Hybrid Neural Systems for Reduced-Reference Image Quality Assessment

  • Judith Redi
  • Paolo Gastaldo
  • Rodolfo Zunino
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5769)

Abstract

Reduced-reference paradigms are suitable for supporting real-time modeling of perceived quality, since they make use of salient features both from the target image and its original, undistorted version, without requiring the full original information. In this paper a reduced-reference system is proposed, based on a feature-based description of images which encodes relevant information on the changes in luminance distribution brought about by distortions. Such a numerical description feeds a double-layer hybrid neural system: first, the kind of distortion affecting the image is identified by a classifier relying on Support Vector Machines (SVMs); in a second step, the actual quality level of the distorted image is assessed by a dedicated predictor based on Circular Back Propagation (CBP) neural networks, specifically trained to assess image quality for a given artifact. The general validity of the approach is supported by experimental validations based on subjective quality data.

Keywords

Image quality assessment neural networks svm 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    ITU: Methodology for the subjective assessment of the quality of television pictures. International Telecommunication Union (1995)Google Scholar
  2. 2.
    Wang, Z., Sheikh, H., Bovik, A.: The Handbook of Video Databases: Design and Applications. CRC Press, Boca Raton (2003)Google Scholar
  3. 3.
    Sheikh, H., Sabir, M., Bovik, A.: A statistical evaluation of recent full reference image quality assessment algorithm. IEEE Trans. Image Processing (2006)Google Scholar
  4. 4.
    Wang, Z., Simoncelli, E.P.: Reduced-reference image quality assessment using a wavelet-domain natural image statistic model. Proc. SPIE Human Vision and Electronic Imaging (2005)Google Scholar
  5. 5.
    Gastaldo, P., Zunino, Z.: Neural networks for the no-reference assessment of perceived quality. Journal of Electronic Imaging (2005)Google Scholar
  6. 6.
    Redi, J., Gastaldo, P., Zunino, R., Heynderickx, I.: Co-occurrence matrixes for the quality assessment of coded images. In: Kůrková, V., Neruda, R., Koutník, J. (eds.) ICANN 2008, Part I. LNCS, vol. 5163, pp. 897–906. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  7. 7.
    Huang, J., Kumar, S.R., Mitra, M., Zhu, W., Zabih, R.: Image indexing using color correlograms. In: Proc. IEEE CVPR 1997, pp. 762–768 (1997)Google Scholar
  8. 8.
    Haralick, R., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Trans. on Systems, Man and Cybernetics SMC-3 (1973)Google Scholar
  9. 9.
    Sheikh, H., Wang, Z., Cormack, L., Bovik, A.: Image quality assessment database, http://live.ece.utexas.edu/research/quality
  10. 10.
    Vapnik, V.: Statistical Learning Theory. Wiley, Chichester (1998)MATHGoogle Scholar
  11. 11.
    Bartlett, P., Boucheron, S., Lugosi, G.: Model selection and error estimation. Machine Learning, 85–113 (2002)Google Scholar
  12. 12.
    Ridella, S., Rovetta, S., Zunino, R.: Circular back-propagation networks for classification. IEEE Trans. on Neural Networks, 84–97 (1997)Google Scholar
  13. 13.
    Rumelhart, D., McClelland, J.: Parallel distributed processing (1986)Google Scholar
  14. 14.
    Kittler, J., Hatef, M., Duin, R., Matas, J.: On combining classifiers. IEEE Trans. Pattern Analysis and Machine Intelligence (1998)Google Scholar
  15. 15.
    Kittler, J., Hatef, M., Duin, R., Matas, J.: Final report from the video quality experts group on the validation of objective models of video quality assessment (2000), http://www.vqeg.org/

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Judith Redi
    • 1
  • Paolo Gastaldo
    • 1
  • Rodolfo Zunino
    • 1
  1. 1.Dept. of Biophysical and Electronic Engineering (DIBE)Genoa UniversityGenoaItaly

Personalised recommendations