{"id":{"repo_id":"unlv","oai_identifier":"oai:oasis.library.unlv.edu:rtds-2610"},"canonical_url":"https://search.dev.ndltd.org/etd/unlv/oai:oasis.library.unlv.edu:rtds-2610","repository":{"repo_id":"unlv","name":"University of Nevada - Las Vegas","base_url":"https://oasis.library.unlv.edu/do/oai/"},"display":{"title":"Identification of headers and footers in noisy documents","abstract":"Optical Recognition Technology is typically used to convert hard copy printed material into its electronic form. Many presentational artifacts such as end-of-line hyphenations, running headers and footers are literally converted. These artifacts can possibly hinder proximity and exact match searching; This thesis develops an algorithm to extract running headers and footers from electronic documents generated by OCR. This method associates each page of the document with its neighboring pages and detects the headers and footers by comparing the page with its neighboring pages. Experiments are also taken to test the effectiveness of these algorithms.","abstract_html":"Optical Recognition Technology is typically used to convert hard copy printed material into its electronic form. Many presentational artifacts such as end-of-line hyphenations, running headers and footers are literally converted. These artifacts can possibly hinder proximity and exact match searching; This thesis develops an algorithm to extract running headers and footers from electronic documents generated by OCR. This method associates each page of the document with its neighboring pages and detects the headers and footers by comparing the page with its neighboring pages. Experiments are also taken to test the effectiveness of these algorithms.","abstract_has_math":false,"creators":["Liu, Qin"],"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 Tagva"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2003,"date_issued":"2003-01-01T08:00:00Z","date_published":"2003-01-01T08:00:00Z","updated_at":"2026-07-24T05:25:47Z","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/1611"],"render_values":[{"text":"https://oasis.library.unlv.edu/rtds/1611","href":"https://oasis.library.unlv.edu/rtds/1611","code":true}]}]},"links":{"outbound_url":"https://doi.org/10.25669/r00m-5nzp","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Kazem Tagva"]},{"key":"dc:creator","label":"Author","values":["Liu, Qin"]}]},{"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/r00m-5nzp","https://oasis.library.unlv.edu/rtds/1611","https://oasis.library.unlv.edu/context/rtds/article/2610/viewcontent/uc.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Optical Recognition Technology is typically used to convert hard copy printed material into its electronic form. Many presentational artifacts such as end-of-line hyphenations, running headers and footers are literally converted. These artifacts can possibly hinder proximity and exact match searching; This thesis develops an algorithm to extract running headers and footers from electronic documents generated by OCR. This method associates each page of the document with its neighboring pages and detects the headers and footers by comparing the page with its neighboring pages. Experiments are also taken to test the effectiveness of these algorithms."]},{"key":"dc:format","label":"Dc Format","values":["pdf"]},{"key":"dc:title","label":"Title","values":["Identification of headers and footers in noisy documents"]}]}],"canonical_facts":{"dc:contributor":["Kazem Tagva"],"dc:creator":["Liu, Qin"],"dc:description.abstract":["Optical Recognition Technology is typically used to convert hard copy printed material into its electronic form. Many presentational artifacts such as end-of-line hyphenations, running headers and footers are literally converted. These artifacts can possibly hinder proximity and exact match searching; This thesis develops an algorithm to extract running headers and footers from electronic documents generated by OCR. This method associates each page of the document with its neighboring pages and detects the headers and footers by comparing the page with its neighboring pages. Experiments are also taken to test the effectiveness of these algorithms."],"dc:format":["pdf"],"dc:identifier":["10.25669/r00m-5nzp","https://oasis.library.unlv.edu/rtds/1611","https://oasis.library.unlv.edu/context/rtds/article/2610/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":["Identification of headers and footers in noisy documents"],"dc:type":["Text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-07-24T05:25:47Z"}