DSpace JSPUI
DSpace almacena y facilita el acceso abierto a todo tipo de contenido digital incluyendo texto, imágenes, vídeos y colecciones de datos.
Leer más
Por favor, use este identificador para citar o enlazar este ítem:
https://repositorio.uti.edu.ec//handle/123456789/3400| Título : | Classify ecuadorian receipes with convolutional neural networks |
| Autor : | Soria, Luis Jiménez-Cadena, Gabriela Martínez, Carlos Castillo-Salazar, David |
| Fecha de publicación : | 2020 |
| Editorial : | Advances in Intelligent Systems and Computing. Volume 1137 AISC, Pages 223 - 229. International Conference on Information Technology and Systems, ICITS 2020. Bogota. 5 February 2020 through 7 February 2020 |
| Resumen : | This work is a proposal to resolve the problem of identification plates of food through photographs. It involves using a large set of pictures which are processed by convolutional neural networks and parallel processing TensorFlow. The results show a 90% greater accuracy in training and between 63% and 80% in the test. The reason is that Ecuadorian dishes are very similar in the images of some recipes. © Springer Nature Switzerland AG 2020. |
| URI : | https://link.springer.com/chapter/10.1007/978-3-030-40690-5_22 http://repositorio.uti.edu.ec//handle/123456789/3400 |
| Aparece en las colecciones: | Artículos Científicos Indexados |
Ficheros en este ítem:
No hay ficheros asociados a este ítem.
Este ítem está sujeto a una licencia Creative Commons Licencia Creative Commons
