Entirely Blind Image Quality Assessment Estimator

Abstract:

Prior knowledge about anticipated distortions and their corresponding human opinion scores is needed in the most general purpose no-reference image quality assessment algorithms. When creating the model, all distortion types may not be existed. Predicting the quality of distorted images in practical no-reference image quality assessment algorithms is devised without prior knowledge about images or their distortions. In this study, a blind/no-reference opinion and distortion unaware image quality assessment algorithm based on natural scenes is developed. The proposed approach uses a set of novel features to measure image quality in a spatial domain. The extracted features which are from the scenes gist are formed using Weibull distribution statistics. When testing the proposed algorithm on LIVE database, experiments show that it correlates well with subjective opinion scores. They also show that the proposed algorithm significantly outperforms the popular full-reference peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) methods. Not only do the results reasonably well compete with the recently developed natural image quality evaluator (NIQE) model, but also outperform it.

• Periodical: Applied Mechanics and Materials (Volumes 543-547)
• Pages: 2496-2499
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.543-547.2496
• Online since: March 2014
• Authors: Abdalmajeed Saifeldeen*, Shu Hong Jiao, Wei Liu
• Keywords: Blind/No-Reference, Image Quality Assessment, Wiebull Distribution

References

[1] Gabarda, S. and Cristobal, G., No-reference image quality assessment, through von mises distribution, Journal of the Optical Society of America A (JOSA A), 29: 2058–2066(2012).

DOI: 10.1364/josaa.29.002058

[2] A. Mittal, A. K. Moorthy, and A. C. Bovid, No-reference image quality assessment in the spatial domain, IEEE Trans. Image Process., 21: 4695 - 4708, ( 2012).

DOI: 10.1109/tip.2012.2214050

[3] A. Mittal, G. S. Muralidhar, J. Ghosh, and A. C. Bovik, Blind image quality assessment without human training using latent quality factors, IEEE Signal Process. Lett., 19: 75–78, (2011).

DOI: 10.1109/lsp.2011.2179293

[4] Anish Mittal, Rajiv Soundararajan, and Alan C. Bovik, Making a "Completely Blind" Image Quality Analyzer, IEEE Signal Processing Letters, 20: 209-212, (2013).

DOI: 10.1109/lsp.2012.2227726

[5] Ghebreab, S., A.W.M. Smeulders, H. S. Scholte, and V.A.F. Lamme. 2009, A biologically plausible model for rapid natural image identification, Advances in Neural Information Processing Systems 22- Proceedings of the, 629-637. (2009).

[6] Jan-Mark Geusebroek and Arnold, W.M., A six-stimulus theory for stochastic texture, nternational Journal of Computer Vision, 62: 7-16, (2005).

[7] Timm, F. and E. Barth, 2011. Non-parametric texture defect detection using Weibull features. Proceedings of the SPIE 7877, 2011, San Francisc.

DOI: 10.1117/12.872463

[8] D. Martin, C. Fowlkes, D. Tal, and J. Malik, A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics, in Int. Conf. Comput. Vision, 2, 416–423, ( 2001).

DOI: 10.1109/iccv.2001.937655

[9] H. R. Sheikh, Z. Wang, L. Cormack and A. C. Bovik, LIVE Image Quality Assessment Database Release 2, Laboratory for Image and Video Engineering. http: /live. ece. utexas. edu/research/quality, ( 2005).

[10] H. Sheikh, M. Sabir, and A. Bovik, A statistical evaluation of recent full reference image quality assessment algorithms, IEEE Trans. Image Process, 15: 3440–3451, (2006).

DOI: 10.1109/tip.2006.881959

[11] Z. Wang, A.C. Bovik, H.R. Sheikh, and E.P. Simoncelli, Image quality assessment: from error visibility to structuralsimilarity, IEEE Trans, 13: 600-612, ( 2004).

DOI: 10.1109/tip.2003.819861