• Curriculum Vitae
  • Teaching
  • Appointments
  • Research

Stefano Cagnoni graduated in Electronic Engineering at the University of Florence in 1988 where he has been a Ph.D. student and a post-doc until 1997, working in the Bioengineering Lab of the Department of Electronic Engineering.
He received the Ph.D. degree in Bioengineering in 1993.
In 1994, he was a visiting scientist at the Whitaker College Biomedical Imaging and Computation Laboratory at the Massachusetts Institute of Technology.
He held a post-doc position at the University of Florence in 1995 and 1996.
Since 1997 he has been with the Department of Computer Engineering of the University of Parma, where he has been Associate Professor since 2004.

His main research interests, as concerns basic research, are in the field of soft computing, with particular regard to evolutionary computation and neural nets, and in the field of computer vision. As concerns applied research, the main topics of his research are the application of the above-mentioned techniques to problems of computer vision, pattern recognition, and robotics.

As concerns neural nets, his research activity has concerned the development of modular neural net systems for applications to computer vision and for the sub-symbolic processing of non-numerical data. He has proposed a variant of the Learning Vector Quantization (LVQ) algorithm, to optimize the size of the classifiers produced using such a technique. The modified LVQ algorithm has been successfully applied to car license-plate recognition.

In the field of evolutionary computation, besides actively participating in EvoNET, the EU-funded network of excellence in evolutionary computation (from 1997 to 2005, year in which the project was officially closed), he has developed applications of genetic algorithms to the design of filters for the analysis of one-dimensional signals and for contour-based image segmentation. Genetic Programming (GP) has been used to create false-color images to synthesize the information contained in sequences of grey-level ones, using an interactive evolutionary method, of which the user is an active component. GP has also been used to define the optimum strategy of play for a robot goalkeeper, which successfully participated in RoboCup99. Using an original approach based on cellular programming, a license plate character recognition system has been also developed.
Efficient GP algorithms have also been studied, which are particularly good at obtaining, in relatively short time, extremely fast programs for binary image processing. Using such techniques, low-resolution character classifiers have been developed which, despite keeping almost the same accuracy as a reference neural classifier, show a ten-fold increase in performance with respect to the reference.
He has also studied the coevolution of heterogeneous systems, aimed, as a long-term goal, at defining coevolutionary algorithms based on the definition of ecosystems in which different populations evolve cooperatively and self-organize so that each of them optimizes a specific part of the problem at hand.
More recently, his research has been focused on the theory and applications of Particle Swarm Optimization (PSO). In particular, as regards applications, he has studied computer vision algorithms in which PSO is used for detecting and tracking objects/people, as well as defining a highly-efficient massively parallel implementation of PSO on graphics hardware.

As regards computer vision, research has been dedicated mostly to low-level techniques and, in particular, to contour-based and region-based image segmentation, aimed, in a first phase, at extracting three-dimensional information from sequences of tomographic images, and, after that, at locating the free space in applications of autonomous navigation to robotics.
Massively-parallel computer architectures based on cellular automata have been used to implement algorithms for perspective-effect removal and computation of the optical flow field.
More recently, prototypes of hybrid sensors have been designed, made up of a traditional camera associated to an omnidirectional one. Such a system is able to provide a 360-degrees field of view at low resolution, along with a more limited field of view, but at a much higher resolution. These two situations correspond, roughly, to what happens in the human eye, in which the so-called peripheral vision (wide angle of view and low-resolution) coexists with the so-called foveal vision (high resolution in a neighborhood of the focus of attention). The contemporary presence of the two sensors makes it possible for stereo image processing to be performed.
Such sensors have been applied to solve autonomous navigation problems in robotics and to surveillance tasks.

Professor Cagnoni's research activity has been carried out within projects financed by MIUR, CNR, ASI, and ENEA, as well as part of contracts, managed directly or within regional technology transfer projects, between the Dipartimento di Ingegneria dell'Informazione and firms which operate in the province of Parma or in Emilia Romagna. Among the most recent ones, he has coordinated a project aimed at developing a card, based on a hardware neural net architecture, which can be used to develop embedded computer vision systems, and has participated in the design of a self-adaptive lighting system for industrial quality control applications.
He has co-managed a project funded by Italian Railway Network Society (RFI) aimed at developing an inspection system for train pantographs based on computer vision.
He has been recently awarded a grant from the EU, within the "Marie Curie" Actions, for a four-year research education project ("MIBISOC") in Medical Imaging using Bio-Inspired and Soft Computing.

Other activities

He has organized workshops, continuing education courses, edited special issues of international journals and frequently acts as a reviewer for international conferences and journals.

He has been Editor-in-chief of the "Journal of Artificial Evolution and Applications" (2007-2009)

He has been a member of the Managing Board and secretary (2006-2007) of the Italian Association for Artificial Intelligence (AI*IA).

Since 1999, he has been chairman of EvoIASP, a yearly European event dedicated to the applications of evolutionary computation to image analysis and signal processing. In 2001 and 2002 he was General Chair of EvoWorkshops (now "EvoApplications Conference"), the European joint conference of which EvoIASP is a component.
He was Chairman and organizer of GSICE, the Italian Workshop on Evolutionary Computation, in 2005 and 2006, and organizer of SECEVITA, summer school on Evolutionary Computation and Artificial Life, in 2007.
Chairman of the workshop on Evolutionary Computation which was held at ECAI, the European Conference on Artificial Intelligence, in 2006.
Since 2005, he has co-chaired MedGEC, a workshop on medical applications of evolutionary computation held concurrently with GECCO (Genetic and Evolutionary Computation Conference).

Co-editor of the special issues of:
"EURASIP Journal of Applied Signal Processing" (July 2003)
"Pattern Recognition Letters" (2006)
"Evolutionary Computation" (2008)
dedicated to "Genetic and Evolutionary Computation for Image Analysis and Signal Processing.

He has organized the "EvoNET Summer School on Evolutionary Computation" in Parma in 2003.

He has been Editor-in-chief of the "Journal of Artificial Evolution and Applications" (2007-2009)

He is reviewer for many international journals and member of the scientific committees of several conferences, among which: Evostar, Genetic and Evolutionary Computation Conference (GECCO), IEEE Conference on Evolutionary Computation (CEC), International Conference on Evolvable Systems (ICES), Frontiers of Evolutionary Algorithms (FEA), Parallel Problem Solving from Nature (PPSN), Italian Workshop on Evolutionary Computation and Artificial Life (WIVACE), Nature and Bio-inspired Computing (NABIC), Soft Computing for Pattern Recognition (SOCPAR), and Symposium of Applied Computing (SAC).

He has been a member of the Advisory Board of Perada, the UE Coordination Action on Pervasive Adaptation.

He has been awarded the "Evostar 2009 Award", in recognition of the most outstanding contribution to Evolutionary Computation.

As of January 2016, his H-Index is 19 (Google, 15 since 2011) / 12 (Scopus)

Anno accademico di erogazione: 2020/2021

Anno accademico di erogazione: 2019/2020

Anno accademico di erogazione: 2018/2019

Anno accademico di erogazione: 2017/2018

Anno accademico di erogazione: 2016/2017

Anno accademico di erogazione: 2015/2016

Anno accademico di erogazione: 2014/2015

Anno accademico di erogazione: 2013/2014

Teacher tutor




Phone number
Fax number