Identifying the type of font (e.g., Roman, Blackletter) used in historical documents can help optical character recognition (OCR) systems produce more accurate text transcriptions. Towards this end, we present an activelearning strategy that can significantly reduce the number of labeled samples needed to train a font classifier. Our approach extracts image-based features that exploit geometric...

In this paper, we strive towards the development of efficient techniques in order to segment document pages resulting from the digitization of historical machine-printed sources. This kind of documents often suffer from low quality and local skew, several degradations due to the old printing matrix quality or ink diffusion, and exhibit complex and dense layout. To face these problems, we introd...

It is common that documents belonging to historical collections are poorly preserved and are prone to degradation processes. The aim of this work is to leverage state-of-the-art techniques in digital image binarization and text identification for digitized documents allowing further content exploitation in an efficient way. A novel methodology is proposed that leads to preservation of meaningfu...

Online communities bring together people with varied access to and understanding of the work at hand, who must collaborate through documents of various kinds. We develop a framework articulating the characteristics of documents supporting collaborators with asymmetric access to knowledge versus those with symmetric knowledge. Drawing on theories about document genre, boundary objects and proven...

information technology (it) is now widely in use in social .economical and cultural domains all over the world. iran has a forty years long experience in academic computer science education besides more than seven years of experience in it education. due to increasing importance of it application in today's human life and its improving and dynamic nature, it seems to be necessary to consid...

The presence of handwritten text and annotations combined with typewritten machine-printed in historical archival records make them visually complex, posing challenges for OCR systems accurately transcribing their content. This paper is an extension [1], reporting on improvements the separation from (including typewriters), by use FCN-based models trained datasets created different data synthes...

Abstract. The paper points the attention to some hidden parts of metric surveys, that usually are not enough documented in scientific papers but technical reposts. Reporting encountered challenges and discussing identified solutions methodologies overcome bottlenecks operative issues, highlights novelty presented experience from a viewpoint. overall approach has been reported taking care descri...