{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:04:07Z","timestamp":1756771447895,"version":"3.44.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1109\/escience.2019.00020","type":"proceedings-article","created":{"date-parts":[[2020,3,20]],"date-time":"2020-03-20T04:35:09Z","timestamp":1584678909000},"page":"116-125","source":"Crossref","is-referenced-by-count":2,"title":["Quality-Aware Human-Machine Text Extraction for Biocollections using Ensembles of OCRs"],"prefix":"10.1109","author":[{"given":"Icaro","family":"Alzuru","sequence":"first","affiliation":[{"name":"University of Florida"}]},{"given":"Rhiannon","family":"Stephens","sequence":"additional","affiliation":[{"name":"Australian Museum"}]},{"given":"Andr\u00e9a","family":"Matsunaga","sequence":"additional","affiliation":[{"name":"Advanced Computing and Information Systems Laboratory"}]},{"given":"Maur\u00edcio","family":"Tsugawa","sequence":"additional","affiliation":[{"name":"Advanced Computing and Information Systems Laboratory"}]},{"given":"Paul","family":"Flemons","sequence":"additional","affiliation":[{"name":"Australian Museum"}]},{"given":"Jos\u00e9 A.B.","family":"Fortes","sequence":"additional","affiliation":[{"name":"University of Florida"}]}],"member":"263","reference":[{"key":"ref33","article-title":"A Survey of Text Similarity Approaches","volume":"68","author":"gomaa","year":"2013","journal-title":"International Journal of Computer Applications (0975 – 8887)"},{"journal-title":"Github","article-title":"iDigBio Augmenting OCR Working Group & Hackathon","year":"0","key":"ref32"},{"article-title":"READ-BAD: A New Dataset and Evaluation Scheme for Baseline Detection in Archival Documents","year":"2017","author":"gr\u00fcning","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE.2018.8574624"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.12705\/623.16"},{"journal-title":"ScioChronicle","article-title":"ScioChronicle: ScioTR Available Now in the Win8 Store!","year":"2014","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3897\/phytokeys.38.7168"},{"journal-title":"Packt Hub","article-title":"Tesseract version 4.0 releases with new LSTM based engine, and an updated build system","year":"2018","key":"ref13"},{"key":"ref14","article-title":"A web-based ocr service for documents","author":"walker","year":"2018","journal-title":"Proceedings of the 13th International Workshop on Document Analysis Systems IEEE"},{"key":"ref15","first-page":"735","article-title":"OCR as a Service: An Experimental Evaluation of Google Docs OCR, Tesseract, ABBYY FineReader, and Transym","author":"tafti","year":"2016","journal-title":"Advances in Visual Computing"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/ICDAR.2019.00013","article-title":"A Scalable Handwritten Text Recognition System","author":"ingle","year":"2019"},{"year":"0","key":"ref17","article-title":"Competitions – ICDAR2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24592-8_19"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2016.82"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0698-4"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"68150f","DOI":"10.1117\/12.783598","article-title":"The OCRopus open source OCR system","volume":"6815","author":"breuel","year":"2008","journal-title":"Document Recognition and Retrieval XV"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2017.19"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.12"},{"year":"0","key":"ref6","article-title":"ABBYY FineReader 14"},{"year":"0","key":"ref29","article-title":"ICDAR2019 Robust Reading Competition – Challenge on Multi-lingual Scene Text Detection and Recognition"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2007.4376991"},{"year":"0","key":"ref8","article-title":"Notes from Nature"},{"journal-title":"Google Cloud","article-title":"Detect Handwriting (OCR), Cloud Vision API","year":"0","key":"ref7"},{"key":"ref2","article-title":"High-Performance OCR for Printed English and Fraktur using LSTM Networks","author":"ul-hasan","year":"2013","journal-title":"presented at the Proceedings of the International Conference on Document Analysis and Recognition ICDAR"},{"year":"0","key":"ref9","article-title":"DIGIVOL"},{"article-title":"State of the Art Optical Character Recognition of 19th Century Fraktur Scripts using Open Source Engines","year":"2018","author":"reul","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333866"},{"key":"ref22","first-page":"2305","article-title":"CNN-N-Gram for Handwriting Word Recognition","author":"poznanski","year":"2016","journal-title":"presented at the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461951"},{"key":"ref24","first-page":"4","article-title":"Ensemble Optical Character Recognition Systems via Machine Learning","author":"shan","year":"2013","journal-title":"Course Project"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.158"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2501115.2501126"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01653-1_13"}],"event":{"name":"2019 15th International Conference on eScience (eScience)","start":{"date-parts":[[2019,9,24]]},"location":"San Diego, CA, USA","end":{"date-parts":[[2019,9,27]]}},"container-title":["2019 15th International Conference on eScience (eScience)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9036011\/9041688\/09041743.pdf?arnumber=9041743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:26:57Z","timestamp":1756754817000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9041743\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/escience.2019.00020","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}