Authors:
El-Sayed M. El-Alfy
and
Mohammed R. Riaz
Affiliation:
King Fahd University of Petroleum and Minerals, Saudi Arabia
Keyword(s):
Image Quality Assessment, Adaptive Neuro-fuzzy Inference System, ANFIS, Differential Mean Opinion Score, Human Visual System, Subjective Assessment, Objective Assessment.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Artificial Intelligence and Decision Support Systems
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Data Manipulation
;
Enterprise Information Systems
;
Evolutionary Computing
;
Fuzzy Systems
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Hybrid Intelligent Systems
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Machine Learning
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Symbolic Systems
;
Theory and Methods
;
Vision and Perception
Abstract:
Due to the increasing use of digital images in electronic systems, it becomes important to evaluate the degradation in image quality during acquisition, processing, storage and transmission. In this paper, we investigate the ability of the adaptive neuro-fuzzy inference system (ANFIS) for quality assessment of digital images with respect to original (reference) images. Several metrics for objective quality assessment are calculated and used as inputs to an adaptive fuzzy inference system which in turn estimates a differential mean opinion score (DMOS) for different types of distortions. The predicted values are compared with the actual DMOS values using correlation and error measures. With 7-input ANFIS network, the results show that predicted DMOS values are highly correlated to the actual values using a publicly available and subjectively rated image database. For example, for distorted images due to JPEG 2000 compression, the attained results for correlation coefficient, Spearman’
s ranked correlation, and RMSE are 0.9944, 0.9902, and 3.32, respectively. These results show that combining the advantages of neural networks with fuzzy systems can be a promising approach for predicting the subjective quality of digital images.
(More)