M
Mario Ferraro
Researcher at University of Turin
Publications - 83
Citations - 1010
Mario Ferraro is an academic researcher from University of Turin. The author has contributed to research in topics: Anisotropic diffusion & Image segmentation. The author has an hindex of 16, co-authored 83 publications receiving 929 citations. Previous affiliations of Mario Ferraro include Polytechnic University of Turin & Smith-Kettlewell Institute.
Papers
More filters
Journal ArticleDOI
Modelling gaze shift as a constrained random walk
TL;DR: In this paper gaze shifts are considered as a realization of a stochastic process with non-local transition probabilities in a saliency field that represents a landscape upon which a constrained random walk is performed.
Journal ArticleDOI
On the truncated Pareto distribution with applications
Lorenzo Zaninetti,Mario Ferraro +1 more
TL;DR: In this paper, a comparison between the usual Pareto distribution and its truncated version is presented, and a possible physical mechanism that produces pareto tails for the distribution of the masses of stars is presented.
Journal ArticleDOI
On the representation of image structures via scale space entropy conditions
TL;DR: A novel way for representing and computing image features encapsulated within different regions of scale-space where, within a given range of spatial scales, the entropy gradient remains constant.
Journal ArticleDOI
Relationship between integral transform invariances and Lie group theory
Mario Ferraro,Terry Caelli +1 more
TL;DR: In this article, the authors explore the relationships between two classical means of mathematically representing visual patterns that are invariant under geometric transformations, and establish formal relationships between these representations, relating the kernel properties of the integral transforms to the associated Lie transformation groups.
Journal ArticleDOI
Visuomotor Characterization of Eye Movements in a Drawing Task
Ruben Coen-Cagli,Paolo Coraggio,Paolo Napoletano,Odelia Schwartz,Mario Ferraro,Giuseppe Boccignone +5 more
TL;DR: A computational model is proposed in the form of a novel kind of Dynamic Bayesian Network, and simulation results are compared with human eye-hand data, indicating that the motor task has little influence on which regions of the image are overall most likely to be fixated.