Research on No-reference Image Quality Assessment Algorithm Based on Generative Adversarial Networks

Wenqing Zhao; Haoyang Chen

doi:10.54097/fcis.v3i2.7234

Authors

Wenqing Zhao
Haoyang Chen

DOI:

https://doi.org/10.54097/fcis.v3i2.7234

Keywords:

Image quality assessment, Deep learning, Generative adversarial networks (GANs), Convolutional neural networks (CNNs), Feature extraction, Multi-scale feature fusion

Abstract

Currently, with the massive generation and transmission of digital images, especially the rapid development of the Internet and mobile Internet industries where images are widely used, the study of reference-free image quality assessment has attracted much attention in academia and practical applications, and is a popular research direction in the field of computer vision. In response to the low performance of existing reference-free image quality assessment algorithms in the face of real distorted images, a reference-free image quality assessment algorithm based on generative adversarial networks is proposed. Firstly, the generator structure is changed, the U-Net structure is improved, and the channel attention mechanism SeNet structure is introduced to update the feature map after down sampling. Secondly, a feature similarity measurement system is incorporated and a dual discriminator structure is used to discriminate multiple groups of images. The FPN structure is combined in the feature extractor to produce a multi-scale feature representation. Experiments are conducted on KonIQ-10k dataset and LIVEC dataset, and the experimental results show that the algorithm exhibits good prediction accuracy as well as good generalization performance in the face of real distorted images.

Downloads

Download data is not yet available.

References

V Kumar, Bawa V S. No reference image quality assessment metric based on regional mutual information among images[J]. 2019.

Oszust M. Local Feature Descriptor and Derivative Filters for Blind Image Quality Assessment[J]. IEEE Signal Processing Letters, 2019:1-1.

Liu Y, Gu K, Zhang Y, et al. Unsupervised Blind Image Quality Assessment via Statistical Measurements of Structure, Naturalness, and Perception[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30(4):929-943.

Bosse S , Maniry D , Muller K R , et al. Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment[J]. IEEE Transactions on Image Processing, 2017:1-1.

Kang L, Ye P , Li Y, Doermann D. Convolutional Neural Networks for No-Reference Image Quality Assessment[C]// 2014 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2014.

Bianco S, Celona L, Napoletano P , et al. On the Use of Deep Learning for Blind Image Quality Assessment[J]. Signal Image & Video Processing, 2016.

Lin K Y, Wang G. Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2018.

Ren H, Chen D , Wang Y . RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment[J]. 2017.

Pan D, Shi P, Hou M, et al. Blind predicting similar quality map for image quality assessment[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 6373-6382.

Cao Yudong, Cai Xibiao Reference free image quality evaluation algorithm based on enhanced adversarial learning [J] Computer Applications, 2020, v.40; No.363(11):72-77.

Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation[J]. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2015: 234-241.

Jv A, Yqc A , Jing W B . FaultFace: Deep Convolutional Generative Adversarial Network (DCGAN) based Ball-Bearing failure detection method[J]. Information Sciences, 2021, 542:195-211.

Mao C, Huang L , Xiao Y , et al. Target Recognition of SAR Image Based on CN-GAN and CNN in Complex Environment[J]. IEEE Access, 2021, PP (99):1-1.

Yanding Peng, Jiahua Xu, Ziyuan Luo, Wei Zhou, Zhibo Chen; Multi-Metric Fusion Network for Image Quality Assessment. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 1857-1860.