{"id":{"repo_id":"unlv","oai_identifier":"oai:oasis.library.unlv.edu:rtds-1303"},"canonical_url":"https://search.dev.ndltd.org/etd/unlv/oai:oasis.library.unlv.edu:rtds-1303","repository":{"repo_id":"unlv","name":"University of Nevada - Las Vegas","base_url":"https://oasis.library.unlv.edu/do/oai/"},"display":{"title":"The use of synthesized images to evaluate the performance of Ocr devices and algorithms","abstract":"This thesis will attempt to establish if synthesized images can be used to predict the performance of Optical Character Recognition (OCR) algorithms and devices. The value of this research lies in reducing the considerable costs associated with preparing test images for OCR research. The paper reports on a series of experiments in which synthesized images of text files in nine different fonts and sizes are input to eight commercial OCR devices. The method used to create the images is explained and a detailed analysis of the character and word confusion between the output and the true text files is presented. The synthesized images are then printed and scanned to mechanically introduce \"noise\". The resulting images are also input to the devices and analysis performed. A high correlation was found between the output from the printed and scanned images and the output from \"real world\" images.","abstract_html":"This thesis will attempt to establish if synthesized images can be used to predict the performance of Optical Character Recognition (OCR) algorithms and devices. The value of this research lies in reducing the considerable costs associated with preparing test images for OCR research. The paper reports on a series of experiments in which synthesized images of text files in nine different fonts and sizes are input to eight commercial OCR devices. The method used to create the images is explained and a detailed analysis of the character and word confusion between the output and the true text files is presented. The synthesized images are then printed and scanned to mechanically introduce "noise". The resulting images are also input to the devices and analysis performed. A high correlation was found between the output from the printed and scanned images and the output from "real world" images.","abstract_has_math":false,"creators":["Jenkins, Frank Robert"],"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":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":1993,"date_issued":"1993-01-01T08:00:00Z","date_published":"1993-01-01T08:00:00Z","updated_at":"2026-07-24T05:24:22Z","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/304"],"render_values":[{"text":"https://oasis.library.unlv.edu/rtds/304","href":"https://oasis.library.unlv.edu/rtds/304","code":true}]}]},"links":{"outbound_url":"https://doi.org/10.25669/6m80-ciqn","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Jenkins, Frank Robert"]}]},{"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":["10.25669/6m80-ciqn","https://oasis.library.unlv.edu/rtds/304","https://oasis.library.unlv.edu/context/rtds/article/1303/viewcontent/uc.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis will attempt to establish if synthesized images can be used to predict the performance of Optical Character Recognition (OCR) algorithms and devices. The value of this research lies in reducing the considerable costs associated with preparing test images for OCR research. The paper reports on a series of experiments in which synthesized images of text files in nine different fonts and sizes are input to eight commercial OCR devices. The method used to create the images is explained and a detailed analysis of the character and word confusion between the output and the true text files is presented. The synthesized images are then printed and scanned to mechanically introduce \"noise\". The resulting images are also input to the devices and analysis performed. A high correlation was found between the output from the printed and scanned images and the output from \"real world\" images."]},{"key":"dc:format","label":"Dc Format","values":["pdf"]},{"key":"dc:title","label":"Title","values":["The use of synthesized images to evaluate the performance of Ocr devices and algorithms"]}]}],"canonical_facts":{"dc:creator":["Jenkins, Frank Robert"],"dc:description.abstract":["This thesis will attempt to establish if synthesized images can be used to predict the performance of Optical Character Recognition (OCR) algorithms and devices. The value of this research lies in reducing the considerable costs associated with preparing test images for OCR research. The paper reports on a series of experiments in which synthesized images of text files in nine different fonts and sizes are input to eight commercial OCR devices. The method used to create the images is explained and a detailed analysis of the character and word confusion between the output and the true text files is presented. The synthesized images are then printed and scanned to mechanically introduce \"noise\". The resulting images are also input to the devices and analysis performed. A high correlation was found between the output from the printed and scanned images and the output from \"real world\" images."],"dc:format":["pdf"],"dc:identifier":["10.25669/6m80-ciqn","https://oasis.library.unlv.edu/rtds/304","https://oasis.library.unlv.edu/context/rtds/article/1303/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":["The use of synthesized images to evaluate the performance of Ocr devices and algorithms"],"dc:type":["Text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-07-24T05:24:22Z"}