ICFHR2018 Competition on Automated Text Recognition on a READ Dataset

Straub, Tobias; Leifert, Gundram; Labahn, Roger; Hodel, Tobias; Mühlberger, Günter

doi:10.1109/icfhr-2018.2018.00089

Cited by 20 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We achieve the best improvement from 0 to 16 specific training pages with nearly 78% decrease of the CER. Our method also outperforms the other ones submitted to the competition on every metric (reported in [8]). While, the method proposed by [18] seems relevant when it is trained without many specific examples, our approach reaches state of the art performance on writer adaptation using 16 specific training pages.…”

Section: Resultsmentioning

confidence: 68%

“…Recently, as part of the ICFHR 2018 READ competition [8], most of the participants proposed an optical model composed of a Convolutional Neural Network (CNN) and Bidirectional Long Short Term Memory (BLSTM) layers as in [15] and [16]. One of them was using Multi-dimensional LSTM (MDLSTM) [17], which has provided good performance when trained on a generic large data set, but has shown difficulty in carrying the writer adaptation process with few samples.…”

Section: A Optical Model Adaptationmentioning

confidence: 99%

“…If no language is selected, the generic multi-LM is selected as LM g . In contrast to recent works that use a fixed value of λ [8], here λ is selected using cross validation on the specific training corpus. This allows to get a suitable value of λ using writer language examples.…”

Section: Writer Adaptationmentioning

confidence: 99%

“…We evaluate our approach on the READ data set that was proposed as part of the ICFHR 2018 Automated Handwritten Text Recognition competition [8].…”

Section: Experimentationmentioning

confidence: 99%

“…Our approach is evaluated on the 2018 READ competition [8] data sets, dedicated to writer adaptation analysis. We show that our method reaches competitive performance on the adaptation task and outperforms the systems which have been submitted to the competition.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Improving Text Recognition using Optical and Language Model Writer Adaptation

Soullard

Swaileh

Tranouez

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

State-of-the-art methods for handwriting text recognition are based on deep learning approaches and language modeling that require large data sets during training. In practice, there are some applications where the system processes mono-writer documents, and would thus benefit from being trained on examples from that writer. However, this is not common to have numerous examples coming from just one writer. In this paper, we propose an approach to adapt both the optical model and the language model to a particular writer, from a generic system trained on large data sets with a variety of examples. We show the benefits of the optical and language model writer adaptation. Our approach reaches competitive results on the READ 2018 data set, which is dedicated to model adaptation to particular writers.

show abstract

Section: Resultsmentioning

confidence: 68%

Section: A Optical Model Adaptationmentioning

confidence: 99%

Section: Writer Adaptationmentioning

confidence: 99%

“…We evaluate our approach on the READ data set that was proposed as part of the ICFHR 2018 Automated Handwritten Text Recognition competition [8].…”

Section: Experimentationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improving Text Recognition using Optical and Language Model Writer Adaptation

Soullard

Swaileh

Tranouez

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

show abstract

Text-Conditioned Character Segmentation for CTC-Based Text Recognition

Tanaka

Osada

Furuhata

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Generating Synthetic Handwritten Historical Documents with OCR Constrained GANs

Vögtlin

Drazyk

Pondenkandath

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We present a framework to generate synthetic historical documents with precise ground truth using nothing more than a collection of unlabeled historical images. Obtaining large labeled datasets is often the limiting factor to effectively use supervised deep learning methods for Document Image Analysis (DIA). Prior approaches towards synthetic data generation either require expertise or result in poor accuracy in the synthetic documents. To achieve high precision transformations without requiring expertise, we tackle the problem in two steps. First, we create template documents with user-specified content and structure. Second, we transfer the style of a collection of unlabeled historical images to these template documents while preserving their text and layout. We evaluate the use of our synthetic historical documents in a pre-training setting and find that we outperform the baselines (randomly initialized and pre-trained). Additionally, with visual examples, we demonstrate a high-quality synthesis that makes it possible to generate large labeled historical document datasets with precise ground truth.

show abstract

ICFHR2018 Competition on Automated Text Recognition on a READ Dataset

Cited by 20 publications

References 9 publications

Improving Text Recognition using Optical and Language Model Writer Adaptation

Improving Text Recognition using Optical and Language Model Writer Adaptation

Text-Conditioned Character Segmentation for CTC-Based Text Recognition

Generating Synthetic Handwritten Historical Documents with OCR Constrained GANs

Contact Info

Product

Resources

About