{"id":"https://openalex.org/W2042677921","doi":"https://doi.org/10.1145/1860559.1860605","title":"Picture detection in document page images","display_name":"Picture detection in document page images","publication_year":2010,"publication_date":"2010-09-21","ids":{"openalex":"https://openalex.org/W2042677921","doi":"https://doi.org/10.1145/1860559.1860605","mag":"2042677921"},"language":"en","primary_location":{"id":"doi:10.1145/1860559.1860605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1860559.1860605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM symposium on Document engineering","raw_type":"proceedings-article"},"type":"article","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/A5103331862","display_name":"Patrick Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I26274970","display_name":"FX Palo Alto Laboratory","ror":"https://ror.org/05ef4zt88","country_code":"US","type":"facility","lineage":["https://openalex.org/I26274970"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Patrick Chiu","raw_affiliation_strings":["FX Palo Alto Laboratory, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"FX Palo Alto Laboratory, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I26274970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025376488","display_name":"Francine Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I26274970","display_name":"FX Palo Alto Laboratory","ror":"https://ror.org/05ef4zt88","country_code":"US","type":"facility","lineage":["https://openalex.org/I26274970"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francine Chen","raw_affiliation_strings":["FX Palo Alto Laboratory, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"FX Palo Alto Laboratory, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I26274970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075159263","display_name":"Laurent Denoue","orcid":null},"institutions":[{"id":"https://openalex.org/I26274970","display_name":"FX Palo Alto Laboratory","ror":"https://ror.org/05ef4zt88","country_code":"US","type":"facility","lineage":["https://openalex.org/I26274970"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laurent Denoue","raw_affiliation_strings":["FX Palo Alto Laboratory, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"FX Palo Alto Laboratory, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I26274970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103331862"],"corresponding_institution_ids":["https://openalex.org/I26274970"],"apc_list":null,"apc_paid":null,"fwci":0.6465,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.70518931,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"211","last_page":"214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval 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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification 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":0.848141074180603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6214168071746826},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.6082682609558105},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5773438811302185},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.543769359588623},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.47873374819755554},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4651661217212677},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4547625184059143},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.44961753487586975},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.42073649168014526},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3880600929260254},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3497389554977417},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3432854115962982},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3403271734714508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.848141074180603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6214168071746826},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6082682609558105},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5773438811302185},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.543769359588623},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.47873374819755554},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4651661217212677},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4547625184059143},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.44961753487586975},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.42073649168014526},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3880600929260254},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3497389554977417},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3432854115962982},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3403271734714508},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1860559.1860605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1860559.1860605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.185.3673","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.185.3673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.fxpal.com/people/chiu/chiu-10_PicDetect_DocEng10.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.363.1555","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.363.1555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://207.21.18.5/publications/FXPAL-PR-10-574.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W187264860","https://openalex.org/W630303251","https://openalex.org/W1966950310","https://openalex.org/W2035147392","https://openalex.org/W2035636904","https://openalex.org/W2054457389","https://openalex.org/W2092312899","https://openalex.org/W2110212011","https://openalex.org/W2118030626","https://openalex.org/W2121947440","https://openalex.org/W2137181306","https://openalex.org/W2158295445"],"related_works":["https://openalex.org/W4306707571","https://openalex.org/W3179897446","https://openalex.org/W2131730163","https://openalex.org/W2038329042","https://openalex.org/W4388916331","https://openalex.org/W2573990671","https://openalex.org/W4281724000","https://openalex.org/W2110425765","https://openalex.org/W2317477910","https://openalex.org/W2043611036"],"abstract_inverted_index":{"We":[0,91],"present":[1],"a":[2,66],"method":[3,26,94],"for":[4,71],"picture":[5,46,67],"detection":[6,86],"in":[7,55,65],"document":[8],"page":[9,100],"images,":[10,18],"which":[11,81],"can":[12],"come":[13],"from":[14,21,102],"scanned":[15],"or":[16,19],"camera":[17],"rendered":[20],"electronic":[22],"file":[23],"formats.":[24],"Our":[25],"uses":[27,51],"OCR":[28,57],"to":[29,40,59],"separate":[30],"out":[31],"the":[32,36,42,52,56,85,96],"text":[33,58],"and":[34,73,88],"applies":[35],"Normalized":[37],"Cuts":[38],"algorithm":[39],"cluster":[41],"non-text":[43],"pixels":[44],"into":[45,83],"regions.":[47],"A":[48,75],"refinement":[49],"step":[50],"captions":[53],"found":[54],"deduce":[60],"how":[61],"many":[62],"pictures":[63],"are":[64],"region,":[68],"thereby":[69],"correcting":[70],"under-":[72],"over-segmentation.":[74],"performance":[76],"evaluation":[77],"scheme":[78],"is":[79],"applied":[80],"takes":[82],"account":[84],"quality":[87],"fragmentation":[89],"quality.":[90],"benchmark":[92],"our":[93],"against":[95],"ABBYY":[97],"application":[98],"on":[99],"images":[101],"conference":[103],"papers.":[104]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}