last modified November 30, 2017 - 14:43 CET

Circuits for parallel nonlinear information processing

The development of algorithms and circuits able to find in real time approximate solutions to problems involving huge of data has been extensively investigated in the last few years, from both a circuit theory and an implementation point of view. The main applications are in the field of image processing, for instance in systems for autonomous navigation, video surveillance, support to sightless people or to drivers, or data fusion.

In order to avoid the bottleneck intrinsic to serial computation, these circuits and algorithms usually have an intrinsically parallel structure.

We developed algorithms and circuits (called Cellular Nonlinear Networks or CNNs) for the minimization of functionals depending on large sets of variables. The main applications concern the real-time solution of problems stated in terms of partial differential equations and the segmentation and edge detection of real images or image sequences.

In many cases, the algorithms were implemented on DSP boards.

Example: DSP implementation of an algorithm for vessel segmentation in red-free images of the human retina.

Vessel segmentation

Involved People:

Major Publications:

  • Anzalone, A.; Bizzarri, F.; Storace, M. & Parodi, M.
    A Cellular Nonlinear Network for image fusion based on data regularization
    International Journal of Circuit Theory and Applications, 2006, 34, 533-546
  • Storace, M.; Bizzarri, F. & Parodi, M.
    Cellular non-linear networks for minimization of functionals. Part 1: Theoretical aspects
    International Journal of Circuit Theory and Applications, 2001, 29, 151-167
  • Bizzarri, F.; Storace, M. & Parodi, M.
    Cellular non-linear networks for minimization of functionals. Part 2: Examples
    International Journal of Circuit Theory and Applications, 2001, 29, 169-184
  • Anzalone, A.; Bizzarri, F.; Camera, P.; Petrillo, L. & Storace, M.
    DSP implementation of a low-complexity algorithm for real-time automated vessel detection in images of the fundus of the human retina
    Proceedings of the 2007 IEEE International Symposium on Circuits and Systems (ISCAS'07), 2007, 97-100

Funding:

  • Italian Ministry of University and Research Grant - 2001-2003 (PRIN2001). Research network with the Universities of Turin (Polytechnic), Genoa, Bari, and Rome "Tor Vergata". Title:"Development and testing of a real-time system, based on neural circuits and algorithms, for information extraction through stereoscopic vision in 3D enviroments"
  • Italian Ministry of University and Research Grant - 2004-2006 (PRIN2004). Research network with the Universities of Rome "Tor Vergata", Genoa, Bari, and Turin (Polytechnic). Title:"CNN application to real time processing of ophthalmic images as medical diagnosis support"

This site conforms to the following standards: