{"id":{"repo_id":"unlv","oai_identifier":"oai:oasis.library.unlv.edu:rtds-1586"},"canonical_url":"https://search.dev.ndltd.org/etd/unlv/oai:oasis.library.unlv.edu:rtds-1586","repository":{"repo_id":"unlv","name":"University of Nevada - Las Vegas","base_url":"https://oasis.library.unlv.edu/do/oai/"},"display":{"title":"Feature recognition in OCR text","abstract":"This thesis investigates the recognition and extraction of special word sequences, representing concepts, from OCR text. Unlike general index terms, concepts can consist of one or more terms that combined, have higher retrieval value than the terms alone (i.e. acronyms, proper nouns, phrases). An algorithm to recognize acronyms and their definitions will be presented. An evaluation of the algorithm will also be presented.","abstract_html":"This thesis investigates the recognition and extraction of special word sequences, representing concepts, from OCR text. Unlike general index terms, concepts can consist of one or more terms that combined, have higher retrieval value than the terms alone (i.e. acronyms, proper nouns, phrases). An algorithm to recognize acronyms and their definitions will be presented. An evaluation of the algorithm will also be presented.","abstract_has_math":false,"creators":["Gilbreth, Jeffrey Todd"],"institution":"University of Nevada, Las Vegas","degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Kazem Taghva"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":1996,"date_issued":"1996-01-01T08:00:00Z","date_published":"1996-01-01T08:00:00Z","updated_at":"2026-07-24T05:24:45Z","subjects":[],"languages":["English"],"rights":["IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://oasis.library.unlv.edu/rtds/587"],"render_values":[{"text":"https://oasis.library.unlv.edu/rtds/587","href":"https://oasis.library.unlv.edu/rtds/587","code":true}]}]},"links":{"outbound_url":"https://doi.org/10.25669/ar50-yge7","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Kazem Taghva"]},{"key":"dc:creator","label":"Author","values":["Gilbreth, Jeffrey Todd"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:publisher","label":"Institution","values":["University of Nevada, Las Vegas"]},{"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":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:rights","label":"Dc Rights","values":["IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.25669/ar50-yge7","https://oasis.library.unlv.edu/rtds/587","https://oasis.library.unlv.edu/context/rtds/article/1586/viewcontent/uc.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis investigates the recognition and extraction of special word sequences, representing concepts, from OCR text. Unlike general index terms, concepts can consist of one or more terms that combined, have higher retrieval value than the terms alone (i.e. acronyms, proper nouns, phrases). An algorithm to recognize acronyms and their definitions will be presented. An evaluation of the algorithm will also be presented."]},{"key":"dc:format","label":"Dc Format","values":["pdf"]},{"key":"dc:title","label":"Title","values":["Feature recognition in OCR text"]}]}],"canonical_facts":{"dc:contributor":["Kazem Taghva"],"dc:creator":["Gilbreth, Jeffrey Todd"],"dc:description.abstract":["This thesis investigates the recognition and extraction of special word sequences, representing concepts, from OCR text. Unlike general index terms, concepts can consist of one or more terms that combined, have higher retrieval value than the terms alone (i.e. acronyms, proper nouns, phrases). An algorithm to recognize acronyms and their definitions will be presented. An evaluation of the algorithm will also be presented."],"dc:format":["pdf"],"dc:identifier":["10.25669/ar50-yge7","https://oasis.library.unlv.edu/rtds/587","https://oasis.library.unlv.edu/context/rtds/article/1586/viewcontent/uc.pdf"],"dc:language":["English"],"dc:publisher":["University of Nevada, Las Vegas"],"dc:rights":["IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/"],"dc:title":["Feature recognition in OCR text"],"dc:type":["Text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-07-24T05:24:45Z"}