Zobrazeno 1 - 3
of 3
pro vyhledávání: '"68T07 (Primary), 68U10 (Secondary)"'
Autor:
Anjum, Tayaba, Khan, Nazar
Recognition of Arabic-like scripts such as Persian and Urdu is more challenging than Latin-based scripts. This is due to the presence of a two-dimensional structure, context-dependent character shapes, spaces and overlaps, and placement of diacritics
Externí odkaz:
http://arxiv.org/abs/2111.03952
Autor:
García, R. Gallardo, Rodríguez, S. Jarquín, Martínez, B. Beltrán, Gracidas, C. Hernández, Torres, R. Martínez
This work presents twelve fine-tuned deep learning architectures to solve the bacterial classification problem over the Digital Image of Bacterial Species Dataset. The base architectures were mainly published as mobile or efficient solutions to the I
Externí odkaz:
http://arxiv.org/abs/2106.06505
Autor:
Tayaba Anjum, Nazar Khan
Publikováno v:
Neural Processing Letters.
Recognition of Arabic-like scripts such as Persian and Urdu is more challenging than Latin-based scripts. This is due to the presence of a two-dimensional structure, context-dependent character shapes, spaces and overlaps, and placement of diacritics