Image quality assessment by using neural networks

P. Carrai; I.E.J. Heynderickx; P. Gastaldo; R. Zunino

doi:10.1109/ISCAS.2002.1010688

Image quality assessment by using neural networks

P. Carrai
, I.E.J. Heynderickx
, P. Gastaldo
, R. Zunino

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

23 Citations (Scopus)

Abstract

This paper presents a model using neural networks for image quality assessment. The proposed system aims at evaluating the difference in the perceived quality when a static image is processed with an enhancement algorithm. A CBP neural network is designed to mimic the human perception. Objective features are worked out on a block-by-block basis from both the original and the enhanced image; they feed the neural network, which yields as output the quality rating. Experimental results confirm the approach validity, as the system provides a satisfactory approximation of subjective opinions.

Original language	English
Title of host publication	2002 IEEE International Symposium on Circuits and Systems, 26-29 May 2002, Phoenix, AZ
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	V/253-V/256
Volume	5
ISBN (Print)	0-7803-7448-7
DOIs	https://doi.org/10.1109/ISCAS.2002.1010688
Publication status	Published - 2002

Access to Document

10.1109/ISCAS.2002.1010688

Cite this

@inproceedings{7e91eaa098f5461c90df961dd7d78653,

title = "Image quality assessment by using neural networks",

abstract = "This paper presents a model using neural networks for image quality assessment. The proposed system aims at evaluating the difference in the perceived quality when a static image is processed with an enhancement algorithm. A CBP neural network is designed to mimic the human perception. Objective features are worked out on a block-by-block basis from both the original and the enhanced image; they feed the neural network, which yields as output the quality rating. Experimental results confirm the approach validity, as the system provides a satisfactory approximation of subjective opinions.",

author = "P. Carrai and I.E.J. Heynderickx and P. Gastaldo and R. Zunino",

year = "2002",

doi = "10.1109/ISCAS.2002.1010688",

language = "English",

isbn = "0-7803-7448-7",

volume = "5",

pages = "V/253--V/256",

booktitle = "2002 IEEE International Symposium on Circuits and Systems, 26-29 May 2002, Phoenix, AZ",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

Image quality assessment by using neural networks. / Carrai, P.; Heynderickx, I.E.J.; Gastaldo, P. et al.
2002 IEEE International Symposium on Circuits and Systems, 26-29 May 2002, Phoenix, AZ. Vol. 5 Piscataway: Institute of Electrical and Electronics Engineers, 2002. p. V/253-V/256.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Image quality assessment by using neural networks

AU - Carrai, P.

AU - Heynderickx, I.E.J.

AU - Gastaldo, P.

AU - Zunino, R.

PY - 2002

Y1 - 2002

N2 - This paper presents a model using neural networks for image quality assessment. The proposed system aims at evaluating the difference in the perceived quality when a static image is processed with an enhancement algorithm. A CBP neural network is designed to mimic the human perception. Objective features are worked out on a block-by-block basis from both the original and the enhanced image; they feed the neural network, which yields as output the quality rating. Experimental results confirm the approach validity, as the system provides a satisfactory approximation of subjective opinions.

AB - This paper presents a model using neural networks for image quality assessment. The proposed system aims at evaluating the difference in the perceived quality when a static image is processed with an enhancement algorithm. A CBP neural network is designed to mimic the human perception. Objective features are worked out on a block-by-block basis from both the original and the enhanced image; they feed the neural network, which yields as output the quality rating. Experimental results confirm the approach validity, as the system provides a satisfactory approximation of subjective opinions.

U2 - 10.1109/ISCAS.2002.1010688

DO - 10.1109/ISCAS.2002.1010688

M3 - Conference contribution

SN - 0-7803-7448-7

VL - 5

SP - V/253-V/256

BT - 2002 IEEE International Symposium on Circuits and Systems, 26-29 May 2002, Phoenix, AZ

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Image quality assessment by using neural networks

Abstract

Access to Document

Fingerprint

Cite this