Local descriptors for matching and 3D object recognition
work in collaboration with: Nicoletta Noceti, Francesca Odone and Alessandro Verri
During my phd I focused on view-based object recognition in images using local descriptors, features tracking and matching techniques.
I concentrated on local approaches for the study and the analysis of the visual information coming from an image. In fact recent research has demonstrated local descriptors lead to a more compact and robust representation of the image even when there are major changes in the object appearance. Thus in my work I concentrated on the use of local
features and interest points to determine a representation of the
image content by means of its most informative elements.
Points of interest in 3D shapes: from detection and description to feature selection.
work in collaboration with: Curzio Basso, Francesca Odone and Enrico Puppo
Recent developments in techniques for modelling, digitizing and visualizing
3D shapes has led to an explosion in the number of available 3D models on the Internet
and in domain-speciﬁc databases. This has led to the development of 3D shape retrieval
systems that, given a query object, retrieve similar 3D objects. Recently, local approaches
have been exploited in the context of image understanding, since they provide compact and
efficient descriptors for images. Similarly, there has been an increasing attention for detecting and describing points of interest in 3D shapes. Our aim is to develop a method for shape retrieval by exploiting the peculiarity of 3D shapes and by combining techniques coming from 2D image description with feature selection methods.
Thanks to Elise Arnaud for the inspiration of this webpage