A Comparative Study of Global and Deep Features for the Analysis of User-Generated Natural Disaster Related Images

The paper addresses the problem of adverse events (natural disasters) recognition in user-generated images from social media, addressing the problem from two complementary perspectives. On one side, we aim to provide a comprehensive comparative analysis of different feature extraction and classification algorithms, relying on two different families of feature extraction algorithms, namely (i) Global features and (ii) Deep features. On the other hand, we demonstrate that the fusion of different feature extraction and classification strategies can outperform the single methods by jointly exploiting the capabilities of individual feature descriptors. The evaluation of the methods are carried out on two datasets, including a benchmark and a self-collected dataset.