Loading [MathJax]/extensions/MathMenu.js
Objective quality assessment of MPEG-2 video streams by using CBP neural networks | IEEE Journals & Magazine | IEEE Xplore
Access provided by:

MIT Libraries

Sign Out
Access provided by:

MIT Libraries

Sign Out
ADVANCED SEARCH
Journals & Magazines >IEEE Transactions on Neural N... >Volume: 13 Issue: 4

Objective quality assessment of MPEG-2 video streams by using CBP neural networks

PDF
P. Gastaldo; S. Rovetta; R. Zunino
All Authors

Abstract:

The increasing use of compression standards in broadcasting digital TV has raised the need for established criteria to measure perceived quality. Novel methods must take ...Show More

Metadata

Abstract:

The increasing use of compression standards in broadcasting digital TV has raised the need for established criteria to measure perceived quality. Novel methods must take into account the specific artifacts introduced by digital compression techniques. This paper presents a methodology using circular backpropagation (CBP) neural networks for the objective quality assessment of motion picture expert group (MPEG) video streams. Objective features are continuously extracted from compressed video streams on a frame-by-frame basis; they feed the CBP network estimating the corresponding perceived quality. The resulting adaptive modeling of subjective perception supports a real-time system for monitoring displayed video quality. The overall system mimics perception but does not require an analytical model of the underlying physical phenomenon. The ability to process compressed video streams represents a crucial advantage over existing approaches, as avoiding the decoding process greatly enhances the system's real-time performance. Experimental evidence confirmed the approach validity. The system was tested on real test videos; they included different contents ranging from fiction to sport. The neural model provided a satisfactory, continuous-time approximation for actual scoring curves, which was validated statistically in terms of confidence analysis. As expected, videos with slow-varying contents such as fiction featured the best performances.
Published in: IEEE Transactions on Neural Networks ( Volume: 13, Issue: 4, July 2002)
Page(s): 939 - 947
Date of Publication: 31 July 2002

ISSN Information:

PubMed ID: 18244489
DOI: 10.1109/TNN.2002.1021894
Department of Biophysical and Electronic Engineering-DIBE, University of Genoa, Genoa, Italy
Paolo Gastaldo received the Laurea degree in electronic engineering from Genoa University, Genoa, Italy, in 1998. He is currently with the Electronic Systems and Networking Group of the Department of Biophysical and Electronic Engineering, University of Genoa, and is pursuing the Ph. D. degree in space science and engineering.
His research interests include neural-network implementation and applications, advanced multimedi...Show More
Paolo Gastaldo received the Laurea degree in electronic engineering from Genoa University, Genoa, Italy, in 1998. He is currently with the Electronic Systems and Networking Group of the Department of Biophysical and Electronic Engineering, University of Genoa, and is pursuing the Ph. D. degree in space science and engineering.
His research interests include neural-network implementation and applications, advanced multimedi...View more
Author image of S. Rovetta
Department of Computer and Information Sciences-DISI, University of Genoa, Genoa, Italy
Stefano Rovetta received the Laurea degree in electronic engineering in 1993 and the Ph. D. degree in models, methods and tools for electronic and electromagnetic systems in 1997, both from the University of Genoa, Genoa, Italy.
He held a position as a Postdoctoral Researcher with the Electronic Systems and Networking Group of the Department of Biophysical and Electronic Engineering, University of Genoa. He has been an Inv...Show More
Stefano Rovetta received the Laurea degree in electronic engineering in 1993 and the Ph. D. degree in models, methods and tools for electronic and electromagnetic systems in 1997, both from the University of Genoa, Genoa, Italy.
He held a position as a Postdoctoral Researcher with the Electronic Systems and Networking Group of the Department of Biophysical and Electronic Engineering, University of Genoa. He has been an Inv...View more
Author image of R. Zunino
Department of Biophysical and Electronic Engineering-DIBE, University of Genoa, Genoa, Italy
Rodolfo Zunino (S'90–M'90) received the Laurea degree in electronic engineering from Genoa University, Genoa, Italy, in 1985.
From 1986 to 1995, he was a Research Consultant with the Department of Biophysical and Electronic Engineering of Genoa University. He is currently with the same department as an Associate Professor in Industrial Electronics. His main scientific interests include electronic systems for neural network...Show More
Rodolfo Zunino (S'90–M'90) received the Laurea degree in electronic engineering from Genoa University, Genoa, Italy, in 1985.
From 1986 to 1995, he was a Research Consultant with the Department of Biophysical and Electronic Engineering of Genoa University. He is currently with the same department as an Associate Professor in Industrial Electronics. His main scientific interests include electronic systems for neural network...View more
Contents

I. Introduction

The recent increasing success of digital TV has stimulated the research for objective automated methods to assess the user-end perception of broadcasting. The underlying technical problem is to estimate the effects of the visual artifacts brought about by digital encoding. In this sense, traditional techniques for analog data processing often prove ineffective in measuring the perceived quality of a digital compressed video.

Department of Biophysical and Electronic Engineering-DIBE, University of Genoa, Genoa, Italy
Paolo Gastaldo received the Laurea degree in electronic engineering from Genoa University, Genoa, Italy, in 1998. He is currently with the Electronic Systems and Networking Group of the Department of Biophysical and Electronic Engineering, University of Genoa, and is pursuing the Ph. D. degree in space science and engineering.
His research interests include neural-network implementation and applications, advanced multimedia signal processing, and digital television.
Paolo Gastaldo received the Laurea degree in electronic engineering from Genoa University, Genoa, Italy, in 1998. He is currently with the Electronic Systems and Networking Group of the Department of Biophysical and Electronic Engineering, University of Genoa, and is pursuing the Ph. D. degree in space science and engineering.
His research interests include neural-network implementation and applications, advanced multimedia signal processing, and digital television.View more
Author image of S. Rovetta
Department of Computer and Information Sciences-DISI, University of Genoa, Genoa, Italy
Stefano Rovetta received the Laurea degree in electronic engineering in 1993 and the Ph. D. degree in models, methods and tools for electronic and electromagnetic systems in 1997, both from the University of Genoa, Genoa, Italy.
He held a position as a Postdoctoral Researcher with the Electronic Systems and Networking Group of the Department of Biophysical and Electronic Engineering, University of Genoa. He has been an Invited Professor of Operating Systems at the University of Siena. He is currently Assistant Professor at the Department of Computer and Information Sciences of Genoa University. His research interests include electronic circuits and systems, and neural-network theory, implementation, and applications.
Stefano Rovetta received the Laurea degree in electronic engineering in 1993 and the Ph. D. degree in models, methods and tools for electronic and electromagnetic systems in 1997, both from the University of Genoa, Genoa, Italy.
He held a position as a Postdoctoral Researcher with the Electronic Systems and Networking Group of the Department of Biophysical and Electronic Engineering, University of Genoa. He has been an Invited Professor of Operating Systems at the University of Siena. He is currently Assistant Professor at the Department of Computer and Information Sciences of Genoa University. His research interests include electronic circuits and systems, and neural-network theory, implementation, and applications.View more
Author image of R. Zunino
Department of Biophysical and Electronic Engineering-DIBE, University of Genoa, Genoa, Italy
Rodolfo Zunino (S'90–M'90) received the Laurea degree in electronic engineering from Genoa University, Genoa, Italy, in 1985.
From 1986 to 1995, he was a Research Consultant with the Department of Biophysical and Electronic Engineering of Genoa University. He is currently with the same department as an Associate Professor in Industrial Electronics. His main scientific interests include electronic systems for neural networks, efficient models for data representation and learning, advanced techniques for multimedia data processing, and distributed-control methodologies.
Prof. Zunino is a Member of SMPTE.
Rodolfo Zunino (S'90–M'90) received the Laurea degree in electronic engineering from Genoa University, Genoa, Italy, in 1985.
From 1986 to 1995, he was a Research Consultant with the Department of Biophysical and Electronic Engineering of Genoa University. He is currently with the same department as an Associate Professor in Industrial Electronics. His main scientific interests include electronic systems for neural networks, efficient models for data representation and learning, advanced techniques for multimedia data processing, and distributed-control methodologies.
Prof. Zunino is a Member of SMPTE.View more
Contact IEEE to Subscribe
More Like This
Objective assessment of MPEG-video quality: a neural-network approach

IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222)

Published: 2001

A real-time system based on a neural network model to control hexacopter trajectories

2014 International Symposium on Power Electronics, Electrical Drives, Automation and Motion

Published: 2014

Show More

References

References is not available for this document.

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.