Carregant...
Tipus de document
Treball de fi de grauData de publicació
Llicència de publicació
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/48211
PhotoMeet Barcelona: Sistema de reconocimiento de edificios
Títol de la revista
Autors
Director/Tutor
ISSN de la revista
Títol del volum
Recurs relacionat
Resum
Today we take photos for granted which are our memories of holidays and parties, of people and places. The explosion of the cameras and devices that we have today allow us to take pictures easily and the wide range of social networks to share them makes that we have our lives documented with images.With this big number of images that we generate and at the same time are shared in the social networks, is interesting to propose the development of a system that allow us to categorize and sort properly all of this pictures.
Specifically, in this project we present a system of building recognition and classification. The final result is an “intelligent“ system able to extract the information of the images and recognize some of the most emblematic buildings from Barcelona.
This work is part of PhotoMeet Barcelona, a project where a social network based in share pictures is developed and a system such as this one presented could be very useful to improve some of the functionalities classifying and geolocating automatically the images uploaded for the users.
During the process of development of this project, Computer Vision and Artificial Intelligence methods are used, which will allow us to extract the images characteristics and the creation of an intelligent learning system able to recognize buildings.
Descripció
Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2013, Director: Laura Igual Muñoz i Santi Seguí Mesquida
Matèries (anglès)
Citació
Citació
RUIZ FERNÁNDEZ, Guillermo. PhotoMeet Barcelona: Sistema de reconocimiento de edificios. [consulta: 27 de gener de 2026]. [Disponible a: https://hdl.handle.net/2445/48211]