{"id":"https://openalex.org/W2751104554","doi":"https://doi.org/10.1145/3103010.3121042","title":"High-Performance Preprocessing of Architectural Drawings for Legend Metadata Extraction via OCR","display_name":"High-Performance Preprocessing of Architectural Drawings for Legend Metadata Extraction via OCR","publication_year":2017,"publication_date":"2017-08-31","ids":{"openalex":"https://openalex.org/W2751104554","doi":"https://doi.org/10.1145/3103010.3121042","mag":"2751104554"},"language":"en","primary_location":{"id":"doi:10.1145/3103010.3121042","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3103010.3121042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102797774","display_name":"Tamir Hassan","orcid":"https://orcid.org/0000-0002-1940-1037"},"institutions":[{"id":"https://openalex.org/I4210121244","display_name":"Hewlett-Packard (Austria)","ror":"https://ror.org/01wt6rn90","country_code":"AT","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210121244"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Tamir Hassan","raw_affiliation_strings":["HP Labs, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs, Vienna, Austria","institution_ids":["https://openalex.org/I4210121244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065638055","display_name":"Jaume Verg\u00e9s\u2013Llah\u00ed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaume Verges-Llahi","raw_affiliation_strings":["HP, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP, Barcelona, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012379093","display_name":"Andr\u00e9s Gonz\u00e1lez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andres Gonzalez","raw_affiliation_strings":["HP, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP, Barcelona, Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"197","last_page":"200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8259333968162537},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7548917531967163},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7422770261764526},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7228792309761047},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4459529221057892},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3976110517978668},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32560786604881287},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11433598399162292},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10732218623161316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259333968162537},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7548917531967163},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7422770261764526},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7228792309761047},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4459529221057892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3976110517978668},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32560786604881287},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11433598399162292},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10732218623161316}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3103010.3121042","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3103010.3121042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2017962986","https://openalex.org/W2019995264","https://openalex.org/W2022351003","https://openalex.org/W2031118188","https://openalex.org/W2118030626","https://openalex.org/W2135085165","https://openalex.org/W2164078152"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4388446985","https://openalex.org/W2977327189"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,25,28,86,97,110],"results":[4,66],"of":[5,10,55,94,105],"an":[6],"investigation":[7],"into":[8],"methods":[9],"preprocessing":[11],"architectural":[12],"plots":[13],"to":[14,17,52,77],"enable":[15],"them":[16],"be":[18],"processed":[19],"very":[20],"quickly":[21],"via":[22],"OCR,":[23],"detecting":[24],"region":[26,99],"containing":[27],"relevant":[29],"metadata":[30],"legend":[31,98],"and":[32,42,96],"obtaining":[33],"it":[34],"in":[35,70,92,103],"machine-readable":[36],"form":[37],"for":[38,81,109],"e.g.":[39],"automated":[40],"folding":[41,87],"filenaming":[43],"applications.":[44],"We":[45],"show":[46,67],"how":[47],"a":[48,68],"processing":[49,60,72],"pipeline":[50],"adapted":[51],"this":[53],"type":[54],"content":[56],"can":[57],"vastly":[58],"decrease":[59],"time,":[61],"maintaining":[62],"acceptable":[63],"accuracy.":[64],"Initial":[65],"reduction":[69],"total":[71],"time":[73],"from":[74],"2--3":[75],"minutes":[76],"around":[78],"15":[79],"seconds":[80],"most":[82],"documents":[83],"encountered,":[84],"with":[85],"orientation":[88],"being":[89,100],"correctly":[90],"detected":[91,102],"78%":[93],"cases":[95],"completely":[101],"60%":[104],"cases,":[106],"high":[107],"enough":[108],"use-case":[111],"at":[112],"hand.":[113]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}