{"id":"https://openalex.org/W4412945183","doi":"https://doi.org/10.18653/v1/2025.acl-long.749","title":"PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy","display_name":"PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945183","doi":"https://doi.org/10.18653/v1/2025.acl-long.749"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.749","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.749","pdf_url":"https://aclanthology.org/2025.acl-long.749.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.749.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102684501","display_name":"Shuhao Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuhao Guan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031820538","display_name":"Moule Lin","orcid":"https://orcid.org/0000-0001-6227-2392"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moule Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004417909","display_name":"Cheng-Zhong Xu","orcid":"https://orcid.org/0000-0003-1622-778X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395652","display_name":"Xinyi Liu","orcid":"https://orcid.org/0000-0001-5333-8054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyi Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036110657","display_name":"Jinman Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinman Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiexin Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiexin Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018908193","display_name":"Qi Xu","orcid":"https://orcid.org/0000-0002-0580-1005"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053619267","display_name":"Derek Greene","orcid":"https://orcid.org/0000-0001-8065-5418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Derek Greene","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.821,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98269012,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"15413","last_page":"15425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9857000112533569,"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":0.9857000112533569,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9757000207901001,"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/optical-character-recognition","display_name":"Optical character recognition","score":0.7872508764266968},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7802722454071045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7363283634185791},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5678287148475647},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.5079510807991028},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.49645429849624634},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46451535820961},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40025821328163147},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3643520772457123},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.24694085121154785},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.217641681432724}],"concepts":[{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7872508764266968},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7802722454071045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7363283634185791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5678287148475647},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.5079510807991028},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.49645429849624634},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46451535820961},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40025821328163147},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3643520772457123},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.24694085121154785},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.217641681432724},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.749","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.749","pdf_url":"https://aclanthology.org/2025.acl-long.749.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.20429","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.20429","pdf_url":"https://arxiv.org/pdf/2505.20429","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.749","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.749","pdf_url":"https://aclanthology.org/2025.acl-long.749.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945183.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2974904990","https://openalex.org/W2365681766","https://openalex.org/W2393963626","https://openalex.org/W2131730163","https://openalex.org/W2038329042","https://openalex.org/W2573990671","https://openalex.org/W2043611036","https://openalex.org/W4388916331","https://openalex.org/W2543788071","https://openalex.org/W2039452999"],"abstract_inverted_index":{"Shuhao":[0],"Guan,":[1],"Moule":[2],"Lin,":[3],"Cheng":[4],"Xu,":[5,13],"Xinyi":[6],"Liu,":[7],"Jinman":[8],"Zhao,":[9],"Jiexin":[10],"Fan,":[11],"Qi":[12],"Derek":[14],"Greene.":[15],"Proceedings":[16],"of":[17,22],"the":[18,23],"63rd":[19],"Annual":[20],"Meeting":[21],"Association":[24],"for":[25],"Computational":[26],"Linguistics":[27],"(Volume":[28],"1:":[29],"Long":[30],"Papers).":[31],"2025.":[32]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
