PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guan, Shuhao, Lin, Moule, Xu, Cheng, Liu, Xinyi, Zhao, Jinman, Fan, Jiexin, Xu, Qi, Greene, Derek
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914162529009664
author Guan, Shuhao
Lin, Moule
Xu, Cheng
Liu, Xinyi
Zhao, Jinman
Fan, Jiexin
Xu, Qi
Greene, Derek
author_facet Guan, Shuhao
Lin, Moule
Xu, Cheng
Liu, Xinyi
Zhao, Jinman
Fan, Jiexin
Xu, Qi
Greene, Derek
contents 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correction to enhance both visual clarity and textual consistency, thereby improving text extraction from degraded historical documents.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 Detailed experiments on 13,831 pages of real historical documents in English, French, and Spanish show that the PreP-OCR pipeline reduces character error rates by 63.9-70.3% compared to OCR on raw images.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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20429
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy
Guan, Shuhao
Lin, Moule
Xu, Cheng
Liu, Xinyi
Zhao, Jinman
Fan, Jiexin
Xu, Qi
Greene, Derek
Computation and Language
Computer Vision and Pattern Recognition
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correction to enhance both visual clarity and textual consistency, thereby improving text extraction from degraded historical documents.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.
title PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.20429