Abstract
In recent years, Convolutional Neural Network (CNN) has been gradually applied to Image Quality Assessment (IQA). Most CNNs segment the image into patches for training, which lead to increase of data and affect calculation speed of the model. Meanwhile, the parameters of CNN usually reach millions, which is the root cause of overfitting. In this paper, a multiscale CNN for NR-IQA is established to solve these problems. Since IQA simulates the perception of Human Visual System (HVS) on image quality, salient areas are more valuable for reference. Therefore a patch sampling method was designed based on saliency detection. Firstly, patches with salient values between given thresholds are retained as training data. Secondly, the sampled patches are fed into multiscale CNN. The network consists of three branches with multiscale convolutional kernels. Finally, the weighted average of the quality scores from the salient patches is the final score. The CNN was trained on LIVE dataset and cross-validated on CSIQ dataset. The experimental results show that the proposed method can achieve better performance with fewer parameters compared with state-of-the-art NR-IQA algorithms.
Similar content being viewed by others
References
Achanta R, Estrada F, Wils P (2008) Salient region detection and segmentation. In: IEEE international conference on computer vision systems (ICVS), pp 66-75. https://doi.org/10.1007/978-3-540-79547-6_7
Achanta R, Hemami S, Estrada F, Susstrunk S (2009) Frequency-tuned salient region detection. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1597-1604. https://doi.org/10.1109/CVPR.2009.5206569
Bosse S, Maniry D, Wiegand T, Samek W (2016) A deep neural network for image quality assessment. In: IEEE international conference on image processing (ICIP), pp 3773-3777. https://doi.org/10.1109/ICIP.2016.7533065
Bosse S, Maniry D, Müller K, Wiegand T, Samek W (2018) Deep neural networks for no-reference and full-reference image quality assessment. IEEE Trans Image Process 27(1):206–219. https://doi.org/10.1109/TIP.2017.2760518
Chandler EC, Larson DM (2010) Most apparent distortion: full-reference image quality assessment and the role of strategy. Journal of Electronic Imaging 19(1):011006. https://doi.org/10.1117/1.3267105
Cheng M, Zhang G, Mitra NJ, Huang X, Hu S (2011) Global contrast based salient region detection. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 409-416. https://doi.org/10.1109/CVPR.2011.5995344
Gu K, Zhai G, Lin W, Yang X, Zhang W (2015) Visual saliency detection with free energy theory. IEEE Signal Process Lett 22(10):1552–1555. https://doi.org/10.1109/LSP.2015.2413944
Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011–2023. https://doi.org/10.1109/TPAMI.2019.2913372
Itti L, Koch C, Niebur E (1998) A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Mach Intell 20(11):1254–1259. https://doi.org/10.1109/34.730558
Jia S, Zhang Y (2018) Saliency-based deep convolutional neural network for no-reference image quality assessment. Multimed Tools Appl 77(12):14859–14872. https://doi.org/10.1007/s11042-017-5070-6
Kang L, Ye P, Li Y, Doermann D (2014) Convolutional neural networks for no-reference image quality assessment. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1733-1740. https://doi.org/10.1109/CVPR.2014.224
Li L, Zhou Y (2017) Visual saliency based blind image quality assessment via convolutional neural network. In: IEEE international conference on neural information processing (ICONIP), pp 550-557. https://doi.org/10.1007/978-3-319-70136-3_58
Li J, Zou L, Yan J, Deng D, Qu T, Xie G (2015) No-reference image quality assessment using prewitt magnitude based on convolutional neural networks. Signal Image Vid Process 10:609–616. https://doi.org/10.1007/s11760-015-0784-2
Li Y, Po L, Feng L, Yuan F (2016) No-reference image quality assessment with deep convolutional neural networks. In: IEEE international conference on digital signal processing (DSP), pp 685-689. https://doi.org/10.1109/ICDSP.2016.7868646
Ma J, Wu J, Li L, Dong W, Lin W (2021) Blind image quality assessment with active inference. IEEE Transactions on Image Processing, pp 99:1–1. https://doi.org/10.1109/TIP.2021.3064195
Mittal A, Moorthy AK, Bovik AC (2012) No-reference image quality assessment in the spatial domain. IEEE Trans Image Process 21(12):4695–4678. https://doi.org/10.1109/TIP.2012.2214050
Pan C, Xu Y, Yan Y, Gu K, Yang X (2016) Exploiting neural models for no-reference image quality assessment. In: IEEE visual communications and image processing (VCIP), pp1–4. https://doi.org/10.1109/VCIP.2016.7805524
Po LM, Liu M, YuenWilson YF et al (2019) A novel patch variance biased convolutional neural network for no-reference image quality assessment. IEEE Transactions on Circuits and Systems for Video Technology 29(4):1223–1229. https://doi.org/10.1109/TCSVT.2019.2891159
Sheikh H, Wang Z, Cormack L, Bovik A (2004) LIVE image quality assessment dataset release 2. http://live.ece.utexas.edu/research/quality
Sun C, Li H, Li W (2016) No-reference image quality assessment based on global and local content perception. In: IEEE visual communications and image processing (VCIP), pp 1-4. https://doi.org/10.1109/VCIP.2016.7805544
Xiong Y, Shao F, Meng Y, Zhou B, Ho YS (2019) Sparse representation of salient regions for no-reference image quality assessment. IEEE Access 13(5):106295–106306. https://doi.org/10.1177/1729881416669486
Ye P, Kumar J, Kang L, Doermann D (2012) Unsupervised feature learning framework for no-reference image quality assessment. In: IEEE conference on computer vision and pattern recognition (CVPR), pp1098–1105. https://doi.org/10.1109/CVPR.2012.6247789
Yun Z, Shah M (2006) Visual attention detection in video sequences using spatiotemporal cues. Proceedings of the 14th ACM international conference on multimedia, pp 815-824. https://doi.org/10.1145/1180639.1180824
Zhang L, Gu Z, Li H (2013) SDSP: a novel saliency detection method by combining simple priors. In: IEEE international conference on image processing (ICIP), pp 171-175. https://doi.org/10.1109/ICIP.2013.6728036
Zhang P, Zhou W, Wu L, Li H (2015) SOM: semantic obviousness metric for image quality assessment. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 2394-2402. https://doi.org/10.1109/CVPR.2015.7298853
Zhou ZN, Zhou Z, Huang J (2021) Gauss-guided patch-based deep convolutional neural networks for no-reference image quality assessment. J Intell Fuzzy Syst 41(1):1–10. https://doi.org/10.3233/JIFS-210063
Zoph B, Vasudevan V, Shlens J, Le QV (2017) Learning transferable architectures for scalable image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 8697–8710. https://doi.org/10.48550/arXiv.1707.07012
Acknowledgements
This work was supported by the National Natural, Science Foundation of China under Grant 61976027, Liaoning Provincial Department of Education under Grant LJ2019011, LJKZ1026, Liaoning Natural Foundation Guidance Plan under Grant 2019-ZD-0502, and Liaoning Revitalization Talents Program under Grant XLYC2008002.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Fan, X., Wang, Y., Wang, C. et al. Multiscale convolutional neural network for no-reference image quality assessment with saliency detection. Multimed Tools Appl 81, 42607–42619 (2022). https://doi.org/10.1007/s11042-022-13477-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13477-9