(UMI)AAI9543647","http://hdl.handle.net/2142/20282"],"dc:language":["eng"],"dc:rights":["Copyright 1995 Lew, Michael S."],"dc:subject":["Engineering, Electronics and Electrical"],"dc:title":["Learning and feature selection in stereo matching"],"dc:type":["text"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:15Z"}