Image Quality Assessment Based on Region of Interest

Abstract:

In this paper a new No-Reference (NR) image quality assessment (IQA) method based on the point wise statistics of local normalized luminance signals using region of interest (ROI) processing is proposed. This algorithm firstly extracts the ROI which is relative to human subjectivity by using the image gradient and phase congruency, and then extracts the image quality feature in spatial domain. Particularly, most of the present IQA methods mainly focus on predicting the image quality with respect to human perception, yet, in some other image domains, the final receiver of a digital image may not a human. Thus, we propose a method which can assess the image quality relative to edge detection algorithm. In addition, experimental results on LIVE database are provided to justify the superior compared to the significant image quality metrics.

• Periodical: Applied Mechanics and Materials (Volume 596)
• Pages: 350-354
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.596.350
• Online since: July 2014
• Authors: Yue Wang*, Zeng Gang Lin, Zi Cheng Liao
• Keywords: Edge Detection, No Reference Image Quality Assessment, ROI

References

[1] H. R. Sheikh, A. C. Bovik, and L. Cormack, No-reference quality assessment using natural scene statistics: JPEG2000, IEEE Trans. Image Process., vol. 14, no. 11, p.1918–1927, Nov. (2005).

DOI: 10.1109/tip.2005.854492

[2] Gastaldo, P., Neural networks for the no-reference assessment of perceived quality. Journal of Electronic Imaging, 2005. 14(3): p.033004.

DOI: 10.1117/1.1988313

[3] Marziliano P., Dufaux F., Winkler S., Ebrahimi, T.: A no-reference perceptual blur metric. In: Proceedings of Image Processing, 2002 International Conference on Image Processing, Lausanne, Switzerland, vol. 3, p.57–60 (2002).

DOI: 10.1109/icip.2002.1038902

[4] Moorthy, A.K. and A.C. Bovik. A Two-Step Framework for Constructing Blind Image Quality Indices. IEEE Signal Processing Letters, 2010. 17(5): pp.513-516.

DOI: 10.1109/lsp.2010.2043888

[5] Ye P, Doermann D.  2012.  No-Reference Image Quality Assessment using Visual Codebooks. Image Processing, IEEE Transactions on PP (99): 1-1.

DOI: 10.1109/tip.2012.2190086

[6] H. R. Sheikh, Image Quality Assessment Using Natural Scene Statistics, Ph.D. dissertation, University of Texas at Austin, May (2004).

[7] L. Zhang, L. Zhang, X. Mou, and D. Zhang, FSIM: A feature similarity index for image quality assessment, IEEE Trans. Image Process., vol. 20, no. 8, p.2378–2386, Aug. (2011).

DOI: 10.1109/tip.2011.2109730

[8] Lu, T., Y. Zhang and H. Li, An image quality assessment algorithm based on feature selection, in Intelligent Science and Intelligent Data Engineering. 2013, Springer. P. 289-297.

DOI: 10.1007/978-3-642-36669-7_36

[9] P. Kovesi, Image features from phase congruency,J. Comput. Vis. Res., vol. 1, no. 3, p.1–26, (1999).

[10] Mittal, A., A.K. Moorthy and A.C. Bovik. No-reference image quality assessment in the spatial domain. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 2012. 21(12): pp.4695-4708.

DOI: 10.1109/tip.2012.2214050

[11] M. Narwaria and W. Lin. Objective image quality assessment based on support vector algorithms, Neutral compute, vol. 12 no. 5 pp.1207-1245, (2010).