{"id":"https://openalex.org/W2405851518","doi":"https://doi.org/10.1109/icassp.2016.7472017","title":"A multi-scale approach to extract meaningful annotations from document images","display_name":"A multi-scale approach to extract meaningful annotations from document images","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2405851518","doi":"https://doi.org/10.1109/icassp.2016.7472017","mag":"2405851518"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":null,"display_name":"Yang Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Lei","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077871435","display_name":"Jian Fan","orcid":"https://orcid.org/0000-0001-5009-9588"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Fan","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107840655","display_name":"Jerry Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jerry Liu","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3872","issue":null,"first_page":"1951","last_page":"1955"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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":0.9995999932289124,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994999766349792,"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":0.7861308455467224},{"id":"https://openalex.org/keywords/camera-phone","display_name":"Camera phone","score":0.6869527697563171},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6575594544410706},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6266986131668091},{"id":"https://openalex.org/keywords/scanner","display_name":"Scanner","score":0.5877460241317749},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5690557956695557},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5525609254837036},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.49930262565612793},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49096134305000305},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4470941424369812},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.43201613426208496},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4256061911582947},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.42362892627716064},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4208364486694336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09659719467163086},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0911514163017273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7861308455467224},{"id":"https://openalex.org/C147942929","wikidata":"https://www.wikidata.org/wiki/Q210820","display_name":"Camera phone","level":2,"score":0.6869527697563171},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6575594544410706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6266986131668091},{"id":"https://openalex.org/C2779751349","wikidata":"https://www.wikidata.org/wiki/Q1474480","display_name":"Scanner","level":2,"score":0.5877460241317749},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5690557956695557},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5525609254837036},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.49930262565612793},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49096134305000305},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4470941424369812},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.43201613426208496},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4256061911582947},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.42362892627716064},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4208364486694336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09659719467163086},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0911514163017273},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W55836907","https://openalex.org/W1534808658","https://openalex.org/W1968234316","https://openalex.org/W2082404624","https://openalex.org/W2084884002","https://openalex.org/W2085261163","https://openalex.org/W2097429259","https://openalex.org/W2111962961","https://openalex.org/W2119605622","https://openalex.org/W2124921411","https://openalex.org/W2135054073","https://openalex.org/W2141092372","https://openalex.org/W2151103935","https://openalex.org/W6602200828","https://openalex.org/W6676877879","https://openalex.org/W6680724680"],"related_works":["https://openalex.org/W3177930984","https://openalex.org/W2052697133","https://openalex.org/W2076896210","https://openalex.org/W2384288472","https://openalex.org/W1539573266","https://openalex.org/W2093596879","https://openalex.org/W2376984068","https://openalex.org/W2201969175","https://openalex.org/W2017257332","https://openalex.org/W2747088704"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,12,67,100],"multi-scale":[3],"approach":[4],"to":[5,37,114,122],"extract":[6],"annotations":[7],"from":[8],"document":[9,51],"images":[10],"in":[11,35],"meaningful":[13,89],"way.":[14],"It":[15,59,118],"compares":[16],"the":[17,39,56,82,88,105,116],"rectified":[18],"captured":[19],"image":[20,29,85,97],"with":[21,66,143],"original":[22],"image,":[23],"which":[24],"can":[25,119],"be":[26,120],"obtained":[27],"through":[28],"retrieval":[30],"technology,":[31],"at":[32,74],"various":[33,123],"resolutions,":[34],"order":[36],"remove":[38],"noise":[40],"caused":[41],"by":[42],"nonuniform":[43],"distortions,":[44],"such":[45,94,126],"as":[46,95,127],"camera":[47,135],"lens":[48],"distortion":[49],"and":[50,70,86,110,141],"surface":[52],"curvature,":[53],"while":[54],"preserving":[55],"true":[57],"annotations.":[58],"also":[60],"provides":[61],"users":[62],"lots":[63],"of":[64,92,99,107],"flexibility":[65],"voting":[68],"scheme":[69],"potentially":[71],"different":[72,75],"weights":[73],"resolution":[76],"levels.":[77],"In":[78],"addition,":[79],"we":[80],"analyzed":[81],"final":[83],"annotation":[84,108],"found":[87],"pieces":[90],"out":[91],"it,":[93],"an":[96],"patch":[98],"handwritten":[101],"paragraph.":[102],"This":[103],"broadens":[104],"application":[106],"extraction,":[109],"makes":[111],"it":[112],"easier":[113],"share":[115],"notes.":[117],"applied":[121],"imaging":[124],"systems,":[125],"flatbed":[128],"scanner,":[129],"mobile":[130],"phone":[131],"camera,":[132],"or":[133],"fixed":[134],"etc.":[136],"Experimental":[137],"results":[138],"are":[139],"presented":[140],"compared":[142],"previous":[144],"approaches.":[145]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}