Adversarial Autoencoders for Denoising Digitized Historical Documents: The Use Case of Incunabula

Neji, Hala; Nogueras-Iso, Javier; Lacasta, Javier; Halima, Mohamed Ben; Alimi, Adel M.

doi:10.1109/icdarw.2019.50112

Cited by 12 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evolving from its original meaning, incunabulum came to mean “place of birth” or “beginning”. In the world of books, the word incunabula refers to books that were printed using movable metal type up to the year 1500 [ 22 ].…”

Section: Historical Documentsmentioning

confidence: 99%

“…Historical document denoising is one of the most challenging steps in the field of image processing and computer vision. Neji et al [ 22 ] propose a novel end to end adversarial autoencoder (AAE) which generates clean images and shows adversarial autoencoder’s power when used in historical document denoising. The proposed AAE uses a generative adversarial networks (GAN) so as to suit the aggregated posterior of the hidden code vector of the autoencoder with an arbitrary prior.…”

Section: Addressed Problemsmentioning

confidence: 99%

“…Some methods take as input an image patch that is translated over the input image and that can produce as output a modified patch for image denoising [ 22 ], document restoration [ 42 ] or letter restoration [ 44 ]. The output information computed from each patch can be also used for document dating [ 15 ] or writer identification [ 28 ].…”

Section: Neural Architectures and Their Applicationsmentioning

confidence: 99%

“…A convolutional autoencoder to learn features in document images used by an Support Vector Machines (SVM) to perform page segmentation is proposed in Reference [ 90 ]. Another typical use of autoencoders is image denoising—in this context Incunabula are processed by Reference [ 22 ].…”

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“…In the area of historical document recognition several approaches used standard frameworks like Pytorch [ 107 ] (e.g., in Reference [ 67 ]) Tensorflow [ 108 ] and Keras [ 109 ] (e.g., References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%

See 4 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: Historical Documentsmentioning

confidence: 99%

Section: Addressed Problemsmentioning

confidence: 99%

Section: Neural Architectures and Their Applicationsmentioning

confidence: 99%

Section: Neural Architectures and Their Applicationsmentioning

confidence: 99%

Section: Experimental Environmentmentioning

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

show abstract

Paired Image to Image Translation for Strikethrough Removal from Handwritten Words

Heil

Vats²,

Hast

2022

Document Analysis Systems

View full text Add to dashboard Cite

Personalizing image enhancement for critical visual tasks: improved legibility of papyri using color processing and visual illusions

Atanasiu

Marthot-Santaniello

2021

IJDAR

View full text Add to dashboard Cite

This article develops theoretical, algorithmic, perceptual, and interaction aspects of script legibility enhancement in the visible light spectrum for the purpose of scholarly editing of papyri texts. Novel legibility enhancement algorithms based on color processing and visual illusions are compared to classic methods in a user experience experiment. (1) The proposed methods outperformed the comparison methods. (2) Users exhibited a broad behavioral spectrum, under the influence of factors such as personality and social conditioning, tasks and application domains, expertise level and image quality, and affordances of software, hardware, and interfaces. No single enhancement method satisfied all factor configurations. Therefore, it is suggested to offer users a broad choice of methods to facilitate personalization, contextualization, and complementarity. (3) A distinction is made between casual and critical vision on the basis of signal ambiguity and error consequences. The criteria of a paradigm for enhancing images for critical applications comprise: interpreting images skeptically; approaching enhancement as a system problem; considering all image structures as potential information; and making uncertainty and alternative interpretations explicit, both visually and numerically.

show abstract

Adversarial Autoencoders for Denoising Digitized Historical Documents: The Use Case of Incunabula

Cited by 12 publications

References 7 publications

Deep Learning for Historical Document Analysis and Recognition—A Survey

Deep Learning for Historical Document Analysis and Recognition—A Survey

Paired Image to Image Translation for Strikethrough Removal from Handwritten Words

Personalizing image enhancement for critical visual tasks: improved legibility of papyri using color processing and visual illusions

Contact Info

Product

Resources

About