Zobrazeno 1 - 10
of 179
pro vyhledávání: '"Rolf Ingold"'
Autor:
Vlad Atanasiu, Rolf Ingold
Publikováno v:
SoftwareX, Vol 14, Iss , Pp 100684- (2021)
This article introduces the generic Document Towers paradigm, visualization, and software for visualizing the structure of paginated documents, based on the metaphor of documents-as-architecture. The Document Towers visualizations resemble three-dime
Externí odkaz:
https://doaj.org/article/bb70002481d74ad0bb39ea3ffd3f44f9
Publikováno v:
IET Computer Vision, Vol 12, Iss 5, Pp 710-719 (2018)
This study presents a novel approach for Arabic video text recognition based on recurrent neural networks. In fact, embedded texts in videos represent a rich source of information for indexing and automatically annotating multimedia documents. Howeve
Externí odkaz:
https://doaj.org/article/9015363f8abf4b7f86c6536de31da16e
Autor:
Vinaychandran Pondenkandath, Michele Alberti, Nicole Eichenberger, Rolf Ingold, Marcus Liwicki
Publikováno v:
Journal of Imaging, Vol 6, Iss 7, p 71 (2020)
In this paper, we tackle the problem of categorizing and identifying cross-depicted historical motifs using recent deep learning techniques, with aim of developing a content-based image retrieval system. As cross-depiction, we understand the problem
Externí odkaz:
https://doaj.org/article/43b8f51c0db0446d9e546b2a337a5352
Publikováno v:
Journal of Imaging, Vol 4, Iss 2, p 32 (2018)
Recognizing texts in video is more complex than in other environments such as scanned documents. Video texts appear in various colors, unknown fonts and sizes, often affected by compression artifacts and low quality. In contrast to Latin texts, there
Externí odkaz:
https://doaj.org/article/67bc5eab544e419e83daa4bcb1967e97
Publikováno v:
International Journal on Document Analysis and Recognition (IJDAR).
Using neural networks for semantic labeling has become a dominant technique for layout analysis of historical document images. However, to train or fine-tune appropriate models, large labeled datasets are needed. This paper addresses the case when on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6313fa2165151c0d9dd6d2a31c69168d
https://doi.org/10.1007/s10032-023-00437-8
https://doi.org/10.1007/s10032-023-00437-8
Publikováno v:
International Journal on Document Analysis and Recognition (IJDAR). 24:197-218
One of the most important preliminary tasks in a transcription system of historical document images is text line segmentation. Nevertheless, this task remains complex due to the idiosyncrasies of ancient document images. In this article, we present a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::860573da4d9a991b1ae6d6e458156577
https://doi.org/10.1007/s10032-021-00377-1
https://doi.org/10.1007/s10032-021-00377-1
Publikováno v:
Series in Machine Perception and Artificial Intelligence. :i-xiii
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9021f770bde9ee0ce839a2e5ea93ecb0
https://doi.org/10.1142/9789811203244_fmatter
https://doi.org/10.1142/9789811203244_fmatter
Publikováno v:
Computational Collective Intelligence ISBN: 9783031160134
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb74eb548a2b6e8a07dc7d221877fa40
https://doi.org/10.1007/978-3-031-16014-1_10
https://doi.org/10.1007/978-3-031-16014-1_10
Autor:
Andreas Fischer, Paul Maergner, Marcus Liwicki, Kaspar Riesen, Vinaychandran Pondenkandath, Michele Alberti, Rolf Ingold
Publikováno v:
Pattern Recognition Letters. 125:527-533
Offline signature verification is a challenging pattern recognition task where a writer model is inferred using only a small number of genuine signatures. A combination of complementary writer mode ...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb26017b441aea98146b5c0d50ca0bcb
https://doi.org/10.1016/j.patrec.2019.06.024
https://doi.org/10.1016/j.patrec.2019.06.024
Publikováno v:
Pattern Recognition Letters. 121:46-51
This paper presents an improvement of handwriting binarization techniques on colored historical documents. We introduce a novel preprocessing step into the usual document image analysis (DIA) workflow. Before binarization, we propose a grayification
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0b76838cd13d6adad2dd41cfd79cd9b0
https://doi.org/10.1016/j.patrec.2018.05.021
https://doi.org/10.1016/j.patrec.2018.05.021