{"id":"https://openalex.org/W2517021335","doi":"https://doi.org/10.1109/icip.2016.7532514","title":"Text detection based on convolutional neural networks with spatial pyramid pooling","display_name":"Text detection based on convolutional neural networks with spatial pyramid pooling","publication_year":2016,"publication_date":"2016-08-17","ids":{"openalex":"https://openalex.org/W2517021335","doi":"https://doi.org/10.1109/icip.2016.7532514","mag":"2517021335"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2016.7532514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2016.7532514","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 Image Processing (ICIP)","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/A5070090646","display_name":"Rui Zhu","orcid":"https://orcid.org/0000-0002-6037-6515"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100965851","display_name":"Xiao-Jiao Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Jiao Mao","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009425170","display_name":"Qi-Hai Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi-Hai Zhu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369100","display_name":"Ning Li","orcid":"https://orcid.org/0000-0003-4870-1140"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Li","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111673780","display_name":"Yu-Bin Yang","orcid":"https://orcid.org/0000-0002-3764-1114"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Bin Yang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.9058,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87203026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"36","issue":null,"first_page":"1032","last_page":"1036"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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":0.9943000078201294,"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":0.9941999912261963,"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/pooling","display_name":"Pooling","score":0.7805356979370117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.75963294506073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7495921850204468},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6996419429779053},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6728569269180298},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6632456183433533},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5937771797180176},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5480747818946838},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4978818893432617},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.4740457534790039},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.42895767092704773},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34596988558769226},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17658421397209167},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13292458653450012}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7805356979370117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.75963294506073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7495921850204468},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6996419429779053},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6728569269180298},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6632456183433533},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5937771797180176},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5480747818946838},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4978818893432617},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.4740457534790039},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.42895767092704773},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34596988558769226},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17658421397209167},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13292458653450012},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip.2016.7532514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2016.7532514","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 Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5600000023841858},{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W70975097","https://openalex.org/W117491841","https://openalex.org/W1488125194","https://openalex.org/W1935817682","https://openalex.org/W1988461287","https://openalex.org/W2008806374","https://openalex.org/W2023415694","https://openalex.org/W2036887016","https://openalex.org/W2056518953","https://openalex.org/W2061802763","https://openalex.org/W2102605133","https://openalex.org/W2109255472","https://openalex.org/W2131447359","https://openalex.org/W2148214126","https://openalex.org/W2150259535","https://openalex.org/W2162915993","https://openalex.org/W2163605009","https://openalex.org/W6629021407","https://openalex.org/W6679524940","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W2022849497","https://openalex.org/W3081299480","https://openalex.org/W2407190427","https://openalex.org/W2919210741","https://openalex.org/W2907584218","https://openalex.org/W3002446410","https://openalex.org/W4390224712","https://openalex.org/W4322096758","https://openalex.org/W3113266311","https://openalex.org/W3114556517"],"abstract_inverted_index":{"Text":[0],"detection":[1],"is":[2],"a":[3,24,87],"difficult":[4],"task":[5],"due":[6],"to":[7],"the":[8,12,32,44,48,60,69,79,83],"significant":[9],"diversity":[10],"of":[11,95,103],"texts":[13],"appearing":[14],"in":[15],"natural":[16],"scene":[17],"images.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22],"propose":[23],"novel":[25],"text":[26,50,64,98,105],"descriptor,":[27],"SPP-net,":[28],"extracted":[29],"by":[30,86],"equipping":[31],"Convolutional":[33],"Neural":[34],"Network":[35],"(CNN)":[36],"with":[37,92,107],"spatial":[38],"pyramid":[39],"pooling.":[40],"We":[41],"first":[42],"compute":[43],"feature":[45],"maps":[46],"from":[47],"original":[49],"lines":[51],"without":[52],"any":[53],"cropping":[54],"or":[55],"warping,":[56],"and":[57,73,100,110],"then":[58],"generate":[59],"fixed-size":[61],"representations":[62],"for":[63],"discrimination.":[65],"Experimental":[66],"results":[67],"on":[68,90],"latest":[70],"ICDAR":[71],"2011":[72],"2013":[74],"datasets":[75],"have":[76],"proven":[77],"that":[78],"proposed":[80],"descriptor":[81],"outperforms":[82],"state-of-the-art":[84],"methods":[85],"noticeable":[88],"margin":[89],"F-measure":[91],"its":[93,101],"merit":[94],"incorporating":[96],"multi-scale":[97],"information":[99],"flexibility":[102],"describing":[104],"regions":[106],"different":[108],"sizes":[109],"shapes.":[111]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}