{"id":{"repo_id":"unlv","oai_identifier":"oai:oasis.library.unlv.edu:rtds-1454"},"canonical_url":"https://search.dev.ndltd.org/etd/unlv/oai:oasis.library.unlv.edu:rtds-1454","repository":{"repo_id":"unlv","name":"University of Nevada - Las Vegas","base_url":"https://oasis.library.unlv.edu/do/oai/"},"display":{"title":"Effect of OCR errors on short documents","abstract":"Presented in this thesis is a study of the effect of OCR errors on short documents. OCR recognizes and translates text image into ASCII format. When this data is retrieved in response to a query, the retrieval performance depends on the efficiency of the OCR device used. Measures like recall, precision and ranking were used to gauge the retrieval performance. The information retrieval system that was used is SMART, based on the vector space model. On evaluating these measures, it has been concluded that average precision and recall are not affected significantly when the OCR collection is compared to its corrected version. However, it was also concluded that with more complex weighting schemes, the relevant document rankings became more divergent. Also, the effect of an automatic post-processing system on the retrieval performance was studied.","abstract_html":"Presented in this thesis is a study of the effect of OCR errors on short documents. OCR recognizes and translates text image into ASCII format. When this data is retrieved in response to a query, the retrieval performance depends on the efficiency of the OCR device used. Measures like recall, precision and ranking were used to gauge the retrieval performance. The information retrieval system that was used is SMART, based on the vector space model. On evaluating these measures, it has been concluded that average precision and recall are not affected significantly when the OCR collection is compared to its corrected version. However, it was also concluded that with more complex weighting schemes, the relevant document rankings became more divergent. Also, the effect of an automatic post-processing system on the retrieval performance was studied.","abstract_has_math":false,"creators":["Inaparthy, Padma"],"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":1994,"date_issued":"1994-01-01T08:00:00Z","date_published":"1994-01-01T08:00:00Z","updated_at":"2026-07-24T05:24:31Z","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/455"],"render_values":[{"text":"https://oasis.library.unlv.edu/rtds/455","href":"https://oasis.library.unlv.edu/rtds/455","code":true}]}]},"links":{"outbound_url":"https://doi.org/10.25669/2gel-89vo","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":["Inaparthy, Padma"]}]},{"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":["10.25669/2gel-89vo","https://oasis.library.unlv.edu/rtds/455","https://oasis.library.unlv.edu/context/rtds/article/1454/viewcontent/uc.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Presented in this thesis is a study of the effect of OCR errors on short documents. OCR recognizes and translates text image into ASCII format. When this data is retrieved in response to a query, the retrieval performance depends on the efficiency of the OCR device used. Measures like recall, precision and ranking were used to gauge the retrieval performance. The information retrieval system that was used is SMART, based on the vector space model. On evaluating these measures, it has been concluded that average precision and recall are not affected significantly when the OCR collection is compared to its corrected version. However, it was also concluded that with more complex weighting schemes, the relevant document rankings became more divergent. Also, the effect of an automatic post-processing system on the retrieval performance was studied."]},{"key":"dc:format","label":"Dc Format","values":["pdf"]},{"key":"dc:title","label":"Title","values":["Effect of OCR errors on short documents"]}]}],"canonical_facts":{"dc:contributor":["Kazem Taghva"],"dc:creator":["Inaparthy, Padma"],"dc:description.abstract":["Presented in this thesis is a study of the effect of OCR errors on short documents. OCR recognizes and translates text image into ASCII format. When this data is retrieved in response to a query, the retrieval performance depends on the efficiency of the OCR device used. Measures like recall, precision and ranking were used to gauge the retrieval performance. The information retrieval system that was used is SMART, based on the vector space model. On evaluating these measures, it has been concluded that average precision and recall are not affected significantly when the OCR collection is compared to its corrected version. However, it was also concluded that with more complex weighting schemes, the relevant document rankings became more divergent. Also, the effect of an automatic post-processing system on the retrieval performance was studied."],"dc:format":["pdf"],"dc:identifier":["10.25669/2gel-89vo","https://oasis.library.unlv.edu/rtds/455","https://oasis.library.unlv.edu/context/rtds/article/1454/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":["Effect of OCR errors on short documents"],"dc:type":["Text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-07-24T05:24:31Z"}