Next Article in Journal
Image-Guided Cancer Nanomedicine
Next Article in Special Issue
A New Binarization Algorithm for Historical Documents
Previous Article in Journal
Secure Image Transmission Using Fractal and 2D-Chaotic Map
Previous Article in Special Issue
A Holistic Technique for an Arabic OCR System
Article Menu
Issue 1 (January) cover image

Export Article

Open AccessArticle
J. Imaging 2018, 4(1), 15; https://doi.org/10.3390/jimaging4010015

Transcription of Spanish Historical Handwritten Documents with Deep Neural Networks

1
PRHLT Research Center, Universitat Politècnica de València, 46022 València, Spain
2
Department of Computer Engineering, University of Balamand, 2960 Balamand, Lebanon
3
Institut Mines-Télécom/Télécom ParisTech, Université Paris-Saclay, 75013 Paris, France
*
Author to whom correspondence should be addressed.
Received: 30 October 2017 / Revised: 22 December 2017 / Accepted: 2 January 2018 / Published: 11 January 2018
(This article belongs to the Special Issue Document Image Processing)
View Full-Text   |   Download PDF [1223 KB, uploaded 11 January 2018]   |  

Abstract

The digitization of historical handwritten document images is important for the preservation of cultural heritage. Moreover, the transcription of text images obtained from digitization is necessary to provide efficient information access to the content of these documents. Handwritten Text Recognition (HTR) has become an important research topic in the areas of image and computational language processing that allows us to obtain transcriptions from text images. State-of-the-art HTR systems are, however, far from perfect. One difficulty is that they have to cope with image noise and handwriting variability. Another difficulty is the presence of a large amount of Out-Of-Vocabulary (OOV) words in ancient historical texts. A solution to this problem is to use external lexical resources, but such resources might be scarce or unavailable given the nature and the age of such documents. This work proposes a solution to avoid this limitation. It consists of associating a powerful optical recognition system that will cope with image noise and variability, with a language model based on sub-lexical units that will model OOV words. Such a language modeling approach reduces the size of the lexicon while increasing the lexicon coverage. Experiments are first conducted on the publicly available Rodrigo dataset, which contains the digitization of an ancient Spanish manuscript, with a recognizer based on Hidden Markov Models (HMMs). They show that sub-lexical units outperform word units in terms of Word Error Rate (WER), Character Error Rate (CER) and OOV word accuracy rate. This approach is then applied to deep net classifiers, namely Bi-directional Long-Short Term Memory (BLSTMs) and Convolutional Recurrent Neural Nets (CRNNs). Results show that CRNNs outperform HMMs and BLSTMs, reaching the lowest WER and CER for this image dataset and significantly improving OOV recognition. View Full-Text
Keywords: historical handwritten transcription; out-of-vocabulary word recognition; character-level language model; word structure retrieval historical handwritten transcription; out-of-vocabulary word recognition; character-level language model; word structure retrieval
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Granell, E.; Chammas, E.; Likforman-Sulem, L.; Martínez-Hinarejos, C.-D.; Mokbel, C.; Cîrstea, B.-I. Transcription of Spanish Historical Handwritten Documents with Deep Neural Networks. J. Imaging 2018, 4, 15.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
J. Imaging EISSN 2313-433X Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top