Social media are revolutionizing various areas of our society, including the cultural heritage one. The same goes for artificial intelligent strategies and machine learning algorithms, which are exploited in many contexts, and could play an interesting role in promoting and sharing cultural heritage and touristic activities and points of interests in urban environments. An interesting application of these techniques in the cultural and touristic domain could be represented by the automatic recognition and classification of monuments and points of interest. In this work, we present a study on monuments recognition, starting from pictures taken by users by means of their mobile devices, while visiting an urban environment. In particular, we employed images collected by the citizens and tourists with the aim of contributing to valorize monuments or places in a specific case study, that is the city of Cesena (Italy). In this paper, we compared several architectures of convolutional neural networks, that are able to discriminate among a set of outdoor monuments with an accuracy of over 90%.
Social Sensing for Monuments Recognition using Convolutional Neural Networks: A Case Study / Delnevo G.; Kazazi A.; Amadori E.; Mirri S.. - ELETTRONICO. - 2022-June:(2022), pp. 1-6. (Intervento presentato al convegno 27th IEEE Symposium on Computers and Communications, ISCC 2022 tenutosi a Rhodes (Greece) nel 30 giugno 2022 - 3 luglio 2022) [10.1109/ISCC55528.2022.9912961].
Social Sensing for Monuments Recognition using Convolutional Neural Networks: A Case Study
Delnevo G.;Mirri S.
2022
Abstract
Social media are revolutionizing various areas of our society, including the cultural heritage one. The same goes for artificial intelligent strategies and machine learning algorithms, which are exploited in many contexts, and could play an interesting role in promoting and sharing cultural heritage and touristic activities and points of interests in urban environments. An interesting application of these techniques in the cultural and touristic domain could be represented by the automatic recognition and classification of monuments and points of interest. In this work, we present a study on monuments recognition, starting from pictures taken by users by means of their mobile devices, while visiting an urban environment. In particular, we employed images collected by the citizens and tourists with the aim of contributing to valorize monuments or places in a specific case study, that is the city of Cesena (Italy). In this paper, we compared several architectures of convolutional neural networks, that are able to discriminate among a set of outdoor monuments with an accuracy of over 90%.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
