Assistant Professor, University of Rome - La Sapienza
Danilo Avola is an Assistant Professor in Computer Science and Artificial Intelligence at Sapienza University in Rome. He received the M.Sc. degree in Computer Science from Sapienza University, Rome in 2002 and the Ph.D. degree in Molecular and Ultrastructural Imaging from University of L’Aquila in 2014. Since 2015 he is postdoc researcher at the Department of Mathematics, Computer Science and Physics (DMIF), University of Udine and member of the AVIRES Lab at the same University. Previously, he was research engineer at the Department of Computer Science, Sapienza University, at the National Institute of Geophysics and Volcanology, Rome, and at the Multimodal & Multimedia Lab of the National Research Council, Rome. His research interests include Human Computer Interaction, Computer Vision, Signal Processing, Machine Learning, Image and Video Processing, Multimodal Systems, and Pattern Recognition. He serves on the Steering Committee of selected International Conferences and is an Editorial Board member of different International Journals. Danilo Avola is author or co-author of more than 60 papers in International Journals, refereed International Conferences and International Book Chapters. Since 2011, Danilo Avola is member of IAPR and member of IEEE.
Road to AI: Computer Vision Tasks from Haralick Operators to Neural Networks
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