A Convolutional Recurrent Neural Network for the Handwritten Text Recognition of Historical Greek Manuscripts

Markou, K.; Tsochatzidis, Lazaros; Zagoris, Konstantinos; Papazoglou, Alexandros; Karagiannis, Xenofon; Symeonidis, Symeon; Pratikakis, Ioannis

doi:10.1007/978-3-030-68787-8_18

Cited by 15 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, a dropout layer, with probability equal to 0.2 (experimentally defined) is included in the last three blocks, to assist for better generalization ability and robustness of the features [23]. The combination of batch normalization and dropout achieved best performance during our experimentation, which coincides with the findings of several state-of-the-art works [2,4,14]. Finally, the average of each column of the feature maps of the last layer is calculated, to acquire a feature vector with 80 features for each time step along the width of the image, as shown in Figure 3.…”

Section: Octave-cnn Architecturesupporting

confidence: 74%

“…For the experimental evaluation of the proposed methodology we have considered three newly created collections of Greek historical handwritten documents, namely, χφ53, χφ79 and χφ114, along with the "EPARCHOS" dataset [4,24]. Additionally, to enable comparison with the state of the art, we have included in our experimentation two public datasets: IAM [5] and RIMES [6].…”

Section: Datasetsmentioning

confidence: 99%

“…The contribution of this work is two-fold: first, a new architecture is proposed that employs Octave convolutions in the encoding stage to achieve a combination of higher-and lower-scale features in each layer; second, three newly created collections are presented, providing the means for the evaluation of our methodology and future research as well. Furthermore, to enable comparison with state of the art, we extended experimentation to three already available datasets, namely EPARCHOS [4], IAM [5] and RIMES [6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

HTR for Greek Historical Handwritten Documents

et al. 2021

View full text Add to dashboard Cite

Offline handwritten text recognition (HTR) for historical documents aims for effective transcription by addressing challenges that originate from the low quality of manuscripts under study as well as from several particularities which are related to the historical period of writing. In this paper, the challenge in HTR is related to a focused goal of the transcription of Greek historical manuscripts that contain several particularities. To this end, in this paper, a convolutional recurrent neural network architecture is proposed that comprises octave convolution and recurrent units which use effective gated mechanisms. The proposed architecture has been evaluated on three newly created collections from Greek historical handwritten documents that will be made publicly available for research purposes as well as on standard datasets like IAM and RIMES. For evaluation we perform a concise study which shows that compared to state of the art architectures, the proposed one deals effectively with the challenging Greek historical manuscripts.

show abstract

Section: Octave-cnn Architecturesupporting

confidence: 74%

Section: Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

HTR for Greek Historical Handwritten Documents

et al. 2021

View full text Add to dashboard Cite

show abstract

“…This technique effectively reduces the total number of parameters while simultaneously enhancing the overall performance of the model. Authors of [15,60] presented Convolutional Recurrent Neural Network (CRNN) architecture; the latter utilized CRNN for handwriting recognition as an encoder for the input text lines while utilizing a Bidirectional Long Short-Term Memory (BLSTM) network followed by a fully CNN as a decoder to predict the sequence of characters. IAM and Reconnaissance et Indexation de données Manuscrites et de fac similÉS (RIMES) [61] with the newly created dataset (EPARCHOS) [60] that includes historical Greek manuscripts have been used in the evaluation process of the proposed architecture.…”

Section: Advancements In Handwritten Textmentioning

confidence: 99%

Advancements and Challenges in Handwritten Text Recognition: A Comprehensive Survey

AlKendi,

Gechter,

Heyberger

et al. 2024

J. Imaging

View full text Add to dashboard Cite

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: the Belfort civil registers of births. The digitization of these historical documents is challenging due to their unique characteristics such as writing style variations, overlapped characters and words, and marginal annotations. The objective of this survey paper is to summarize research on handwritten text documents and provide research directions toward effectively transcribing this French dataset. To achieve this goal, we presented a brief survey of several modern and historical HTR offline systems of different international languages, and the top state-of-the-art contributions reported of the French language specifically. The survey classifies the HTR systems based on techniques employed, datasets used, publication years, and the level of recognition. Furthermore, an analysis of the systems’ accuracies is presented, highlighting the best-performing approach. We have also showcased the performance of some HTR commercial systems. In addition, this paper presents a summarization of the HTR datasets that publicly available, especially those identified as benchmark datasets in the International Conference on Document Analysis and Recognition (ICDAR) and the International Conference on Frontiers in Handwriting Recognition (ICFHR) competitions. This paper, therefore, presents updated state-of-the-art research in HTR and highlights new directions in the research field.

show abstract

“…Moysset and Messina [35], and Bluche [6], which are based on the MDLSTM-RNN network proposed in [21]. Moreover, we include in the analysis approaches employing 1D-LSTMs, such as those presented by Ly et al [29], which also exploits self-attention in the convolutional block, and Markou et al [30], which features a fullyconnected layer after the recurrent block. We also consider the fully-convolutional architectured by Bluche and Messina [8], and Coquenet et al [17].…”

Section: Implementation Detailsmentioning

confidence: 99%

Boosting modern and historical handwritten text recognition with deformable convolutions

Cascianelli

2022

IJDAR

View full text Add to dashboard Cite

Handwritten Text Recognition (HTR) in free-layout pages is a challenging image understanding task that can provide a relevant boost to the digitization of handwritten documents and reuse of their content. The task becomes even more challenging when dealing with historical documents due to the variability of the writing style and degradation of the page quality. State-of-the-art HTR approaches typically couple recurrent structures for sequence modeling with Convolutional Neural Networks for visual feature extraction. Since convolutional kernels are defined on fixed grids and focus on all input pixels independently while moving over the input image, this strategy disregards the fact that handwritten characters can vary in shape, scale, and orientation even within the same document and that the ink pixels are more relevant than the background ones. To cope with these specific HTR difficulties, we propose to adopt deformable convolutions, which can deform depending on the input at hand and better adapt to the geometric variations of the text. We design two deformable architectures and conduct extensive experiments on both modern and historical datasets. Experimental results confirm the suitability of deformable convolutions for the HTR task.

show abstract

A Convolutional Recurrent Neural Network for the Handwritten Text Recognition of Historical Greek Manuscripts

Cited by 15 publications

References 14 publications

HTR for Greek Historical Handwritten Documents

HTR for Greek Historical Handwritten Documents

Advancements and Challenges in Handwritten Text Recognition: A Comprehensive Survey

Boosting modern and historical handwritten text recognition with deformable convolutions

Contact Info

Product

Resources

About