ICFHR2016 Competition on Handwritten Text Recognition on the READ Dataset

Lafuente, José Vicente; Romero, Verónica; Toselli, Alejandro H.; Vidal, Enrique

doi:10.1109/icfhr.2016.0120

Cited by 72 publications

(40 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After training on 90,000 lines of text, the model had an error rate of 12% on previously unseen data. This is slightly higher than other studies (Sánchez et al, 2014;Sánchez et al, 2015;Sánchez et al, 2016) which generally worked with cleaner, more curated data, potentially explaining the difference. This error rate also exceeds the 2.5% error rate achieved by volunteers when compared to experts.…”

contrasting

confidence: 59%

Combining Human and Machine Transcriptions on the Zooniverse Platform

Hanson¹,

Simenstad

2018

Proceedings of the 2018 EMNLP Workshop W-Nut: The 4th Workshop on Noisy User-Generated Text

View full text Add to dashboard Cite

Transcribing handwritten documents to create fully searchable texts is an essential part of the archival process. Traditional text recognition methods, such as optical character recognition (OCR), do not work on handwritten documents due to their frequent noisiness and OCR's need for individually segmented letters. Crowdsourcing and improved machine models are two modern methods for transcribing handwritten documents.

show abstract

contrasting

confidence: 59%

Combining Human and Machine Transcriptions on the Zooniverse Platform

Hanson¹,

Simenstad

2018

Proceedings of the 2018 EMNLP Workshop W-Nut: The 4th Workshop on Noisy User-Generated Text

View full text Add to dashboard Cite

show abstract

“…The data set consists of a subset of documents from the Ratsprotokolle collection composed of minutes of the council meetings held from 1470 to 1805. This data set was the basis for a HTR competition at the ICFHR2016 [40].…”

Section: A Data Setsmentioning

confidence: 99%

Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition

Michael

Labahn

Grüning³

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

103

View full text Add to dashboard Cite

Encoder-decoder models have become an effective approach for sequence learning tasks like machine translation, image captioning and speech recognition, but have yet to show competitive results for handwritten text recognition. To this end, we propose an attention-based sequence-to-sequence model. It combines a convolutional neural network as a generic feature extractor with a recurrent neural network to encode both the visual information, as well as the temporal context between characters in the input image, and uses a separate recurrent neural network to decode the actual character sequence. We make experimental comparisons between various attention mechanisms and positional encodings, in order to find an appropriate alignment between the input and output sequence. The model can be trained end-to-end and the optional integration of a hybrid loss allows the encoder to retain an interpretable and usable output, if desired. We achieve competitive results on the IAM and ICFHR2016 READ data sets compared to the state-of-theart without the use of a language model, and we significantly improve over any recent sequence-to-sequence approaches.

show abstract

“…In our case, they will be all the characters in the alphabet plus the semantic labels. In the experiments for transfer learning we have tested only one HTR model that was trained with the following datasets: IAM [14], Bentham [15], Bozen [16], and some datasets used by us internally: IntoThePast, Wiensanktulrich, Wienvotivkirche and ITS.…”

Section: Transfer Learningmentioning

confidence: 99%

Joint Recognition of Handwritten Text and Named Entities with a Neural End-to-End Model

Carbonell

Villegas²,

Fornés

et al. 2018

2018 13th IAPR International Workshop on Document Analysis Systems (DAS)

View full text Add to dashboard Cite

When extracting information from handwritten documents, text transcription and named entity recognition are usually faced as separate subsequent tasks. This has the disadvantage that errors in the first module affect heavily the performance of the second module. In this work we propose to do both tasks jointly, using a single neural network with a common architecture used for plain text recognition. Experimentally, the work has been tested on a collection of historical marriage records. Results of experiments are presented to show the effect on the performance for different configurations: different ways of encoding the information, doing or not transfer learning and processing at text line or multi-line region level. The results are comparable to state of the art reported in the ICDAR 2017 Information Extraction competition, even though the proposed technique does not use any dictionaries, language modeling or post processing.

show abstract

ICFHR2016 Competition on Handwritten Text Recognition on the READ Dataset

Cited by 72 publications

References 21 publications

Combining Human and Machine Transcriptions on the Zooniverse Platform

Combining Human and Machine Transcriptions on the Zooniverse Platform

Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition

Joint Recognition of Handwritten Text and Named Entities with a Neural End-to-End Model

Contact Info

Product

Resources

About