Foveated Model based on the Action Potential of Ganglion Cells to Improve Objective Image Quality Metrics

Sergio A. C. Bezerra, Alexandre Pohl

Abstract

In this work, a foveated model (FM) based on the action potential of ganglion cells in the human retina is employed to improve the results obtained by traditional and perceptual image quality metrics. LIVE and VAIQ image databases are used in the experiments to test and validate this model. Statistical techniques, such as the Pearson Linear Correlation Coefficient (PLCC), the Spearman Rank-Order Correlation Coefficient (SROCC) and the Root Mean Square Error (RMSE), are used to evaluate the performance of Peak Signal-to- Noise Ratio (PSNR) and Structural SIMilarity (SSIM) metrics, as well as their versions improved by the FM. The results are encouraging because the model proposed improve the performance of the metrics investigated.

References

  1. Barten, P. G. J. (1999). Contrast sensitivity of the human eye and its effects on image quality. HV Press, Knegsel.
  2. Corriveau, P. (2006). Video Quality Testing, In: H. R. Wu, K. R. Rao, Digital Video Image Quality and Perceptual Coding. CRC Press, USA.
  3. Curcio, C. A. and Allen, K. A. (Oct. 1990). Topography of ganglion cells in human retina. In Journal of Comparative Neurology, volume 300, pages 5 - 25.
  4. Engelke, U., Maeder, A., and Zepernick, H. (2009). Visual attention modelling for subjective image quality databases. In Multimedia Signal Processing (MMSP'09), IEEE International Workshop on, pages 1 - 6.
  5. Engelke, U. and Zepernick, H. (May 2007). Perceptualbased quality metrics for image and video services: A survey. In Next Generation Internet Networks, 3rd Euro NGI Conference on, pages 190 - 197.
  6. H. R. Sheikh, M. F. Sabir, A. C. B. (Nov 2006). A statistical evaluation of recent full reference image quality assessment algorithms. In Image Processing, IEEE Transactions on, volume 15, pages 3441 - 3452.
  7. ITU-R BT.500-11 (2002). Methodology for the subjective assessment of the quality of television pictures. ITU.
  8. ITU-T P.910 (2008). Subjective video quality assessment methods for multimedia applications. ITU.
  9. Pappas, T. N., Safranek, R. J., and Chen, J. (2005). Elsevier, USA, 2 edition.
  10. Ponomarenko, N., Lukin, V., Zelensky, A., Egiazarian, K., Astola, J., Carli, M., and Battisti, F. (2009). Tid2008 - a database for evaluation of full-reference visual quality assessment metrics. In Advances of Modern Radioeletronics, volume 10, pages 30 - 45.
  11. Seshadrinathan, K. and Bovik, A. C. (April 2007). A structural similarity metric for video based on motion models. In Acoustic, Speech and Signal Processing (ICASSP 2007), IEEE International Conference on, volume 1, pages I-869 - I-872.
  12. Sheikh, H. R. and Bovik, A. C. (2006). Image information and visual quality. In Image Processing, IEEE Transactions on, volume 15, pages 430 - 444.
  13. Sheikh, H. R., Wang, Z., Cormack, L., and Bovik, A. C. (2005). Live image quality assessment database release 2. In http://live.ece.utexas.edu/research/quality.
  14. Sun, H., Chen, X., and Chiang, T. (2005). Digital video transcoding for transmission and storage. CRC Press, USA.
  15. VQEG (2003). Final Report from the Video Quality Experts Group on the Validation of Objective Models of Video Quality Assessment, Phase II. Video Quality Experts Group (VQEG). timedia Quality Assessment, Phase I. Video Quality Experts Group (VQEG).
  16. Wang, Z. (2014). The ssim index for image quality assessment. In https://ece.uwaterloo.ca/~z70wang/ research/ssim/.
  17. Wang, Z. and Bovik, A. C. (2006). Modern Image Quality Assessment. Morgan & Claypool, USA.
  18. Wang, Z. and Bovik, A. C. (March 2002). A universal image quality index. In IEEE Signal Processing Letters, volume 9, pages 600 - 612.
  19. Wang, Z., Bovik, A. C., and Sheikh, H. R. (April 2004a). Image quality assessment: From error visibility to structural similarity. In Image Processing, IEEE Transactions on, volume 13, pages 600 - 612.
  20. Wang, Z., Lu, L., and Bovik, A. C. (February 2004b). Video quality assessment based on structural distortion measurement. In Signal Processing: Image Communication, volume 19, pages 121 - 132.
  21. Wang, Z., Simoncelli, E., and Bovik, A. C. (November 2003). Multi-scale structural similarity for image quality assessment. In Signals, Systems and Computers, volume 2, pages 1398 - 1402.
  22. Yang, K., Huang, A., Nguyen, T. Q., Guest, C. C., and Das, P. K. (September 2008). A new objective quality metric for frame interpolation used in video compression. In Broadcasting, IEEE Transactions on, volume 54, pages 680 - 690.
  23. Ye, S., Su, K., and Xiao, C. (2008). Video quality assessment based on edge structural similarity. In Image and Signal Processing (CISP 2008), International Congress on, pages 445 - 448.
  24. Yu, Z. and Wu, H. R. (2000). Human visual system based objective digital video quality metrics. In Signal Processing (ICSP2000), IEEE Proceedings of International Conference on, volume 2, pages 1088 - 1095.
  25. Zhang, L., Zhang, D., Mou, X., and Zhang, D. (Agosto 2011). Fsim: A feature similarity index for image quality assessment. In Image Processing, IEEE Transactions on, volume 20, pages 2378 - 2386.
Download


Paper Citation


in Harvard Style

Bezerra S. and Pohl A. (2015). Foveated Model based on the Action Potential of Ganglion Cells to Improve Objective Image Quality Metrics . In Proceedings of the 12th International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2015) ISBN 978-989-758-118-2, pages 84-91. DOI: 10.5220/0005547200840091


in Bibtex Style

@conference{sigmap15,
author={Sergio A. C. Bezerra and Alexandre Pohl},
title={Foveated Model based on the Action Potential of Ganglion Cells to Improve Objective Image Quality Metrics},
booktitle={Proceedings of the 12th International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2015)},
year={2015},
pages={84-91},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005547200840091},
isbn={978-989-758-118-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2015)
TI - Foveated Model based on the Action Potential of Ganglion Cells to Improve Objective Image Quality Metrics
SN - 978-989-758-118-2
AU - Bezerra S.
AU - Pohl A.
PY - 2015
SP - 84
EP - 91
DO - 10.5220/0005547200840091