English

Improving OCR Accuracy on Early Printed Books using Deep Convolutional Networks

Computer Vision and Pattern Recognition 2018-02-28 v1 Digital Libraries

Abstract

This paper proposes a combination of a convolutional and a LSTM network to improve the accuracy of OCR on early printed books. While the standard model of line based OCR uses a single LSTM layer, we utilize a CNN- and Pooling-Layer combination in advance of an LSTM layer. Due to the higher amount of trainable parameters the performance of the network relies on a high amount of training examples to unleash its power. Hereby, the error is reduced by a factor of up to 44%, yielding a CER of 1% and below. To further improve the results we use a voting mechanism to achieve character error rates (CER) below 0.50.5%. The runtime of the deep model for training and prediction of a book behaves very similar to a shallow network.

Keywords

Cite

@article{arxiv.1802.10033,
  title  = {Improving OCR Accuracy on Early Printed Books using Deep Convolutional Networks},
  author = {Christoph Wick and Christian Reul and Frank Puppe},
  journal= {arXiv preprint arXiv:1802.10033},
  year   = {2018}
}

Comments

16 pages, 4 figures, 8 tables, submitted to JLCL Volume 33 (2018), Issue 1

R2 v1 2026-06-23T00:35:30.923Z