
handle: 10553/42278
El presente proyecto tiene como objetivo, determinar cómo se pueden utilizar las redes neuronales a la hora de clasificar correctamente entre distintos tipos de prendas. Para este enfoque, se ha utilizado una base de datos con miles de imágenes, donde cada imagen está etiquetada con su categoría correspondiente. Se emplea una metodología basada en prototipos. Mediante la utilización de un algoritmo del estado del arte para este tipo de problemas, el cual ya ha sido entrenado previamente, se han ido realizando pequeñas variaciones para obtener los resultados óptimos. Posteriormente, se han aplicado diferentes algoritmos de Aprendizaje Automático para acrecentar los resultados y se han evaluado los resultados, proponiendo posibles mejoras para próximos proyectos.
The current project has as objective, to determine how to use neural networks to classify different types of clothes. For this approach, we have used a database containing thousands of images, where each image contains a label with the correspondent category. We apply a methodology based on prototypes. With the use of a state of the art algorithm for this kind of problems, we have been doing small alterations to obtain the optimum results. Subsequently, we have applied different Machine Learning algorithms to enhance the performance. We also evaluate the results and propose possible improvements for future works.
120317 Informática, Aprendizaje profundo, Redes neuronales, Aprendizaje automático
120317 Informática, Aprendizaje profundo, Redes neuronales, Aprendizaje automático
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
