CNN-GRNN for Image Sharpness Assessment
Image sharpness is key to readability and scene understanding. Because of the inaccessible reference information, blind image sharpness assessment (BISA) is useful and challenging. In this paper, a shallow convolutional neural network (CNN) is proposed for intrinsic representation of image sharpness and general regression neural network (GRNN) is utilized for precise score prediction. The hybrid CNN-GRNN model tends to build functional relationship between retrieved features and subjective human scores by supervised learning. Superior to traditional algorithms based on handcrafted features and machine learning, CNN-GRNN fuses feature extraction and score prediction into an optimization procedure. Experiments on Gaussian blurring images in LIVE, CSIQ, TID2008 and TID2013 show that CNN-GRNN outperforms the state-of-the-art algorithms and gets closer to human subjective judgment.
KeywordsMean Opinion Score Convolutional Neural Network General Regression Neural Network Image Quality Assessment Image Sharpness
The authors would like to thank reviewers for their valuable suggestion that has helped to improve the paper quality. This work is supported from National Natural Science Foundation of China (Grant No. 81501463 and 61379143), Guangdong Innovative Research Team Program (Grant No. 2011S013), National 863 Programs of China (Grant No. 2015AA043203), the Shenzhen Fundamental Research Program (Grant Nos. JCYJ20140417113430726, JCYJ20140417113430665 and JCYJ20150401145529039), the Qing Lan Project of Jiangsu Province and the China Postdoctoral Science Foundation (Grant No. 2016M590827).
- 9.Kang, L., Ye, P., Li, Y., Doermann, D.: Convolutional neural networks for no-reference image quality assessment. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1733–1740 (2014)Google Scholar
- 10.Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
- 18.Lv, Q., Jiang, G., Yu, M., Xu, H., Shao, F., Liu, S.: Difference of Gaussian statistical features based blind image quality assessment: a deep learning approach. In: IEEE Conference on Image Processing, pp. 2344–2348 (2015)Google Scholar
- 25.Palm, R.B.: Prediction as a candidate for learning deep hierarchical models of data. Technical University of Denmar (2012)Google Scholar
- 26.Ponomarenko, N., Lukin, V., Zelensky, A., Egiazarian, K., Astola, J., Carli, M., Battisti, F.: TID2008 - a database for evaluation of full-reference visual quality assessment metrics. Adv. Mod. Radioelectron. 10(4), 30–45 (2009)Google Scholar
- 33.Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)Google Scholar
- 39.Yu, S., Zhang, W., Wu, S., Li, X., Xie, Y.: Applications of edge preservation ratio in image processing. In: IEEE International Conference on Signal Processing, pp. 698–702 (2014)Google Scholar