Saved in:
Bibliographic Details
Main Authors: Belzarena, Diego, Mowlavi, Seginus, Artola, Aitor, Mariño, Camilo, Gardella, Marina, Ramírez, Ignacio, Tadros, Antoine, He, Roy, Bottaioli, Natalia, Rajaei, Boshra, Randall, Gregory, Morel, Jean-Michel
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.14557
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908496284352512
author Belzarena, Diego
Mowlavi, Seginus
Artola, Aitor
Mariño, Camilo
Gardella, Marina
Ramírez, Ignacio
Tadros, Antoine
He, Roy
Bottaioli, Natalia
Rajaei, Boshra
Randall, Gregory
Morel, Jean-Michel
author_facet Belzarena, Diego
Mowlavi, Seginus
Artola, Aitor
Mariño, Camilo
Gardella, Marina
Ramírez, Ignacio
Tadros, Antoine
He, Roy
Bottaioli, Natalia
Rajaei, Boshra
Randall, Gregory
Morel, Jean-Michel
contents Current OCR systems are based on deep learning models trained on large amounts of data. Although they have shown some ability to generalize to unseen data, especially in detection tasks, they can struggle with recognizing low-quality data. This is particularly evident for printed documents, where intra-domain data variability is typically low, but inter-domain data variability is high. In that context, current OCR methods do not fully exploit each document's redundancy. We propose an unsupervised method by leveraging the redundancy of character shapes within a document to correct imperfect outputs of a given OCR system and suggest better clustering. To this aim, we introduce an extended Gaussian Mixture Model (GMM) by alternating an Expectation-Maximization (EM) algorithm with an intra-cluster realignment process and normality statistical testing. We demonstrate improvements in documents with various levels of degradation, including recovered Uruguayan military archives and 17th to mid-20th century European newspapers.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14557
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving OCR using internal document redundancy
Belzarena, Diego
Mowlavi, Seginus
Artola, Aitor
Mariño, Camilo
Gardella, Marina
Ramírez, Ignacio
Tadros, Antoine
He, Roy
Bottaioli, Natalia
Rajaei, Boshra
Randall, Gregory
Morel, Jean-Michel
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
Current OCR systems are based on deep learning models trained on large amounts of data. Although they have shown some ability to generalize to unseen data, especially in detection tasks, they can struggle with recognizing low-quality data. This is particularly evident for printed documents, where intra-domain data variability is typically low, but inter-domain data variability is high. In that context, current OCR methods do not fully exploit each document's redundancy. We propose an unsupervised method by leveraging the redundancy of character shapes within a document to correct imperfect outputs of a given OCR system and suggest better clustering. To this aim, we introduce an extended Gaussian Mixture Model (GMM) by alternating an Expectation-Maximization (EM) algorithm with an intra-cluster realignment process and normality statistical testing. We demonstrate improvements in documents with various levels of degradation, including recovered Uruguayan military archives and 17th to mid-20th century European newspapers.
title Improving OCR using internal document redundancy
topic Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2508.14557