Open vocabulary handwriting recognition using combined word-level and character-level language models

Kozielski, Michał; Rybach, David; Hahn, Stefan; Schlüter, Ralf; Ney, Hermann

doi:10.1109/icassp.2013.6639275

Cited by 27 publications

(11 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another approach for coping with OOV words consists of modeling text at a sub-word level, as a sequence of characters, syllables or multi-grams [15]. Hybrid approaches [16,17] consist of using word-based language models for the most frequent words and character-based models for the less frequent ones. In sub-word approaches, the dictionary is considerably reduced to the number of lexical units, as well as the computational complexity.…”

Section: Introductionmentioning

confidence: 99%

Transcription of Spanish Historical Handwritten Documents with Deep Neural Networks

et al. 2018

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

Transcription of Spanish Historical Handwritten Documents with Deep Neural Networks

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The state-of-the-art methods in the field of OFHR often applied on unconstrained open vocabulary databases [23]. Kozielski [23] used IAM database for English handwriting, creating language model for the character level and combine it into the word level language model.…”

Section: Comparative Resultsmentioning

confidence: 99%

“…Kozielski [23] used IAM database for English handwriting, creating language model for the character level and combine it into the word level language model. The major drawback for using such open database is that the The first attempt to develop a Malay word was by Wahap [12].…”

Section: Comparative Resultsmentioning

confidence: 99%

A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: study case on Malay word recognition

Al-Boeridi¹,

Ahmad

Koh

2015

Neural Comput & Applic

View full text Add to dashboard Cite

An off-line handwriting recognition (OFHR) system is a computerized system that is capable of intelligently converting human handwritten data extracted from scanned paper documents into an equivalent text format. This paper studies a proposed OFHR for Malaysian bank cheques written in the Malay language. The proposed system comprised of three components, namely a character recognition system (CRS), a hybrid decision system and lexical word classification system. Two types of feature extraction techniques have been used in the system, namely statistical and geometrical. Experiments show that the statistical feature is reliable, accessible and offers results that are more accurate. The CRS in this system was implemented using two individual classifiers, namely an adaptive multilayer feed-forward back-propagation neural network and support vector machine. The results of this study are very promising and could generalize to the entire Malay lexical dictionary in future work toward scaled-up applications.

show abstract

“…A further contribution of this paper is the presentation of a working recognition system that can cope with very large vocabularies of several hundred thousand words, which is much more than existing system [7,9], to the knowledge of the authors.…”

Section: Introductionmentioning

confidence: 99%

Handwriting recognition in historical documents using very large vocabularies

Frinken

Fischer

Martínez-Hinarejos

2013

Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing

View full text Add to dashboard Cite

lets see, to be written by Volkmar Lorem ipsum dolor sit amet, consectetur adipiscing elit. Pellentesque tincidunt fringilla urna, eu congue felis suscipit tincidunt. Aenean semper mi lacus, in laoreet arcu. Nulla velit metus, sodales id tincidunt id, condimentum a neque. Nunc adipiscing nulla egestas risus egestas a convallis leo egestas. Donec vitae libero et risus venenatis vulputate in id magna. Aliquam vel suscipit dolor. Praesent in elit in risus facilisis mattis. Vivamus et urna augue. Duis eu diam magna, sed placerat diam. Aliquam erat volutpat. Mauris pharetra, tellus ut posuere sodales, libero velit tempus odio, nec facilisis urna nisi quis nunc. Sed ut ligula vel turpis hendrerit condimentum. Nunc vel erat a eros tincidunt rutrum eget a massa. Quisque a leo in nibh porttitor fermentum.

show abstract

Open vocabulary handwriting recognition using combined word-level and character-level language models

Cited by 27 publications

References 21 publications

Transcription of Spanish Historical Handwritten Documents with Deep Neural Networks

Transcription of Spanish Historical Handwritten Documents with Deep Neural Networks

A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: study case on Malay word recognition

Handwriting recognition in historical documents using very large vocabularies

Contact Info

Product

Resources

About