Signal, Image and Video Processing

, Volume 10, Issue 4, pp 609–616 | Cite as

No-reference image quality assessment using Prewitt magnitude based on convolutional neural networks

  • Jie Li
  • Lian Zou
  • Jia Yan
  • Dexiang Deng
  • Tao Qu
  • Guihui Xie
Original Paper

Abstract

No-reference image quality assessment is of great importance to numerous image processing applications, and various methods have been widely studied with promising results. These methods exploit handcrafted features in the transformation or space domain that are discriminated for image degradations. However, abundant a priori knowledge is required to extract these handcrafted features. The convolutional neural network (CNN) is recently introduced into the no-reference image quality assessment, which integrates feature learning and regression into one optimization process. Therefore, the network structure generates an effective model for estimating image quality. However, the image quality score obtained by the CNN is based on the mean of all of the image patch scores without considering the human visual system, such as edges and contour of images. In this paper, we combine the CNN and the Prewitt magnitude of segmented images and obtain the image quality score using the mean of all the products of the image patch scores and weights based on the result of segmented images. Experimental results on various image distortion types demonstrate that the proposed algorithm achieves good performance.

Keywords

No-reference image quality assessment Convolutional neural networks (CNNs) Graph-based image segmentation Prewitt magnitude 

References

  1. 1.
    Thung, K.H., Paramesran, R.: A survey of image quality measures. In: Proceedings of international conference for technical postgraduates (TECHPOS). pp. 1–4 (2009)Google Scholar
  2. 2.
    Sheikh, H.R., Bovik, A.C., de Veciana, G.: An information fidelity criterion for image quality assessment using natural scene statistics. IEEE Trans. Image Process. 14(12), 2117–2128 (2005)CrossRefGoogle Scholar
  3. 3.
    Zhang, L., Zhang, D., Mou, X., Zhang, D.: FSIM: a feature similarity index for image quality assessment. IEEE Trans. Image Process. 20(8), 2378–2386 (2011)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Li, Qiang, Wang, Zhou: Reduced-reference image quality assessment using divisive normalization-based image representation. IEEE Signal Process. Soc. 2(3), 202–211 (2009)Google Scholar
  5. 5.
    Narwaria, M., Lin, W., McLoughlin, I., Emmanuel, S., Chia, L.T.: Fourier transform based scalable image quality measure. IEEE Trans. Image Process. 21(8), 3364–3377 (2012)Google Scholar
  6. 6.
    Moorthy, A.K., Bovik, A.C.: A two-step framework for constructing blind image quality indices. IEEE Signal Process. Lett. 17(5), 513–516 (2010)Google Scholar
  7. 7.
    Moorthy, A.K., Bovik, A.C.: Blind image quality assessment: from natural scene statistics to perceptual quality. IEEE Trans. Image Process. 20(12), 3350–3364 (2011)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Saad, M., Bovik, A.C., Charrier, C.: Blind image quality assessment: a natural scene statistics approach in the DCT domain. IEEE Trans. Image Process. 21(8), 3339–3352 (2012)Google Scholar
  9. 9.
    Ye, P., Kumar, J., Kang, L., Doermann, D.: Unsupervised feature learning framework for no-reference image quality assessment. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1098–1105 (2012)Google Scholar
  10. 10.
    Mittal, A., Moorthy, A., Bovik, A.: No-reference image quality assessment in the spatial domain. IEEE Trans. Image Process. 21(12), 4695–4708 (2012)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Kang, L., Ye, P.: Convolutional neutral networks for no-reference image quality assessment. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)Google Scholar
  12. 12.
    Narwaria, M., Lin, W.: Objective image quality assessment based on support vector regression. IEEE Trans. Neural Netw. 21(3), 515–519 (2010)Google Scholar
  13. 13.
    Narwaria, M., Lin, W.: SVD-based quality metric for image and video using machine learning. IEEE Trans. Syst. Man Cybern. Part B 42(2), 347–364 (2012)Google Scholar
  14. 14.
    Narwaria, M., Lin, W.S., Enis Cetin, A.: Scalable image quality assessment with 2D mel-cepstrum and machine learning approach. Pattern Recognit. 45, 299–313 (2012)CrossRefGoogle Scholar
  15. 15.
    Chen, G.-H., Yang, C.-L., Xie, S.-L.: Gradient-based structural similarity for image quality assessment, conference: image processing. IEEE International Conference-ICIP, pp. 2929–2932 (2006)Google Scholar
  16. 16.
    Deng, L., Hinton, G.E., Kingsbury, B.: New types of deep neural network learning for speech recognition and related applications: an overview. In: IEEE International Conference on Acoustic Speech and Signal Processing (ICASSP 2013) (2013)Google Scholar
  17. 17.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. NIPS 1, 4 (2012)Google Scholar
  18. 18.
    Felzenszwalb, PedroF, Huttenlocher, DanielP: Efficient graph-based image segmentation. Int. J. Comput. Vis.—IJCV 59(2), 167–181 (2004)CrossRefGoogle Scholar
  19. 19.
    Mittal, A., Moorthy, A., Bovik, A.: No-reference image quality assessment in the spatial domain. IEEE Trans. Image Process. 21(12), 4695–4708 (2012)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Sheikh, H.R., Wang, Z., Cormack, L., Bovik, A.C.: LIVE image quality assessment database release2. http://live.ece.utexas.edu/research/quality
  21. 21.
    Ponomarenko, N., Lukin, V., Zelensky, A., Egiazarian, K., Carli, M., Battisti, F.: TID2008: a dataset for evaluation of full-reference visual quality assessment metrics. Adv. Mod. Radio Electron. 10, 30–45 (2009)Google Scholar

Copyright information

© Springer-Verlag London 2015

Authors and Affiliations

  • Jie Li
    • 1
  • Lian Zou
    • 1
  • Jia Yan
    • 1
  • Dexiang Deng
    • 1
  • Tao Qu
    • 1
  • Guihui Xie
    • 1
  1. 1.School of Electronic InformationWuhan UniversityWuhanChina

Personalised recommendations