Image Quality Predictor with Highly Efficient Fully Convolutional Neural Network

A highly efficient deep fully convolutional neural network (DFCN) for image quality assessment (IQA) is designed in this paper. The DFCN consists of two branches, one scoring local patches and the other estimating the weights of local patches to enhance quality prediction. Then, the DFCN outputs qua...

Full description

Saved in:
Bibliographic Details
Main Authors: Cao Yu-Dong, Liao Xin-Lin, Liu Hai-Yan
Format: Article
Language:English
Published: Wiley 2022-01-01
Series:Advances in Multimedia
Online Access:http://dx.doi.org/10.1155/2022/1686298
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849308296916238336
author Cao Yu-Dong
Liao Xin-Lin
Liu Hai-Yan
author_facet Cao Yu-Dong
Liao Xin-Lin
Liu Hai-Yan
author_sort Cao Yu-Dong
collection DOAJ
description A highly efficient deep fully convolutional neural network (DFCN) for image quality assessment (IQA) is designed in this paper. The DFCN consists of two branches, one scoring local patches and the other estimating the weights of local patches to enhance quality prediction. Then, the DFCN outputs quality score of the whole image with aggregate weighted average pooling. There are no fully connected layers in the DFCN, resulting in far fewer parameters. In addition, the network model utilizes multiscale images as inputs to enrich the extracted distortion information. Furthermore, the parameters of the model are optimized in two steps to reduce the requirement for computing power and the risk of overfitting. The parameters of the shared layers and the quality module are optimized firstly, and then, the parameters of the weight module are optimized with the designed loss function. The extensive experimental results show that the proposed DFCN outperforms other competing IQA methods and has strong generalization ability.
format Article
id doaj-art-14e01bacad084dfeaf2cd411485f277c
institution Kabale University
issn 1687-5699
language English
publishDate 2022-01-01
publisher Wiley
record_format Article
series Advances in Multimedia
spelling doaj-art-14e01bacad084dfeaf2cd411485f277c2025-08-20T03:54:29ZengWileyAdvances in Multimedia1687-56992022-01-01202210.1155/2022/1686298Image Quality Predictor with Highly Efficient Fully Convolutional Neural NetworkCao Yu-Dong0Liao Xin-Lin1Liu Hai-Yan2School of Electronics and Information EngineeringSchool of Electronics and Information EngineeringSchool of Electronics and Information EngineeringA highly efficient deep fully convolutional neural network (DFCN) for image quality assessment (IQA) is designed in this paper. The DFCN consists of two branches, one scoring local patches and the other estimating the weights of local patches to enhance quality prediction. Then, the DFCN outputs quality score of the whole image with aggregate weighted average pooling. There are no fully connected layers in the DFCN, resulting in far fewer parameters. In addition, the network model utilizes multiscale images as inputs to enrich the extracted distortion information. Furthermore, the parameters of the model are optimized in two steps to reduce the requirement for computing power and the risk of overfitting. The parameters of the shared layers and the quality module are optimized firstly, and then, the parameters of the weight module are optimized with the designed loss function. The extensive experimental results show that the proposed DFCN outperforms other competing IQA methods and has strong generalization ability.http://dx.doi.org/10.1155/2022/1686298
spellingShingle Cao Yu-Dong
Liao Xin-Lin
Liu Hai-Yan
Image Quality Predictor with Highly Efficient Fully Convolutional Neural Network
Advances in Multimedia
title Image Quality Predictor with Highly Efficient Fully Convolutional Neural Network
title_full Image Quality Predictor with Highly Efficient Fully Convolutional Neural Network
title_fullStr Image Quality Predictor with Highly Efficient Fully Convolutional Neural Network
title_full_unstemmed Image Quality Predictor with Highly Efficient Fully Convolutional Neural Network
title_short Image Quality Predictor with Highly Efficient Fully Convolutional Neural Network
title_sort image quality predictor with highly efficient fully convolutional neural network
url http://dx.doi.org/10.1155/2022/1686298
work_keys_str_mv AT caoyudong imagequalitypredictorwithhighlyefficientfullyconvolutionalneuralnetwork
AT liaoxinlin imagequalitypredictorwithhighlyefficientfullyconvolutionalneuralnetwork
AT liuhaiyan imagequalitypredictorwithhighlyefficientfullyconvolutionalneuralnetwork