Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Birhanu Hailu Belay"'
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-14 (2024)
Abstract Braille, the most popular tactile-based writing system, uses patterns of raised dots arranged in cells to inscribe characters for visually impaired persons. Amharic is Ethiopia’s official working language, spoken by more than 100 million p
Externí odkaz:
https://doaj.org/article/96b1f69816d44620a2aefebbb5ea4cd6
Publikováno v:
Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering ISBN: 9783031287244
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::059f3f26e4c9c43e903657bf6a14fb2b
https://doi.org/10.1007/978-3-031-28725-1_8
https://doi.org/10.1007/978-3-031-28725-1_8
Publikováno v:
ICPRAM
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c395b89d574406d2969c85e1207bdbee
https://doi.org/10.5220/0010284204350441
https://doi.org/10.5220/0010284204350441
Autor:
Marcus Liwicki, Tewodros Habtegebrial, Gebeyehu Belay, Birhanu Hailu Belay, Million Meshesha, Didier Stricker
Publikováno v:
Applied Sciences
Volume 10
Issue 3
Applied Sciences, Vol 10, Iss 3, p 1117 (2020)
Volume 10
Issue 3
Applied Sciences, Vol 10, Iss 3, p 1117 (2020)
In this paper, we introduce an end-to-end Amharic text-line image recognition approach based on recurrent neural networks. Amharic is an indigenous Ethiopic script which follows a unique syllabic writing system adopted from an ancient Geez script. Th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::68adb4f587ac969071103b8539cbf2d5
Publikováno v:
ICPRAM
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8a95fd5842d6ca2801860f20f3c8c00
https://doi.org/10.5220/0008940704400445
https://doi.org/10.5220/0008940704400445
Publikováno v:
ICIP
In this paper we propose a novel CNN based approach for Amharic character image recognition. The proposed method is designed by leveraging the structure of Amharic graphemes. Amharic characters could be decomposed in to a consonant and a vowel. As a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::14ce7a19698f382a02f356f73404aa6e
https://doi.org/10.1109/icip.2019.8804407
https://doi.org/10.1109/icip.2019.8804407
Publikováno v:
ICDAR
This paper introduces a dataset for an exotic, but very interesting script, Amharic. Amharic follows a unique syllabic writing system which uses 33 consonant characters with their 7 vowels variants of each. Some labialized characters derived by addin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6d0113c803323890f4acd0a11113ddc8
https://doi.org/10.1109/icdar.2019.00205
https://doi.org/10.1109/icdar.2019.00205
Publikováno v:
Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering ISBN: 9783030153564
In this paper, we propose a technique to recognize multi-font printed Amharic character images using deep convolutional neural network (DCNN) which is one of the recent techniques adopted from the deep learning community. Experiments were done on 86,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9617b97bb4db50286af6c713db169b75
https://doi.org/10.1007/978-3-030-15357-1_27
https://doi.org/10.1007/978-3-030-15357-1_27
Publikováno v:
2018 IEEE 18th International Conference on Communication Technology (ICCT).
In this paper we introduce Convolutional Neural Network (CNN) based method for Amharic character image recognition. We also introduce a dataset for training purposes. The proposed method has less pre-processing steps and out per- forms the state-of-t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a9e8b47f031280bea62b76d1bf49e291
https://doi.org/10.1109/icct.2018.8599888
https://doi.org/10.1109/icct.2018.8599888