# Improving OCR Accuracy on Early Printed Books by utilizing Cross Fold Training and Voting

arXiv: https://arxiv.org/abs/1711.09670 · HTML: https://mlsanity.com/paper/1711.09670/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2017.

## Built on by (most cited first, 6 of 6)

- [Neural OCR Post-Hoc Correction of Historical Corpora](https://mlsanity.com/paper/2102.00583/) (2021)
- [Mixed Model OCR Training on Historical Latin Script for Out-of-the-Box Recognition and Finetuning](https://mlsanity.com/paper/2106.07881/) (2021)
- [Toward Advancing License Plate Super-Resolution in Real-World Scenarios: A Dataset and Benchmark](https://mlsanity.com/paper/2505.06393/) (2025)
- [Unknown-box Approximation to Improve Optical Character Recognition Performance](https://mlsanity.com/paper/2105.07983/) (2021)
- [Open Source Handwritten Text Recognition on Medieval Manuscripts using Mixed Models and Document-Specific Finetuning](https://mlsanity.com/paper/2201.07661/) (2022)
- [Combining OCR Models for Reading Early Modern Printed Books](https://mlsanity.com/paper/2305.07131/) (2023)

## Abstract (arXiv)

In this paper we introduce a method that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books. The method uses a combination of cross fold training and confidence based voting. After allocating the available ground truth in different subsets several training processes are performed, each resulting in a specific OCR model. The OCR text generated by these models then gets voted to determine the final output by taking the recognized characters, their alternatives, and the confidence values assigned to each character into consideration. Experiments on seven early printed books show that the proposed method outperforms the standard approach considerably by reducing the amount of errors by up to 50% and more.