[ { "key": "22P69D9B", "version": 3491, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/22P69D9B", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/22P69D9B", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/RTW73K66", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } } }, "data": { "key": "22P69D9B", "version": 3491, "parentItem": "RTW73K66", "itemType": "attachment", "linkMode": "linked_url", "title": "Public Pair - Public Pair", "accessDate": "2013-02-02T03:41:51Z", "url": "http://portal.uspto.gov/pair/PublicPair", "note": "", "contentType": "text/html", "charset": "windows-1252", "tags": [], "relations": {}, "dateAdded": "2013-11-07T15:36:18Z", "dateModified": "2013-11-07T15:36:18Z" } }, { "key": "RTW73K66", "version": 3491, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/RTW73K66", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/RTW73K66", "type": "text/html" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } }, "creatorSummary": "Thomas et al.", "parsedDate": "2012", "numChildren": 4 }, "data": { "key": "RTW73K66", "version": 3491, "itemType": "patent", "title": "Itemized receipt extraction using machine learning", "creators": [ { "creatorType": "inventor", "firstName": "James", "lastName": "Thomas" }, { "creatorType": "inventor", "firstName": "Gopali", "lastName": "Contractor" }, { "creatorType": "inventor", "firstName": "Thomas L.", "lastName": "Packer" }, { "creatorType": "inventor", "firstName": "Michael A.", "lastName": "Haley" } ], "abstractNote": "A method, including retrieving a transaction receipt, wherein the transaction receipt includes unstructured data. Features indicating details of the transaction are extracted from the unstructured data, and using a receipt language model, weights are applied to the features. Based on the features and the weights, labels are associated with tokens in the receipt, and the receipt language model is updated with the extracted features, the applied weights and the associated labels.", "place": "", "country": "", "assignee": "", "issuingAuthority": "", "patentNumber": "", "filingDate": "2012-00-00 2012", "pages": "", "applicationNumber": "13/532,863", "priorityNumbers": "", "issueDate": "2012", "priorityDate": "", "references": "", "legalStatus": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [ "TQ9CEZIB" ], "relations": {}, "dateAdded": "2013-11-07T15:36:18Z", "dateModified": "2013-11-07T15:36:18Z" } }, { "key": "AM5J4S39", "version": 3491, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/AM5J4S39", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/AM5J4S39", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/RTW73K66", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } } }, "data": { "key": "AM5J4S39", "version": 3491, "parentItem": "RTW73K66", "itemType": "attachment", "linkMode": "linked_url", "title": "US20120330971.pdf", "accessDate": "2013-02-01T21:37:35Z", "url": "https://docs.google.com/a/google.com/viewer?url=patentimages.storage.googleapis.com/pdfs/US20120330971.pdf", "note": "", "contentType": "text/html", "charset": "utf-8", "tags": [], "relations": {}, "dateAdded": "2013-11-07T15:36:18Z", "dateModified": "2013-11-07T15:36:18Z" } }, { "key": "D37SS8BJ", "version": 3491, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/D37SS8BJ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/D37SS8BJ", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/RTW73K66", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } } }, "data": { "key": "D37SS8BJ", "version": 3491, "parentItem": "RTW73K66", "itemType": "attachment", "linkMode": "linked_url", "title": "Patent US20120330971 - Itemized receipt extraction using machine learning - Google Patents", "accessDate": "2013-02-01T21:37:03Z", "url": "http://www.google.com/patents/US20120330971", "note": "", "contentType": "text/html", "charset": "utf-8", "tags": [], "relations": {}, "dateAdded": "2013-11-07T15:36:18Z", "dateModified": "2013-11-07T15:36:18Z" } }, { "key": "B9S4Q5PN", "version": 3491, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/B9S4Q5PN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/B9S4Q5PN", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/RTW73K66", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } } }, "data": { "key": "B9S4Q5PN", "version": 3491, "parentItem": "RTW73K66", "itemType": "attachment", "linkMode": "linked_url", "title": "Itemized Receipt Extraction Using Machine Learning", "accessDate": "2013-02-01T21:37:17Z", "url": "http://www.freshpatents.com/-dt20121227ptan20120330971.php", "note": "", "contentType": "text/html", "charset": "utf-8", "tags": [], "relations": {}, "dateAdded": "2013-11-07T15:36:18Z", "dateModified": "2013-11-07T15:36:18Z" } }, { "key": "63FS9WWM", "version": 3491, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/63FS9WWM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/63FS9WWM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } }, "creatorSummary": "Packer and Embley", "parsedDate": "2013", "numChildren": 0 }, "data": { "key": "63FS9WWM", "version": 3491, "itemType": "conferencePaper", "title": "Populating Ontologies with Data from Lists in Family History Books", "creators": [ { "creatorType": "author", "firstName": "Thomas L.", "lastName": "Packer" }, { "creatorType": "author", "firstName": "David W.", "lastName": "Embley" } ], "abstractNote": "Abstract—A flexible, accurate, and cost-effective method of\nautomatically extracting facts from lists in OCRed documents\nand inserting them into an ontology would help make those facts\nmachine searchable, queryable, and linkable and expose their\nrich ontological interrelationships. To work well, such a process\nmust be adaptable to variations in list format, tolerant of OCR\nerrors, and careful in its selection of human guidance.We propose\na wrapper-induction solution for information extraction that is\nspecialized for lists in OCRed documents. In this approach, we\ninduce a regular-expression grammar that can infer list structure\nand field labels from OCR text. We decrease the cost and improve\nthe accuracy of this induction process using semi-supervised\nmachine learning and active learning, allowing induction of a\nwrapper from a single hand-labeled instance per field per list. To\nfurther reduce cost, we use the wrappers learned from the semisupervised\nprocess to bootstrap an automatic (self-supervised)\nwrapper induction process for additional lists in the same domain.\nIn both induction scenarios, we automatically map labeled text\nto a rich variety of ontologically structured facts. We evaluate\nour implementation in terms of annotation cost and extraction\nquality for lists in family history books.", "proceedingsTitle": "Proceedings of the Family History Technology Workshop", "conferenceName": "Family History Technology Workshop", "publisher": "", "place": "Salt Lake City, Utah, USA", "date": "2013", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "TQ9CEZIB" ], "relations": {}, "dateAdded": "2013-11-07T15:36:18Z", "dateModified": "2013-11-07T15:36:18Z" } }, { "key": "5MTNCDTE", "version": 2, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/5MTNCDTE", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/5MTNCDTE", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/4W4U6T47", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } } }, "data": { "key": "5MTNCDTE", "version": 2, "parentItem": "4W4U6T47", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Snapshot", "accessDate": "2010-10-13T17:07:57Z", "url": "http://portal.acm.org/citation.cfm?id=146380", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "citation.html", "md5": "3d9b1c46e52d7a2cfd08e9d012cf879c", "mtime": 1286989678509, "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "SNUCMKW6", "version": 2, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/SNUCMKW6", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/SNUCMKW6", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/EDQIQRX4", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } } }, "data": { "key": "SNUCMKW6", "version": 2, "parentItem": "EDQIQRX4", "itemType": "attachment", "linkMode": "imported_url", "title": "comparing Tesseract to Enterprise solutions like Abby Fine Reader - tesseract-ocr | Google Groups", "accessDate": "2010-01-20T22:50:04Z", "url": "http://groups.google.com/group/tesseract-ocr/browse_thread/thread/f01135c5228b7f30", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "f01135c5228b7f30.html", "md5": "b221642c3582a7d18877af48d76aa0b9", "mtime": 1264027804939, "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "GVD6CR8S", "version": 2, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/GVD6CR8S", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/GVD6CR8S", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/EDQIQRX4", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "GVD6CR8S", "version": 2, "parentItem": "EDQIQRX4", "itemType": "attachment", "linkMode": "imported_url", "title": "2007-IUPR-28Nov_1234.pdf", "accessDate": "2010-01-20T22:48:46Z", "url": "http://pubs.iupr.org/DATA/2007-IUPR-28Nov_1234.pdf", "note": "", "contentType": "application/pdf", "charset": "", "filename": "2007-IUPR-28Nov_1234.pdf", "md5": "86a35c8d23ab137280ebaec6ba24adb6", "mtime": 1264027728439, "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "J4NE6MFB", "version": 2, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/J4NE6MFB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/J4NE6MFB", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/XX4TQGEP", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } } }, "data": { "key": "J4NE6MFB", "version": 2, "parentItem": "XX4TQGEP", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Snapshot", "accessDate": "2010-07-12T17:30:05Z", "url": "http://portal.acm.org/citation.cfm?id=1568296.1568308&coll=GUIDE&dl=GUIDE&type=series&idx=SERIES10714&part=series&WantType=Proceedings&title=AICPS&CFID=://sites.google.com/site/and2009workshop/proceedings&CFTOKEN=sites.google.com/site/and2009workshop/proceedings", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "citation.html", "md5": "7fe6028568baf3244be3cc175d3aaeb1", "mtime": 1278955804500, "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "SN3JGTRW", "version": 2, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/SN3JGTRW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/SN3JGTRW", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/KD8KQS59", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "SN3JGTRW", "version": 2, "parentItem": "KD8KQS59", "itemType": "attachment", "linkMode": "imported_url", "title": "IEEE Xplore Full Text PDF", "accessDate": "2012-01-18T00:15:48Z", "url": "http://ieeexplore.ieee.org/ielx3/3741/10939/00502518.pdf?tp=&arnumber=502518&isnumber=10939", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Lopresti - 1996 - Robust retrieval of noisy text.pdf", "md5": "8d27d43178b45e2755a1ded9aa51531f", "mtime": 1326845870234, "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "DIHHGTAB", "version": 2, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/DIHHGTAB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/DIHHGTAB", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/Q73P2SZB", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } } }, "data": { "key": "DIHHGTAB", "version": 2, "parentItem": "Q73P2SZB", "itemType": "attachment", "linkMode": "imported_url", "title": "ScienceDirect Snapshot", "accessDate": "2010-10-15T15:14:27Z", "url": "http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6V14-4S50K33-1&_user=456938&_coverDate=08%2F31%2F2008&_rdoc=1&_fmt=high&_orig=search&_origin=search&_sort=d&_docanchor=&view=c&_searchStrId=1499694941&_rerunOrigin=scholar.google&_acct=C000021830&_version=1&_urlVersion=0&_userid=456938&md5=4e9507d1b9a68ac187e3666666b40cc5&searchtype=a", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "science.html", "md5": "40615cc51493a10cc42de559d813aef2", "mtime": 1287155668562, "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "EETSETM9", "version": 1, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/EETSETM9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/EETSETM9", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/4W4U6T47", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } } }, "data": { "key": "EETSETM9", "version": 1, "parentItem": "4W4U6T47", "itemType": "attachment", "linkMode": "linked_url", "title": "Techniques for automatically correcting words in text", "accessDate": "2010-10-13T17:07:54Z", "url": "http://portal.acm.org/citation.cfm?id=146380", "note": "", "contentType": "text/html", "charset": "utf-8", "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "B38TKP98", "version": 1, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/B38TKP98", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/B38TKP98", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/4W4U6T47", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "B38TKP98", "version": 1, "parentItem": "4W4U6T47", "itemType": "note", "note": "

Short Summary:

\n

Kukich reviews spelling detection and correction algorithms, some using context and some not, unified within the framework of generating, ranking and selecting candidate corrections.

", "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "5NX687NW", "version": 1, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/5NX687NW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/5NX687NW", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/EDQIQRX4", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "5NX687NW", "version": 1, "parentItem": "EDQIQRX4", "itemType": "note", "note": "

Good explanation of the pieces, design and goals of OCRopus, plus a small evaluation in errors against other OCR systems.

\n

(Read: 2010.01)

", "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "NZV48J5Q", "version": 1, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/NZV48J5Q", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/NZV48J5Q", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/Q73P2SZB", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } } }, "data": { "key": "NZV48J5Q", "version": 1, "parentItem": "Q73P2SZB", "itemType": "attachment", "linkMode": "linked_url", "title": "ScienceDirect - Pattern Recognition : Forty years of research in character and document recognition—an industrial perspective", "accessDate": "2010-10-15T15:14:46Z", "url": "http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6V14-4S50K33-1&_user=456938&_coverDate=08%2F31%2F2008&_rdoc=1&_fmt=high&_orig=search&_origin=search&_sort=d&_docanchor=&view=c&_searchStrId=1499694941&_rerunOrigin=scholar.google&_acct=C000021830&_version=1&_urlVersion=0&_userid=456938&md5=4e9507d1b9a68ac187e3666666b40cc5&searchtype=a", "note": "", "contentType": "text/html", "charset": "utf-8", "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "DFJ52SCU", "version": 1, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/DFJ52SCU", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/DFJ52SCU", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/Q73P2SZB", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } } }, "data": { "key": "DFJ52SCU", "version": 1, "parentItem": "Q73P2SZB", "itemType": "attachment", "linkMode": "linked_url", "title": "science (application/pdf Object)", "accessDate": "2010-10-15T15:14:51Z", "url": "http://www.sciencedirect.com/science?_ob=MImg&_imagekey=B6V14-4S50K33-1-1M&_cdi=5664&_user=456938&_pii=S0031320308000964&_origin=search&_coverDate=08%2F31%2F2008&_sk=999589991&view=c&wchp=dGLzVlz-zSkzV&md5=3748a90ea35a0c4927341f007bf9cf5a&ie=/sdarticle.pdf", "note": "", "contentType": "application/pdf", "charset": "windows-1252", "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "9NNIJUDV", "version": 1, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/9NNIJUDV", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/9NNIJUDV", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/XX4TQGEP", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } } }, "data": { "key": "9NNIJUDV", "version": 1, "parentItem": "XX4TQGEP", "itemType": "attachment", "linkMode": "linked_url", "title": "p63-subramanian.pdf (application/pdf Object)", "accessDate": "2010-07-12T17:30:21Z", "url": "http://delivery.acm.org/10.1145/1570000/1568308/p63-subramanian.pdf?key1=1568308&key2=9955598721&coll=GUIDE&dl=GUIDE&CFID=94624696&CFTOKEN=79201858", "note": "", "contentType": "application/pdf", "charset": "windows-1252", "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "4W4U6T47", "version": 1, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/4W4U6T47", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/4W4U6T47", "type": "text/html" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } }, "creatorSummary": "Kukich", "parsedDate": "1992", "numChildren": 5 }, "data": { "key": "4W4U6T47", "version": 1, "itemType": "journalArticle", "title": "Techniques for Automatically Correcting Words in Text", "creators": [ { "creatorType": "author", "firstName": "Karen", "lastName": "Kukich" } ], "abstractNote": "Research aimed at correcting words in text has focused on three progressively more difficult problems:(1) nonword error detection; (2) isolated-word error correction; and (3) context-dependent work correction. In response to the first problem, efficient pattern-matching and n-gram analysis techniques have been developed for detecting strings that do not appear in a given word list. In response to the second problem, a variety of general and application-specific spelling correction techniques have been developed. Some of them were based on detailed studies of spelling error patterns. In response to the third problem, a few experiments using natural-language-processing tools or statistical-language models have been carried out. This article surveys documented findings on spelling error patterns, provides descriptions of various nonword detection and isolated-word error correction techniques, reviews the state of the art of context-dependent word correction techniques, and discusses research issues related to all three areas of automatic error correction in text.", "publicationTitle": "ACM Computing Surveys", "publisher": "", "place": "", "date": "1992", "volume": "24", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "377-439", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "2010-10-13T17:07:48Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Statistical Language Model" }, { "tag": "context-dependent spelling correction", "type": 1 }, { "tag": "grammar checking", "type": 1 }, { "tag": "n-gram analysis", "type": 1 }, { "tag": "natural-language-processing models", "type": 1 }, { "tag": "neural net classifiers", "type": 1 }, { "tag": "optical character recognition (OCR)" }, { "tag": "spell checking", "type": 1 }, { "tag": "spelling error detection", "type": 1 }, { "tag": "spelling error patterns", "type": 1 }, { "tag": "word recognition and correction", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "Q73P2SZB", "version": 1, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/Q73P2SZB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/Q73P2SZB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } }, "creatorSummary": "Fujisawa", "parsedDate": "2008", "numChildren": 6 }, "data": { "key": "Q73P2SZB", "version": 1, "itemType": "journalArticle", "title": "Forty Years of Research in Character and Document Recognition --- An Industrial Perspective", "creators": [ { "creatorType": "author", "firstName": "Hiromichi", "lastName": "Fujisawa" } ], "abstractNote": "This paper presents an overview on the last 40-years of technical advances in the field of character and document recognition. Representative developments in each decade are described. Then, key technical developments in the specific area of Kanji recognition in Japan are highlighted. The main part of the paper discusses robustness design principles, which have proven to be effective to solve complex problems in postal address recognition. Included are the hypothesis-driven principle, deferred decision/multiple-hypotheses principle, information integration principle, alternative solution principle, and perturbation principle. Finally, future prospects, the [`]long-tail' phenomena, and promising new applications are discussed.", "publicationTitle": "Pattern Recognition", "publisher": "", "place": "", "date": "2008", "volume": "41", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "2435-2446", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "2010-10-15T15:14:22Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ScienceDirect", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Character recognition", "type": 1 }, { "tag": "Digital pen", "type": 1 }, { "tag": "Handwriting recognition", "type": 1 }, { "tag": "Hypothesis-driven approaches", "type": 1 }, { "tag": "Kanji recognition", "type": 1 }, { "tag": "Robustness design", "type": 1 }, { "tag": "information integration" }, { "tag": "optical character recognition (OCR)" }, { "tag": "postal address recognition" } ], "collections": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "XX4TQGEP", "version": 1, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/XX4TQGEP", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/XX4TQGEP", "type": "text/html" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } }, "creatorSummary": "Subramanian et al.", "parsedDate": "2009", "numChildren": 2 }, "data": { "key": "XX4TQGEP", "version": 1, "itemType": "conferencePaper", "title": "Robust named entity detection using an Arabic offline handwriting recognition system", "creators": [ { "creatorType": "author", "firstName": "Krishna", "lastName": "Subramanian" }, { "creatorType": "author", "firstName": "Rohit", "lastName": "Prasad" }, { "creatorType": "author", "firstName": "Prem", "lastName": "Natarajan" } ], "abstractNote": "Text from Arabic optical handwriting recognition (OHR) systems can provide key indexing information. In particular, the text is rich in named entities (NEs) and detection of such entities is critical for search applications. Traditional approaches for detecting NEs in optical character recognition (OCR) output look for these NEs in the single-best recognition results. Due to the inevitable presence of recognition errors in the single-best output, such approaches usually result in low recall. Given that a lattice is more likely to contain the correct answer, we explore NE detection from word lattices produced by our Arabic handwriting recognition system. Since the improvement in recall is accompanied by a large number of false positives, we use confidence scores based on posterior scores to control precision. We show a 7% improvement in true detects for the same false acceptance rate on using lattices instead of 1-best hypothesis for NE lookup.", "proceedingsTitle": "Proceedings of The Third Workshop on Analytics for Noisy Unstructured Text Data", "conferenceName": "", "publisher": "ACM", "place": "Barcelona, Spain", "date": "2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "63-68", "series": "", "seriesNumber": "", "DOI": "10.1145/1568296.1568308", "ISBN": "978-1-60558-496-6", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=1568296.1568308&coll=GUIDE&dl=GUIDE&type=series&idx=SERIES10714&part=series&WantType=Proceedings&title=AICPS&CFID=://sites.google.com/site/and2009workshop/proceedings&CFTOKEN=sites.google.com/site/and2009workshop/proceedings", "accessDate": "2010-07-12T17:30:02Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "arabic handwriting recognition", "type": 1 }, { "tag": "hidden Markov model (HMM)" }, { "tag": "lattice search", "type": 1 }, { "tag": "named entity detection", "type": 1 }, { "tag": "optical character recognition (OCR)" }, { "tag": "optical handwriting recognition (OHR)" } ], "collections": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "3KDE49JD", "version": 1, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/3KDE49JD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/3KDE49JD", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/4W4U6T47", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } } }, "data": { "key": "3KDE49JD", "version": 1, "parentItem": "4W4U6T47", "itemType": "attachment", "linkMode": "linked_url", "title": "p377-kukich.pdf (application/pdf Object)", "accessDate": "2010-10-13T17:08:02Z", "url": "http://delivery.acm.org/10.1145/150000/146380/p377-kukich.pdf?key1=146380&key2=6359896821&coll=GUIDE&dl=GUIDE&CFID=105643966&CFTOKEN=88975565", "note": "", "contentType": "application/pdf", "charset": "windows-1252", "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "WBE83MFR", "version": 1, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/WBE83MFR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/WBE83MFR", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/4W4U6T47", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "WBE83MFR", "version": 1, "parentItem": "4W4U6T47", "itemType": "note", "note": "

Summary:

\n

Kukich reviews spelling correction algorithms divided into three settings: non-word error detection, isolated-word error correction, and context-dependent word correction.  She unifies the presentation using a framework of generating, ranking and selecting candidate corrections.

", "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "J78I2ATT", "version": 1, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/J78I2ATT", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/J78I2ATT", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/Q73P2SZB", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "J78I2ATT", "version": 1, "parentItem": "Q73P2SZB", "itemType": "note", "note": "

Summary:

\n

Briefly describes advances in OCR and document recognition in each decade since these began, from hardware based approaches to software based approaches.

\n

Describes several principles applied to OCR and document analysis, including: hypothesis-driven principle, deferred decision / multiple hypotheses principle, information integration principle (process integration, combination-based integration, corroboration-based integration), alternative solutions principle, and perturbation principle.

\n

Examples in bank check recognition and postal address recognition (Japanese) are used as examples.  These two applications, along with \"business form reading\" constitute the head of a graph with a long tale of marketable applications.

", "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } }, { "key": "7V9KGXW2", "version": 1, "library": { "type": "group", "id": 9198, "name": "Noisy OCR Group", "links": { "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/9198/items/7V9KGXW2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/noisy_ocr_group/items/7V9KGXW2", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/9198/items/Q73P2SZB", "type": "application/json" } }, "meta": { "createdByUser": { "id": 33222, "username": "tpacker", "name": "Thomas L. Packer", "links": { "alternate": { "href": "https://www.zotero.org/tpacker", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "7V9KGXW2", "version": 1, "parentItem": "Q73P2SZB", "itemType": "note", "note": "

Short Summary:

\n

Fujisawa describes advances in OCR and document recognition, based on robustness design principles, in each decade since these technologies were first used in the 1950's, from hardware based approaches to software based approaches.

", "tags": [], "relations": {}, "dateAdded": "2013-02-06T18:14:30Z", "dateModified": "2013-02-06T18:14:30Z" } } ]