@inproceedings{guan-etal-2025-prep,
title = "{P}re{P}-{OCR}: A Complete Pipeline for Document Image Restoration and Enhanced {OCR} Accuracy",
author = "Guan, Shuhao and
Lin, Moule and
Xu, Cheng and
Liu, Xinyi and
Zhao, Jinman and
Fan, Jiexin and
Xu, Qi and
Greene, Derek",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.749/",
doi = "10.18653/v1/2025.acl-long.749",
pages = "15413--15425",
ISBN = "979-8-89176-251-0",
abstract = "This paper introduces PreP-OCR, a two-stage pipeline that combines document image restoration with semantic-aware post-OCR correction to enhance both visual clarity and textual consistency, thereby improving text extraction from degraded historical documents.First, we synthesize document-image pairs from plaintext, rendering them with diverse fonts and layouts and then applying a randomly ordered set of degradation operations. An image restoration model is trained on this synthetic data, using multi-directional patch extraction and fusion to process large images. Second, a ByT5 post-OCR model, fine-tuned on synthetic historical text pairs, addresses remaining OCR errors.Detailed experiments on 13,831 pages of real historical documents in English, French, and Spanish show that the PreP-OCR pipeline reduces character error rates by 63.9-70.3{\%} compared to OCR on raw images. Our pipeline demonstrates the potential of integrating image restoration with linguistic error correction for digitizing historical archives."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guan-etal-2025-prep">
<titleInfo>
<title>PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuhao</namePart>
<namePart type="family">Guan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moule</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinman</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiexin</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="family">Greene</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>This paper introduces PreP-OCR, a two-stage pipeline that combines document image restoration with semantic-aware post-OCR correction to enhance both visual clarity and textual consistency, thereby improving text extraction from degraded historical documents.First, we synthesize document-image pairs from plaintext, rendering them with diverse fonts and layouts and then applying a randomly ordered set of degradation operations. An image restoration model is trained on this synthetic data, using multi-directional patch extraction and fusion to process large images. Second, a ByT5 post-OCR model, fine-tuned on synthetic historical text pairs, addresses remaining OCR errors.Detailed experiments on 13,831 pages of real historical documents in English, French, and Spanish show that the PreP-OCR pipeline reduces character error rates by 63.9-70.3% compared to OCR on raw images. Our pipeline demonstrates the potential of integrating image restoration with linguistic error correction for digitizing historical archives.</abstract>
<identifier type="citekey">guan-etal-2025-prep</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.749</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.749/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>15413</start>
<end>15425</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy
%A Guan, Shuhao
%A Lin, Moule
%A Xu, Cheng
%A Liu, Xinyi
%A Zhao, Jinman
%A Fan, Jiexin
%A Xu, Qi
%A Greene, Derek
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F guan-etal-2025-prep
%X This paper introduces PreP-OCR, a two-stage pipeline that combines document image restoration with semantic-aware post-OCR correction to enhance both visual clarity and textual consistency, thereby improving text extraction from degraded historical documents.First, we synthesize document-image pairs from plaintext, rendering them with diverse fonts and layouts and then applying a randomly ordered set of degradation operations. An image restoration model is trained on this synthetic data, using multi-directional patch extraction and fusion to process large images. Second, a ByT5 post-OCR model, fine-tuned on synthetic historical text pairs, addresses remaining OCR errors.Detailed experiments on 13,831 pages of real historical documents in English, French, and Spanish show that the PreP-OCR pipeline reduces character error rates by 63.9-70.3% compared to OCR on raw images. Our pipeline demonstrates the potential of integrating image restoration with linguistic error correction for digitizing historical archives.
%R 10.18653/v1/2025.acl-long.749
%U https://aclanthology.org/2025.acl-long.749/
%U https://doi.org/10.18653/v1/2025.acl-long.749
%P 15413-15425
Markdown (Informal)
[PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy](https://aclanthology.org/2025.acl-long.749/) (Guan et al., ACL 2025)
ACL
- Shuhao Guan, Moule Lin, Cheng Xu, Xinyi Liu, Jinman Zhao, Jiexin Fan, Qi Xu, and Derek Greene. 2025. PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15413–15425, Vienna, Austria. Association for Computational Linguistics.