Advancements and challenges in handwritten text recognition: A comprehensive survey

W AlKendi, F Gechter, L Heyberger, C Guyeux - Journal of Imaging, 2024 - mdpi.com
Handwritten Text Recognition (HTR) is essential for digitizing historical documents in
different kinds of archives. In this study, we introduce a hybrid form archive written in French …

Dan: a segmentation-free document attention network for handwritten document recognition

D Coquenet, C Chatelain… - IEEE transactions on …, 2023 - ieeexplore.ieee.org
Unconstrained handwritten text recognition is a challenging computer vision task. It is
traditionally handled by a two-step approach, combining line segmentation followed by text …

Gated convolutional recurrent neural networks for multilingual handwriting recognition

T Bluche, R Messina - 2017 14th IAPR international …, 2017 - ieeexplore.ieee.org
In this paper, we propose a new neural network architecture for state-of-the-art handwriting
recognition, alternative to multi-dimensional long short-term memory (MD-LSTM) recurrent …

Segmentation-free handwritten Chinese text recognition with LSTM-RNN

R Messina, J Louradour - 2015 13th International conference …, 2015 - ieeexplore.ieee.org
We present initial results on the use of Multi-Dimensional Long-Short Term Memory
Recurrent Neural Networks (MDLSTM-RNN) in recognizing lines of handwritten Chinese …

Scalable training of deep learning machines by incremental block training with intra-block parallel optimization and blockwise model-update filtering

K Chen, Q Huo - … conference on acoustics, speech and signal …, 2016 - ieeexplore.ieee.org
We present a new approach to scalable training of deep learning machines by incremental
block training with intra-block parallel optimization to leverage data parallelism and …

Attention-based fully gated CNN-BGRU for Russian handwritten text

A Abdallah, M Hamada, D Nurseitov - Journal of Imaging, 2020 - mdpi.com
This article considers the task of handwritten text recognition using attention-based encoder–
decoder networks trained in the Kazakh and Russian languages. We have developed a …

Deep neural networks for large vocabulary handwritten text recognition

T Bluche - 2015 - theses.hal.science
The automatic transcription of text in handwritten documents has many applications, from
automatic document processing, to indexing and document understanding. One of the most …

ICFHR2014 competition on handwritten text recognition on transcriptorium datasets (HTRtS)

JA Sánchez, V Romero, AH Toselli… - 2014 14th International …, 2014 - ieeexplore.ieee.org
A contest on Handwritten Text Recognition organised in the context of the ICFHR 2014
conference is described. Two tracks with increased freedom on the use of training data were …

Candidate fusion: Integrating language modelling into a sequence-to-sequence handwritten word recognition architecture

L Kang, P Riba, M Villegas, A Fornés, M Rusiñol - Pattern Recognition, 2021 - Elsevier
Sequence-to-sequence models have recently become very popular for tackling handwritten
word recognition problems. However, how to effectively integrate an external language …

Paragraph text segmentation into lines with recurrent neural networks

B Moysset, C Kermorvant, C Wolf… - … on document analysis …, 2015 - ieeexplore.ieee.org
The detection of text lines, as a first processing step, is critical in all text recognition systems.
State-of-the-art methods to locate lines of text are based on handcrafted heuristics fine-tuned …