Co-occurrence Matrixes for the Quality Assessment of Coded Images

Authors:
Judith Redi;Paolo Gastaldo;Rodolfo Zunino;Ingrid Heynderickx
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;Philips Research Laboratories Prof. Holstlaan 4 - 5656 AA Eindhoven - NL and Delft Technical University, Delft, NL 2628 CD
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Year:
2008

Citing 4
Cited 2

On Combining Classifiers

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

Machine Learning
No-reference quality assessment of JPEG images by using CBP neural networks

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms

IEEE Transactions on Image Processing

Hybrid Neural Systems for Reduced-Reference Image Quality Assessment

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
Circular-ELM for the reduced-reference assessment of perceived image quality

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

Intrinsic nonlinearity complicates the modeling of perceived quality of digital images, especially when using feature-based objective methods. The research described in this paper indicates that models from Computational Intelligence can predict quality and cope with multi-dimensional data characterized by complex perceptual relationships. A reduced-reference scheme exploits Support Vector Machines (SVMs) to assess the degradation in perceived image quality induced by three different distortion types: JPEG compression, white noise, and Gaussian blur. First, an objective description of the images is obtained by exploiting the co-occurrence matrix and its features; then, the SVM supports the nonlinear mapping between the objective description and the quality evaluation. Experimental results confirm the validity of the approach.