Blind Source Separation Techniques for Detecting Hidden Texts and Textures in Document Images

Tonazzini, Anna; Salerno, Emanuele; Mochi, Matteo; Bedini, Luigi

doi:10.1007/978-3-540-30126-4_30

Cited by 18 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, in the first place, digital reproductions will have to fulfill the following requirements: coherence with the original dimensions of the fragment, high spacial resolution, readability in all parts of the fragment, accurate color reproduction, absence of light reflexes, perfect image overapping and alignment. In the second place, after having carefully acquired the fragments through the multispectral images, we will intervene with their analysis by applying specific image analysis algorythms (s. , so to separate overlapping texts, or to extract various types of hidden information (s. Tonazzini, Salerno, Mochi, & Bedini, 2004;. All these data will allow us a holistic approach to fragments.…”

Section: A New Design For Textus Invisibilismentioning

confidence: 99%

Handwritten culture through digital native eyes: student participation in the digital fragmentology project Textus invisibilis

Molinari

2021

Open Information Science

View full text Add to dashboard Cite

The present paper addresses the issue of how interest-driven learning can enhance an attitude of student-generated inquiry in the learning process so to promote student participation in university research projects. The research question is how wonder as an epistemic emotion may sustain students’ interest-generated questioning, and how the latter may influence the design of a university research project. As a case-study, the paper describes a laboratory on palaeography which took place in Spring 2019 at an Italian State Archive within a University bachelor program in the context of a digital fragmentology project. To design the laboratory and establish qualitative analysis methods for its data, an interdisciplinary educational approach was designed that combines interest-driven learning, emotion theory, value theory, hermeneutics, and User Experience, on the background of Ernst Cassirer’s view of a human being as an animal symbolicum. In the laboratory, the students’ questions and hypotheses arising from their interaction with historical scripts and Medieval handwriting culture are helping redesign some aspects of the research project Textus invisibilis both on the level of the research design and of the team composition, as well as pointing to a novel relevance of state archives and historical libraries in higher education.

show abstract

Section: A New Design For Textus Invisibilismentioning

confidence: 99%

Handwritten culture through digital native eyes: student participation in the digital fragmentology project Textus invisibilis

Molinari

2021

Open Information Science

View full text Add to dashboard Cite

show abstract

“…The ACE (Automatic Colour Enhancement) algorithm proposed in [9] and the PCA algorithm proposed in [21] have been adopted.…”

Section: Colour Enhancement Of Underwater Imagesmentioning

confidence: 99%

Performance evaluation of underwater image pre-processing algorithms for the improvement of multi-view 3D reconstruction

et al. 2019

View full text Add to dashboard Cite

<p class="Abstract">3D models of submerged structures and underwater archaeological finds are widely used in various and different applications, such as monitoring, analysis, dissemination, and inspection. Underwater environments are characterised by poor visibility conditions and the presence of marine flora and fauna. Consequently, the adoption of passive optical techniques for the 3D reconstruction of underwater scenarios is a highly challenging task.</p>This article presents a performance analysis conducted on a multi-view technique that is commonly used in air in order to highlight its limits in the underwater environment and then provide guidelines for the accurate modelling of a submerged site in poor visibility conditions. A performance analysis has been performed by comparing different image enhancement algorithms, and the results have been adopted to reconstruct an area of 40 m<sup>2</sup> at a depth of about 5 m at the underwater archaeological site of Baiae (Italy).

show abstract

“…In this work, for the sake of simplicity, we consider any image containing readable human-generated artifacts as a document image. In many cases, a grayscale representation of a document image is preferred to be fed to the processing work flows, which use methods from various paradigms, such as statistical methods [30,4] and variational methods [6,8]. This is mainly because of the limitations of these document processing techniques or in order to reduce the computational cost.…”

Section: Introductionmentioning

confidence: 99%

A maximal-information color to gray conversion method for document images: Toward an optimal grayscale representation for document image binarization

Moghaddam,

Chen,

Hedjam

et al. 2013

Preprint

View full text Add to dashboard Cite

A novel method to convert color/multi-spectral images to gray-level images is introduced to increase the performance of document binarization methods. The method uses the distribution of the pixel data of the input document image in a color space to find a transformation, called the dual transform, which balances the amount of information on all color channels. Furthermore, in order to reduce the intensity variations on the gray output, a color reduction preprocessing step is applied. Then, a channel is selected as the gray value representation of the document image based on the homogeneity criterion on the text regions. In this way, the proposed method can provide a luminance-independent contrast enhancement. The performance of the method is evaluated against various images from two databases, the ICDAR'03 Robust Reading, the KAIST and the DIBCO'09 datasets, subjectively and objec-

show abstract

Blind Source Separation Techniques for Detecting Hidden Texts and Textures in Document Images

Cited by 18 publications

References 5 publications

Handwritten culture through digital native eyes: student participation in the digital fragmentology project Textus invisibilis

Handwritten culture through digital native eyes: student participation in the digital fragmentology project Textus invisibilis

Performance evaluation of underwater image pre-processing algorithms for the improvement of multi-view 3D reconstruction

A maximal-information color to gray conversion method for document images: Toward an optimal grayscale representation for document image binarization

Contact Info

Product

Resources

About