Text Line Segmentation in Historical Document Images Using an Adaptive U-Net Architecture

Mechi, Olfa; Mehri, Maroua; Ingold, Rolf; Amara, Najoua Essoukri Ben

doi:10.1109/icdar.2019.00066

Cited by 42 publications

(24 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Grüning et al 33 combined a CNN-based U-shape network with a bottom-up clustering method to identify text lines in historical documents with complex layouts such as curved arbitrarily oriented text lines. Mechi et al 34 applied a CNN-based U-shape network to segment text lines and tested their solution on a challenging cBAD dataset. 68 The fifth area is OCR.…”

Section: Image Classification Using Cnnmentioning

confidence: 99%

Investigating coupling preprocessing with shallow and deep convolutional neural networks in document image classification

2021

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) are effective for image classification, and deeper CNNs are being used to improve classification performance. Indeed, as needs increase for searchability of vast printed document image collections, powerful CNNs have been used in place of conventional image processing. However, better performances of deep CNNs come at the expense of computational complexity. Are the additional training efforts required by deeper CNNs worth the improvement in performance? Or could a shallow CNN coupled with conventional image processing (e.g., binarization and consolidation) outperform deeper CNNbased solutions? We investigate performance gaps among shallow (LeNet-5, -7, and -9), deep (ResNet-18), and very deep (ResNet-152, MobileNetV2, and EfficientNet) CNNs for noisy printed document images, e.g., historical newspapers and document images in the RVL-CDIP repository. Our investigation considers two different classification tasks: (1) identifying poems in historical newspapers and (2) classifying 16 document types in document images. Empirical results show that a shallow CNN coupled with computationally inexpensive preprocessing can have a robust response with significantly reduced training samples; deep CNNs coupled with preprocessing can outperform very deep CNNs effectively and efficiently; and aggressive preprocessing is not helpful as it could remove potentially useful information in document images.

show abstract

Section: Image Classification Using Cnnmentioning

confidence: 99%

Investigating coupling preprocessing with shallow and deep convolutional neural networks in document image classification

2021

View full text Add to dashboard Cite

show abstract

“…The literature has shown that text line segmentation methods can essentially be classified in two categories (Mechi et al [2019]). First, well documented by Likforman-Sulem et al [2007], there are image processing methods, such as connected-components, projections and smearing analysis.…”

Section: Algorithmmentioning

confidence: 99%

Combining Morphological and Histogram based Text Line Segmentation in the OCR Context

Schneider¹

2021

Journal of Data Mining &Amp; Digital Humanities

View full text Add to dashboard Cite

Text line segmentation is one of the pre-stages of modern optical character recognition systems. The algorithmic approach proposed by this paper has been designed for this exact purpose. Its main characteristic is the combination of two different techniques, morphological image operations and horizontal histogram projections. The method was developed to be applied on a historic data collection that commonly features quality issues, such as degraded paper, blurred text, or presence of noise. For that reason, the segmenter in question could be of particular interest for cultural institutions, that want access to robust line bounding boxes for a given historic document. Because of the promising segmentation results that are joined by low computational cost, the algorithm was incorporated into the OCR pipeline of the National Library of Luxembourg, in the context of the initiative of reprocessing their historic newspaper collection. The general contribution of this paper is to outline the approach and to evaluate the gains in terms of accuracy and speed, comparing it to the segmentation algorithm bundled with the used open source OCR software.

show abstract

“…U-Net is used for some tasks in a fashion similar to FCN. Text line segmentation is addressed by Reference [ 77 ] while the related task of baseline detection is discussed in Reference [ 57 ]. The detection and recognition of Kuzushiji Japanese characters is proposed in Reference [ 13 ].…”

Section: Neural Architectures and Their Applicationsmentioning

confidence: 99%

“…In the area of historical document recognition several approaches used standard frameworks like Pytorch [ 107 ] (e.g., in Reference [ 67 ]) Tensorflow [ 108 ] and Keras [ 109 ] (e.g., References [ 22 , 77 ]). In other cases DIAR-specific tools have been recently proposed in order to provide to researchers easily accessible and efficient tools for handling the different steps required in the development of effective applications.…”

Section: Experimental Environmentmentioning

confidence: 99%

Deep Learning for Historical Document Analysis and Recognition—A Survey

Lombardi

Marinai

2020

J. Imaging

View full text Add to dashboard Cite

Nowadays, deep learning methods are employed in a broad range of research fields. The analysis and recognition of historical documents, as we survey in this work, is not an exception. Our study analyzes the papers published in the last few years on this topic from different perspectives: we first provide a pragmatic definition of historical documents from the point of view of the research in the area, then we look at the various sub-tasks addressed in this research. Guided by these tasks, we go through the different input-output relations that are expected from the used deep learning approaches and therefore we accordingly describe the most used models. We also discuss research datasets published in the field and their applications. This analysis shows that the latest research is a leap forward since it is not the simple use of recently proposed algorithms to previous problems, but novel tasks and novel applications of state of the art methods are now considered. Rather than just providing a conclusive picture of the current research in the topic we lastly suggest some potential future trends that can represent a stimulus for innovative research directions.

show abstract

Text Line Segmentation in Historical Document Images Using an Adaptive U-Net Architecture

Cited by 42 publications

References 18 publications

Investigating coupling preprocessing with shallow and deep convolutional neural networks in document image classification

Investigating coupling preprocessing with shallow and deep convolutional neural networks in document image classification

Combining Morphological and Histogram based Text Line Segmentation in the OCR Context

Deep Learning for Historical Document Analysis and Recognition—A Survey

Contact Info

Product

Resources

About