Aplicación del modelo Bag-of-Words al reconocimiento de imágenes

摘要

Object recognition on images has been more investigated in the recent years. Its principal application is the image retrieval and, therefore, image searchers would find the solution to the query based on whether the image has certain objects in its visual content or not instead of based on the adjacent textual annotations. Content based image retrieval would improve notoriously the quality of searchers. It is neccesary to have models that classify an image based on its low level features. In this project, it is used the ‘Bag of words’ model. Multimedia information retrieval entails many fields involved, and has many applications. The objective of this project is the indexing of images of a database based on content. It tries to eliminate the semantic gap finding the descriptors of each imagen, and therefore decide to which class or which semantic concept belongs.--------------------------------------------------------------------