Blind image quality assessment based on natural statistics of double-opponency
College
Gokongwei College of Engineering
Department/Unit
Electronics And Communications Engg
Document Type
Article
Source Title
Journal of Advanced Computational Intelligence and Intelligent Informatics
Volume
22
Issue
5
First Page
725
Last Page
730
Publication Date
9-1-2018
Abstract
One of the challenges in image quality assessment (IQA) is to determine the quality score without the presence of the reference image. In this paper, the authors proposed a no-reference image quality assessment method based on the natural statistics of double opponent (DO) cells. It utilizes the statistical modeling of the three opponency channels using the generalized Gaussian distribution (GGD) and asymmetric generalized Gaussian distribution (AGGD). The parameters of GGD and AGGD are then applied to feedforward neural network to predict the image quality. Result shows that for any opposing channels, its natural statistics parameters when applied to feedforward neural network can achieve satisfactory prediction of image quality. © 2018 Fuji Technology Press.All Rights Reserved.
html
Digitial Object Identifier (DOI)
10.20965/jaciii.2018.p0725
Recommended Citation
Sybingco, E., & Dadios, E. P. (2018). Blind image quality assessment based on natural statistics of double-opponency. Journal of Advanced Computational Intelligence and Intelligent Informatics, 22 (5), 725-730. https://doi.org/10.20965/jaciii.2018.p0725
Disciplines
Electrical and Computer Engineering | Electrical and Electronics
Keywords
Gaussian distribution; Imaging systems—Image quality
Upload File
wf_no