Journal
APPLIED SCIENCES-BASEL
Volume 12, Issue 1, Pages -Publisher
MDPI
DOI: 10.3390/app12010101
Keywords
no-reference image quality assessment; convolutional neural network; decision fusion
Ask authors/readers for more resources
No-reference image quality assessment is a challenging task due to the varied distortions and contents of digital images. Recent research has focused on using convolutional neural networks and deep learning techniques for this assessment. This study introduces a novel NR-IQA architecture that utilizes decision fusion of multiple image quality scores from different types of networks, showing improved characterization of authentic image distortions.
No-reference image quality assessment (NR-IQA) has always been a difficult research problem because digital images may suffer very diverse types of distortions and their contents are extremely various. Moreover, IQA is also a very hot topic in the research community since the number and role of digital images in everyday life is continuously growing. Recently, a huge amount of effort has been devoted to exploiting convolutional neural networks and other deep learning techniques for no-reference image quality assessment. Since deep learning relies on a massive amount of labeled data, utilizing pretrained networks has become very popular in the literature. In this study, we introduce a novel, deep learning-based NR-IQA architecture that relies on the decision fusion of multiple image quality scores coming from different types of convolutional neural networks. The main idea behind this scheme is that a diverse set of different types of networks is able to better characterize authentic image distortions than a single network. The experimental results show that our method can effectively estimate perceptual image quality on four large IQA benchmark databases containing either authentic or artificial distortions. These results are also confirmed in significance and cross database tests.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available