Pietro Vecchio

New object-oriented segmentation algorithm based on the CNN paradigm

This paper illustrates a new object-oriented segmentation algorithm based on the cellular neural network (CNN) paradigm. The approach, which exploits rigorous model of the image contours, presents two remarkable features: 1) it provides more accurate segmented objects than the ones obtained by other CNN-based techniques; 2) it makes use of CNN templates that take into account the hardware characteristics imposed by the CNNUM. Results carried out for benchmark video sequences highlight the capabilities of the proposed technique.

Neural networks for image processing: New edge detection algorithm

Neural networks can be very useful for image processing applications. This paper exploits the cellular neural network (CNN) paradigm to develop a new edge detection algorithm. The approach makes use of rigorous model of the image contours, and takes into account some electrical restrictions of existing CNN-based hardware implementations. Four benchmark video sequences are analyzed, that is, Car-phone, Miss America, Stefan, and Foreman. The analysis shows that the proposed algorithm yields accurate results, better than the ones achievable by other CNN-based methods. Finally, comparisons with standard edge detection techniques (i.e., LoG edge detector and Canny algorithm) further confirm the capability of the developed approach.

A new scheme to synchronize chaotic discrete-time systems via a scalar signal

Chaos synchronization is an important research topic in the field of nonlinear circuits and systems. This paper presents a new synchronization scheme, where two chaotic discrete-time systems synchronize for any invertible scaling matrix. Specifically, potentially different linear combinations of response system states synchronize with each drive system state. The proposed observer-based approach presents some useful features: i) it enables exact synchronization to be achieved in finite time; ii) it exploits a scalar synchronizing signal; and iii) it can be applied to a wide class of discrete-time chaotic (hyperchaotic) systems. An example is reported, which shows that exact synchronization is effectively achieved in finite time, for two arbitrary scaling matrix, via a scalar synchronizing signal only.

Chaos in the fractional Chua and Chen systems with lowest-order

This paper investigates bifurcation and chaos in the fractional-order Chua and Chen systems from the time-domain point of view. The objective is achieved using a decomposition method, which allows the solution of the fractional differential equations to be written in closed form. By taking advantage of the capabilities given by time-domain analysis, the paper illustrates three remarkable findings: (i) chaos exists in the fractional Chua system with very low order, that is, 0.03, which represents the lowest order reported in literature for any dynamical system studied so far; (ii) chaos exists in the fractional Chen system with order as low as 0.24, which represents the smallest value reported in literature for the Chen system; (iii) it is feasible to show the occurrence of pitchfork bifurcations and period-doubling routes to chaos in the fractional Chen system, by virtue of a systematic time-domain analysis of its dynamics.

Cellular neural networks: Implementation of a segmentation algorithm on a Bio-inspired hardware processor

The Cellular Neural/Nonlinear Network (CNN) paradigm has recently led to a Bio-inspired (Bi-i) Cellular Vision system, which represents a computing platform consisting of sensing, array sensing-processing and digital signal processing. This paper illustrates the implementation of a novel CNN-based segmentation algorithm onto the Bi-i system. The experimental results, carried out for a benchmark video sequence, show the feasibility of the approach, which provides a frame rate of about 26 frame/sec. Finally, comparisons with existing CNN-based methods highlight that the proposed implementation represents a good trade-off between real-time requirements and accuracy.

Implementation of a cellular neural network–based segmentation algorithm on the bio-inspired vision system

Based on the cellular neural network (CNN) paradigm, the bio-inspired (bi-i) cellular vision system is a computing platform consisting of state-of-the-art sensing, cellular sensing-processing and digital signal processing. This paper presents the implementation of a novel CNN-based segmentation algorithm onto the bi-i system. The experimental results, carried out for different benchmark video sequences, highlight the feasibility of the approach, which provides a frame rate of about 26 frame/sec. Comparisons with existing CNN-based methods show that, even though these methods are from two to six times faster than the proposed one, the conceived approach is more accurate and, consequently, represents a satisfying trade-off between real-time requirements and accuracy.

Segmentation algorithm via Cellular Neural/ Nonlinear Network: implementation on Bio- inspired hardware platform

The Bio-inspired (Bi-i) Cellular Vision System is a computing platform consisting of sensing, array sensing-processing, and digital signal processing. The platform is based on the Cellular Neural/Nonlinear Network (CNN) paradigm. This article presents the implementation of a novel CNN-based segmentation algorithm onto the Bi-i system. Each part of the algorithm, along with the corresponding implementation on the hardware platform, is carefully described through the article. The experimental results, carried out for Foreman and Car-phone video sequences, highlight the feasibility of the approach, which provides a frame rate of about 26 frames/s. Comparisons with existing CNN-based methods show that the conceived approach is more accurate, thus representing a good trade-off between real-time requirements and accuracy.

Object-oriented approach to video compression via Cellular Neural Networks

Video compression technologies have recently become an integral part of the way we create and consume visual information. This paper aims to show that the Cellular Neural Network (CNN) paradigm can be exploited for obtaining accurate video compression. In particular, the paper presents an architecture that combines CNN algorithms and H.264 codec. The compression capabilities of the devised coding system are analyzed using benchmark video sequences, and comparisons are carried out between the CNN-based approach and the H.264 codec working alone. The outcome of the analysis is that the CNN-based approach outperforms the H.264 codec working alone, making perceive the capabilities of the CNN paradigm.

CELLULAR NEURAL NETWORKS FOR VIDEO COMPRESSION: AN OBJECT-ORIENTED APPROACH

Video compression technologies have recently become an integral part of the way we create, communicate and consume visual information. The aim of this Letter is to show that the Cellular Neural Network (CNN) paradigm can be exploited for obtaining accurate video compression. In particular, the Letter presents an architecture that combines CNN algorithms and H.264 codec. The compression capabilities of the devised coding system are analyzed in detail using some benchmark video sequences, and comparisons are carried out between the CNN-based approach and the H.264 codec working alone. The outcome of the analysis is that the CNN-based coding approach outperforms the H.264 codec working alone, allowing to perceive the capabilities of the CNN paradigm.

CELLULAR NEURAL NETWORKS FOR EDGE DETECTION

This Letter presents an effective edge detection technique based on the cellular neural network paradigm. The approach exploits a rigorous model of the image contours and takes into account some electrical restrictions of existing hardware implementations. The method yields accurate results, better than the ones achievable by other cellular neural network-based techniques.