Visual Importance and Distortion Guided Deep Image Quality Assessment Framework

In this paper, we tackle the problem of no-reference image quality assessment (IQA). A learning-based IQA framework "VIDGIQA" is proposed, which extracts quality features from the input image and regresses the visual quality on these features. Since different distortions lead to different...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on multimedia Vol. 19; no. 11; pp. 2505 - 2520
Main Authors Guan, Jingwei, Yi, Shuai, Zeng, Xingyu, Cham, Wai-Kuen, Wang, Xiaogang
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 01.11.2017
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Artificial neural networks
Boats
Correlation coefficients
Datasets
Distortion
Distortion sensitive features
Estimation
Feature extraction
Image quality
image quality assessment (IQA)
Neural networks
Performance enhancement
Quality
Quality assessment
visual importance
visual quality maps
Visualization
White noise
Online AccessGet full text

Cover

More Information
Summary:In this paper, we tackle the problem of no-reference image quality assessment (IQA). A learning-based IQA framework "VIDGIQA" is proposed, which extracts quality features from the input image and regresses the visual quality on these features. Since different distortions lead to different visual perceptions in the human visual system, distortion information is adopted to guide the feature learning process together with the human quality scores. Besides, a regression method is proposed to model and estimate the visual importance weights of all local regions, which can effectively improve the performance. More importantly, all these operations are integrated into one deep neural network, so that they can be jointly optimized and well cooperate with each other. Experiments were conducted to demonstrate the power of the proposed method on several datasets, including the LIVE dataset [1], the TID 2013 dataset [2], the LIVE multiply distorted IQA dataset [3], CSIQ [4] , and the LIVE in the wild image quality database [5]. The proposed method achieves 0.969 and 0.973 on the LIVE dataset [1] in terms of the spearman rank-order correlation coefficient and the Pearson linear correlation coefficient, respectively, which outperforms the state-of-the-art methods.
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2017.2703148