A Computationally Efficient Pipeline Approach to Full Page Offline Handwritten Text Recognition

Chung, Jonathan; Delteil, Thomas

doi:10.1109/icdarw.2019.40078

Cited by 25 publications

(17 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From left to right, the columns respectively denote the architecture, the number of trainable parameters, the maximum GPU memory usage during training (data augmentation included), the minimum transcription level required, the minimum segmentation level required, the use of PreTraining (PT) on subimages, the use of specific Curriculum Learning (CL) and finally the Hyperparameter Adaptation (HA) requirements from one dataset to another. As one can see, models from [4,6,21] require transcription and segmentation labels at word or line levels to be trained, which implies more costly annotations. The models from [1,2,7] and the SPAN are pretrained on text line images to speed up convergence and to reach better results, thus also using line segmentation and transcription labels even if it is not strictly necessary.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition

Coquenet,

Chatelain,

Paquet

2021

Preprint

View full text Add to dashboard Cite

Unconstrained handwriting recognition is an essential task in document analysis. It is usually carried out in two steps. First, the document is segmented into text lines. Second, an Optical Character Recognition model is applied on these line images. We propose the Simple Predict & Align Network: an end-to-end recurrence-free Fully Convolutional Network performing OCR at paragraph level without any prior segmentation stage. The framework is as simple as the one used for the recognition of isolated lines and we achieve competitive results on three popular datasets: RIMES, IAM and READ 2016. The proposed model does not require any dataset adaptation, it can be trained from scratch, without segmentation labels, and it does not require line breaks in the transcription labels. Our code and trained model weights are available at https://github.com/FactoDeepLearning/SPAN.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Among these approaches, [4,3,6] are based on object-detection methods: a Region Proposal Network (RPN), followed by a non-maximal suppression process and Region Of Interest (ROI), generates line or word bounding boxes. An OCR is then applied on these bounding boxes.…”

Section: Segmentation-based Approachesmentioning

confidence: 99%

SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition

Coquenet,

Chatelain,

Paquet

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Object-detection approaches for word bounding box predictions have been studied in [25], [26]. They follow the standard object-detection paradigm based on a region proposal network and a non-maximum suppression algorithm [27].…”

Section: Document Layout Analysismentioning

confidence: 99%

DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition

Coquenet¹,

Chatelain²,

Paquet³

2022

Preprint

View full text Add to dashboard Cite

Unconstrained handwritten document recognition is a challenging computer vision task. It is traditionally handled by a two-step approach combining line segmentation followed by text line recognition. For the first time, we propose an end-to-end segmentation-free architecture for the task of handwritten document recognition: the Document Attention Network. In addition to the text recognition, the model is trained to label text parts using begin and end tags in an XML-like fashion. This model is made up of an FCN encoder for feature extraction and a stack of transformer decoder layers for a recurrent token-by-token prediction process. It takes whole text documents as input and sequentially outputs characters, as well as logical layout tokens. Contrary to the existing segmentation-based approaches, the model is trained without using any segmentation label. We achieve competitive results on the READ dataset at page level, as well as double-page level with a CER of 3.53% and 3.69%, respectively. We also provide results for the RIMES dataset at page level, reaching 4.54% of CER. We provide all source code and pre-trained model weights at https://github.com/FactoDeepLearning/DAN.

show abstract

“…Ref. [41] proposed an offline technique for recognizing full handwritten documents. This technique comprises a localized (text localization) handwritten text pipeline.…”

Section: Handwriting Recognition Based On Deep Learningmentioning

confidence: 99%

A Sequential Handwriting Recognition Model Based on a Dynamically Configurable CRNN

Al-Saffar

Awang

Al-Saiagh

et al. 2021

Sensors

View full text Add to dashboard Cite

Handwriting recognition refers to recognizing a handwritten input that includes character(s) or digit(s) based on an image. Because most applications of handwriting recognition in real life contain sequential text in various languages, there is a need to develop a dynamic handwriting recognition system. Inspired by the neuroevolutionary technique, this paper proposes a Dynamically Configurable Convolutional Recurrent Neural Network (DC-CRNN) for the handwriting recognition sequence modeling task. The proposed DC-CRNN is based on the Salp Swarm Optimization Algorithm (SSA), which generates the optimal structure and hyperparameters for Convolutional Recurrent Neural Networks (CRNNs). In addition, we investigate two types of encoding techniques used to translate the output of optimization to a CRNN recognizer. Finally, we proposed a novel hybridized SSA with Late Acceptance Hill-Climbing (LAHC) to improve the exploitation process. We conducted our experiments on two well-known datasets, IAM and IFN/ENIT, which include both the Arabic and English languages. The experimental results have shown that LAHC significantly improves the SSA search process. Therefore, the proposed DC-CRNN outperforms the handcrafted CRNN methods.

show abstract

A Computationally Efficient Pipeline Approach to Full Page Offline Handwritten Text Recognition

Cited by 25 publications

References 16 publications

SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition

SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition

DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition

A Sequential Handwriting Recognition Model Based on a Dynamically Configurable CRNN

Contact Info

Product

Resources

About