Alessio Fagioli
Ph.D. fellow, University of Rome - La Sapienza
Bio:
Alessio Fagioli received the B.Sc and the M.Sc. (cum laude) in Computer Science from Sapienza University of Rome, Rome, Italy, in 2016 and 2019, respectively. He is currently a Ph.D. fellow and a member of the VisionLab of the Department of Computer Science, Sapienza University of Rome. His current research interests include Medical Image Analysis, Machine Learning, Deep Learning, Affect Recognition, Event Recognition, Object Tracking, and Human Computer Interaction.
Workshop:
An Application in Anomaly Detection
with Danilo Avola, Daniele Pannone
Abstract:
AI is becoming a predominant aspect of several Computer Science areas. However, most approaches can be considered as “black box” solutions where a given Neural Network (NN) model produces outputs without providing good insights into what happens inside the model itself. To address this aspect, a good starting point includes generating augmented inputs representing diverse aspects of the observed scene and extrapolating image characteristics, e.g., entropy feature map, to better understand what is being observed. While these procedures can be generated through renowned Computer Vision algorithms and offer the possibility to examine various facets of an image, they can also provide further insights into a NN architecture. In this context, the lecture follows the road to AI by introducing a powerful class of Computer Vision operators, i.e, Haralick’s textu.
