Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Sameh Masmoudi"'
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
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:
Sedimentology. 69:2348-2366
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3bc054c7861d7382b039c3a87eddd6af
https://doi.org/10.1111/sed.12995
https://doi.org/10.1111/sed.12995
Publikováno v:
Quaternary International. 571:46-57
In our research work, the central focus is upon the multi-proxy analysis of sediment core recovered in sebkha Mhabeul (southeastern Tunisia), provides the first high-resolution, continuous sedimentary record in the region, extending back to mid Holoc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7469e87928c189c961a2426d79df1ae0
https://doi.org/10.1016/j.quaint.2020.09.006
https://doi.org/10.1016/j.quaint.2020.09.006
Publikováno v:
Comptes Rendus Geoscience. 351:487-497
In this study, we explored the evidence of late Holocene climate changes in southern Tunisia, examining extreme events of flood and sandstorm sedimentary succession records, in Sebkha Mhabeul. A sediment-derived climatic proxy was inferred from a 93.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::758729e76e950707041b2eaf4262b999
https://doi.org/10.1016/j.crte.2019.10.003
https://doi.org/10.1016/j.crte.2019.10.003
Publikováno v:
IET Computer Vision. 12:710-719
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://explore.openaire.eu/search/publication?articleId=doi_________::80d7a913d91c350837df80f09d08bc05
https://doi.org/10.1049/iet-cvi.2017.0468
https://doi.org/10.1049/iet-cvi.2017.0468
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Najoua Essoukri Ben Amara, Oussama Zayene, Nadia Hajjej, Jean Hennebert, Soumaya Ben Mansour, Sameh Masmoudi Touj, Rolf Ingold
Publikováno v:
ICPR
This paper describes the AcTiVComp: detection and recognition of Arabic Text in Video competition in conjunction with the 23rd International Conference on Pattern Recognition (ICPR). The main objective of this competition is to evaluate the performan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c3d55d358166683eda879affb2e3493d
https://doi.org/10.1109/icpr.2016.7899631
https://doi.org/10.1109/icpr.2016.7899631
Autor:
Jean Hennebert, Mathias Seuret, Oussama Zayene, Najoua Essoukri Ben Amara, Rolf Ingold, Sameh Masmoudi Touj
Publikováno v:
DAS
Text detection in videos is a challenging problem due to variety of text specificities, presence of complex background and anti-aliasing/compression artifacts. In this paper, we present an approach for horizontally aligned artificial text detection i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85196383fb19caae7bbe5e802b85be38
https://doi.org/10.1109/das.2016.80
https://doi.org/10.1109/das.2016.80
Publikováno v:
ATSIP
Benchmark datasets and their corresponding evaluation protocols are commonly used by the computer vision community, in a variety of application domains, to assess the performance of existing systems. Even though text detection and recognition in vide
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c982db3e261a34fafba24d1b6df200fb
https://doi.org/10.1109/atsip.2016.7523079
https://doi.org/10.1109/atsip.2016.7523079