{"id":{"repo_id":"unlv","oai_identifier":"oai:oasis.library.unlv.edu:rtds-2583"},"canonical_url":"https://search.dev.ndltd.org/etd/unlv/oai:oasis.library.unlv.edu:rtds-2583","repository":{"repo_id":"unlv","name":"University of Nevada - Las Vegas","base_url":"https://oasis.library.unlv.edu/do/oai/"},"display":{"title":"Form processing with the Hough transform","abstract":"A form document processing system based on the Hough transform (HT) is developed. It performs form identification and form registration. For form identification, HT is applied off-line to master forms to calculate form features and build-up the feature database, and it is performed on-line for the input (scanned) forms to extract features to identify the form type based on feature matching. The derived features are rotation, translation and scale invariant. The proposed form description is compact, thereby allows for fast identification. The registration is feature/knowledge based. Two methods for control points detection are discussed; one implements template matching for finding frame corners. The second approach is based on detection of line crossings via the analysis of the parameter space of the HT. Detected control points are used to calculate parameters of geometrical transform and perform coordinates translation. Linear conformal and projective transforms are tested. The system is featured by fast and reliable type identification, and the moderate preprocessing time, which is attained by proper design of the Hough space.","abstract_html":"A form document processing system based on the Hough transform (HT) is developed. It performs form identification and form registration. For form identification, HT is applied off-line to master forms to calculate form features and build-up the feature database, and it is performed on-line for the input (scanned) forms to extract features to identify the form type based on feature matching. The derived features are rotation, translation and scale invariant. The proposed form description is compact, thereby allows for fast identification. The registration is feature/knowledge based. Two methods for control points detection are discussed; one implements template matching for finding frame corners. The second approach is based on detection of line crossings via the analysis of the parameter space of the HT. Detected control points are used to calculate parameters of geometrical transform and perform coordinates translation. Linear conformal and projective transforms are tested. The system is featured by fast and reliable type identification, and the moderate preprocessing time, which is attained by proper design of the Hough space.","abstract_has_math":false,"creators":["Chen, De"],"institution":"University of Nevada, Las Vegas","degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":["Emma Regentova"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2003,"date_issued":"2003-01-01T08:00:00Z","date_published":"2003-01-01T08:00:00Z","updated_at":"2026-07-24T05:25:40Z","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/1584"],"render_values":[{"text":"https://oasis.library.unlv.edu/rtds/1584","href":"https://oasis.library.unlv.edu/rtds/1584","code":true}]}]},"links":{"outbound_url":"https://doi.org/10.25669/iarb-2vts","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Emma Regentova"]},{"key":"dc:creator","label":"Author","values":["Chen, De"]}]},{"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":["Electrical and Computer Engineering"]},{"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/iarb-2vts","https://oasis.library.unlv.edu/rtds/1584","https://oasis.library.unlv.edu/context/rtds/article/2583/viewcontent/uc.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["A form document processing system based on the Hough transform (HT) is developed. It performs form identification and form registration. For form identification, HT is applied off-line to master forms to calculate form features and build-up the feature database, and it is performed on-line for the input (scanned) forms to extract features to identify the form type based on feature matching. The derived features are rotation, translation and scale invariant. The proposed form description is compact, thereby allows for fast identification. The registration is feature/knowledge based. Two methods for control points detection are discussed; one implements template matching for finding frame corners. The second approach is based on detection of line crossings via the analysis of the parameter space of the HT. Detected control points are used to calculate parameters of geometrical transform and perform coordinates translation. Linear conformal and projective transforms are tested. The system is featured by fast and reliable type identification, and the moderate preprocessing time, which is attained by proper design of the Hough space."]},{"key":"dc:format","label":"Dc Format","values":["pdf"]},{"key":"dc:title","label":"Title","values":["Form processing with the Hough transform"]}]}],"canonical_facts":{"dc:contributor":["Emma Regentova"],"dc:creator":["Chen, De"],"dc:description.abstract":["A form document processing system based on the Hough transform (HT) is developed. It performs form identification and form registration. For form identification, HT is applied off-line to master forms to calculate form features and build-up the feature database, and it is performed on-line for the input (scanned) forms to extract features to identify the form type based on feature matching. The derived features are rotation, translation and scale invariant. The proposed form description is compact, thereby allows for fast identification. The registration is feature/knowledge based. Two methods for control points detection are discussed; one implements template matching for finding frame corners. The second approach is based on detection of line crossings via the analysis of the parameter space of the HT. Detected control points are used to calculate parameters of geometrical transform and perform coordinates translation. Linear conformal and projective transforms are tested. The system is featured by fast and reliable type identification, and the moderate preprocessing time, which is attained by proper design of the Hough space."],"dc:format":["pdf"],"dc:identifier":["10.25669/iarb-2vts","https://oasis.library.unlv.edu/rtds/1584","https://oasis.library.unlv.edu/context/rtds/article/2583/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":["Form processing with the Hough transform"],"dc:type":["Text"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-07-24T05:25:40Z"}