Blind Image Quality Assessment Using Latent Dirichlet Allocation Model

Abstract:

In this paper, we propose a blind image quality assessment (IQA) method under latent Dirichlet allocation (LDA) model. To assess the image quality, firstly, we learn topic-specific word distribution by training a set of pristine and distorted images without human subjective scores. Secondly, LDA model is used to estimate probability distribution of topic for the regions in the test images. Finally, we calculate the perceptual quality score of the test image by comparing the estimated probabilities of topics of the test image with that for the pristine images. Note that the quality-aware visual words are used to represent the images, which generated with respect to the natural scene statistic features. Experimental evaluation on the publicly available subjective-rated database LIVE demonstrates that our proposed method correlates reasonably well with different mean opinion scores (DMOS).

• Periodical: Applied Mechanics and Materials (Volume 483)
• Pages: 594-598
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.483.594
• Online since: December 2013
• Authors: Wang Luo*, Tian Bing Zhang
• Keywords: Distortion, Image Quality, Latent Dirichlet Allocation, No-Reference, Quality Assessment

References

[1] Z. Wang, A. Bovik, H. Sheikh, and E. Simoncelli, Image quality assessment: From error visibility to structural similarity, IEEE Transactions on Image Processing, vol. 13, no. 4, pp.600-612, (2004).

DOI: 10.1109/tip.2003.819861

[2] L. Zhang, L. Zhang, X. Mou, and D. Zhang, Fsim: a feature similarity index for image quality assessment, IEEE Transactions on Image Processing, vol. 20, no. 8, pp.2378-2386, (2011).

DOI: 10.1109/tip.2011.2109730

[3] A. Mittal, G. S. Muralidhar, J. Ghosh, and A. C. Bovik, Blind image quality assessment without huan training using latent quality factors, IEEE Signal Processing Letters, vol. 19, no. 2, pp.75-78, (2012).

DOI: 10.1109/lsp.2011.2179293

[4] W. Luo, H. Li, and G. Liu, Automatic annotation of multispectral satellite images using author topic model, IEEE Geoscience and Remote Sensing Letters, vol. 9, no. 4, pp.634-638, (2012).

DOI: 10.1109/lgrs.2011.2177064

[5] D. M. Blei, A. Y. Ng, and M. I. Jordan, Latent Dirichlet allocation, J. Mach. Learn. Res., vol. 3, no. 5, pp.993-1022, Mar. (2003).

[6] A. Mittal, A. Moorthy, and A. Bovik, Blind/referenceless im-age spatial quality evaluator, In IEEE Asilomar Conference on Signals, Systems and Computers, p.723–727, (2011).

DOI: 10.1109/acssc.2011.6190099

[7] H. R. Sheikh, M. F. Sabir, and A. C. Bovik, A statistical evaluation of recent full reference image quality assessment algorithms, IEEE Transactions on Image Processing, vol. 15, no. 11, pp.3440-3451, (2006).

DOI: 10.1109/tip.2006.881959

[8] J. Sivic, B. C. Russell, A. A. Efros, A. Zisserman, and W. T. Freeman, Discovering objects and their location in images, in IEEE Int. Conf. Computer Vision, pp.370-377, (2005).

DOI: 10.1109/iccv.2005.77

[9] F. F. Li and P. Perona, A bayesian hierarchical model for learning natural scene categories, In IEEE Conference on Computer Vision and Pattern Recognition, (2005).

DOI: 10.1109/cvpr.2005.16