Hybrid Neural Systems for Reduced-Reference Image Quality Assessment

Authors:
Judith Redi;Paolo Gastaldo;Rodolfo Zunino
Affiliations:
Dept. of Biophysical and Electronic Engineering (DIBE), Genoa University, Genoa, Italy 16145;Dept. of Biophysical and Electronic Engineering (DIBE), Genoa University, Genoa, Italy 16145;Dept. of Biophysical and Electronic Engineering (DIBE), Genoa University, Genoa, Italy 16145
Venue:
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
Year:
2009

Citing 7
Cited 0

On Combining Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
Model Selection and Error Estimation

Machine Learning
Image Indexing Using Color Correlograms

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Handbook of Video Databases: Design and Applications

Handbook of Video Databases: Design and Applications
Co-occurrence Matrixes for the Quality Assessment of Coded Images

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms

IEEE Transactions on Image Processing
Circular backpropagation networks for classification

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Reduced-reference paradigms are suitable for supporting real-time modeling of perceived quality, since they make use of salient features both from the target image and its original, undistorted version, without requiring the full original information. In this paper a reduced-reference system is proposed, based on a feature-based description of images which encodes relevant information on the changes in luminance distribution brought about by distortions. Such a numerical description feeds a double-layer hybrid neural system: first, the kind of distortion affecting the image is identified by a classifier relying on Support Vector Machines (SVMs); in a second step, the actual quality level of the distorted image is assessed by a dedicated predictor based on Circular Back Propagation (CBP) neural networks, specifically trained to assess image quality for a given artifact. The general validity of the approach is supported by experimental validations based on subjective quality data.