Binarization Free Layout Analysis for Arabic Historical Documents Using Fully Convolutional Networks

Barakat, Berat Kurar; El-Sana, Jihad

doi:10.1109/asar.2018.8480333

Cited by 17 publications

(16 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach is tested on 8 pages (containing around 4000 patches) taken from different Arabic historical manuscripts. Results have been evaluated in comparison with Reference [ 55 ] and Reference [ 56 ]. In particular, Bukhari et al [ 55 ] uses an MLP-based approach, while Reference [ 56 ] presents an FCN for curved lines layout analysis.…”

Section: Addressed Problemsmentioning

confidence: 99%

“…Results have been evaluated in comparison with Reference [ 55 ] and Reference [ 56 ]. In particular, Bukhari et al [ 55 ] uses an MLP-based approach, while Reference [ 56 ] presents an FCN for curved lines layout analysis. Working on patch level instead of page level, the proposed method outperform these works in both the main text and side text segmentation, improving accuracy for particular pages layout analysis too, bringing F-measure for main text and side text analysis respectively from

and from

[ 12 ].…”

Section: Addressed Problemsmentioning

confidence: 99%

“…Most techniques in layout analysis identify regions with a uniform content, like paragraphs. As an example, in Reference [ 56 ] and Reference [ 75 ] the regions extracted correspond to the main text or to annotations in Arabic manuscripts. In Reference [ 76 ] text, annotations, titles, and illustrations are identified in historical documents.…”

Section: Neural Architectures and Their Applicationsmentioning

confidence: 99%

“…Individual Japanese characters are segmented with FCN in Reference [ 20 ]. Another task addressed with FCN is image binarization, that clearly requires an output representation matching the input size [ 46 , 56 ].…”

Section: Neural Architectures and Their Applicationsmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning for Historical Document Analysis and Recognition—A Survey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 The analysis and recognition of historical documents, as we survey in this work, is not an exception.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

Section: Addressed Problemsmentioning

confidence: 99%

and from

[ 12 ].…”

Section: Addressed Problemsmentioning

confidence: 99%

Section: Neural Architectures and Their Applicationsmentioning

confidence: 99%

Section: Neural Architectures and Their Applicationsmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning for Historical Document Analysis and Recognition—A Survey

Lombardi

Marinai

2020

J. Imaging

View full text Add to dashboard Cite

show abstract

“…Feature extraction and classifier algorithm design are very crucial for the performance of page segmentation methods. Although document image analysis started with more traditional machine learning classifiers, with the emergence of Convolutional Neural Networks (CNNs), they are commonly used in the literature [ 4 , 5 , 15 , 16 ]. Convolutional neural networks can successfully capture the spatial relations in an image by applying relevant filters, which makes their performance better when compared to the traditional classifiers [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

CNN-Based Page Segmentation and Object Classification for Counting Population in Ottoman Archival Documentation

Can

Kabadayı

2020

J. Imaging

View full text Add to dashboard Cite

Historical document analysis systems gain importance with the increasing efforts in the digitalization of archives. Page segmentation and layout analysis are crucial steps for such systems. Errors in these steps will affect the outcome of handwritten text recognition and Optical Character Recognition (OCR) methods, which increase the importance of the page segmentation and layout analysis. Degradation of documents, digitization errors, and varying layout styles are the issues that complicate the segmentation of historical documents. The properties of Arabic scripts such as connected letters, ligatures, diacritics, and different writing styles make it even more challenging to process Arabic script historical documents. In this study, we developed an automatic system for counting registered individuals and assigning them to populated places by using a CNN-based architecture. To evaluate the performance of our system, we created a labeled dataset of registers obtained from the first wave of population registers of the Ottoman Empire held between the 1840s and 1860s. We achieved promising results for classifying different types of objects and counting the individuals and assigning them to populated places.

show abstract