iccv iccv2013 iccv2013-312 iccv2013-312-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Wufeng Xue, Xuanqin Mou, Lei Zhang, Xiangchu Feng
Abstract: How to measure the perceptual quality of natural images is an important problem in low level vision. It is known that the Mean Squared Error (MSE) is not an effective index to describe the perceptual fidelity of images. Numerous perceptual fidelity indices have been developed, while the representatives include the Structural SIMilarity (SSIM) index and its variants. However, most of those perceptual measures are nonlinear, and they cannot be easily adopted as an objective function to minimize in various low level vision tasks. Can MSE be perceptual fidelity aware after some minor adaptation ? In this paper we propose a simple framework to enhance the perceptual fidelity awareness of MSE by introducing an l2-norm structural error term to it. Such a Structural MSE (SMSE) can lead to very competitive image quality assessment (IQA) results. More surprisingly, we show that by using certain structure extractors, SMSE can befurther turned into a Gaussian smoothed MSE (i.e., the Euclidean distance between the original and distorted images after Gaussian , smooth filtering), which is much simpler to calculate but achieves rather better IQA performance than SSIM. The socalled Perceptual-fidelity Aware MSE (PAMSE) can have great potentials in applications such as perceptual image coding and perceptual image restoration.
[1] D. Brunet, E. R. Vrscay, and Z. Wang. On the mathematical properties of the structural similarity index. IEEE TIP, 21: 1488–1499, 2012. 2
[2] G. Cheng, J. Huang, C. Zhu, Z. Liu, and L. Cheng. Perceptual image quality assessment using a geometric structural distortion model. In IEEE ICIP, pages 325–328, 2010. 2, 3
[3] J. Daitch and D. Green. Contrast sensitivity of the human peripheral retina. Vision Research, 9(8):947–952, 1969. 7
[4] S. J. Daly. Visible differences predictor: an algorithm for the assessment of image fidelity. In SPIE/IS&T; Electronic Imaging, pages 2–15, 1992. 7
[5] J. E. Dowling. The retina: an approachable part of the brain. Optometry and Vision Science, 65, 1988. 3
[6] D. Gabor. Information theory in electron microscopy. Laboratory Investigation, 14:801–807, 1965. 7
[7] R. M. Gray. Toeplitz and Circulant Matrices: A Review. Foundations and Trends in Communications andInformation Theory, 2:155–239, 2005. 4
[8] V. Q. E. Group et al. Final report from the video quality experts group on the validation of objective models of video quality assessment, phase II. VQEG, Aug, 2003. 5
[9] K. Hirakawa and T. Parks. Image denoising using total least squares. TIP, 15(9):2730–2742, 2006. 1
[10] E. Larson and D. Chandler. Most apparent distortion: fullreference image quality assessment and the role of strategy. Journal of Electronic Imaging, 19(1), 2010. 2, 4, 6, 7
[11] M. Lindenbaum, M. Fischer, and A. M. Bruckstein. On Gabor’s contribution to image enhancement. Pattern Recognition, 27: 1–8, 1994. 7
[12] J. L. Mannos and D. J. Sakrison. The effects of a visual fidelity criterion of the encoding of images. IEEE Transactions on Information Theory, 20:525–536, 1974. 1
[13] T. Mitsa, K. L. Varkur, and J. R. Alford. Frequencychannel-based visual models as quantitative quality measures in halftoning. In IS&T;/SPIE Electronic Imaging, pages 390–401, 1993. 7
[14] J. B. Mulligan and A. J. Ahumada Jr. Principled halftoning based on human vision models. In SPIE/IS&T; Electronic Imaging, pages 109–121, 1992. 7
[15] N. Ponomarenko, V. Lukin, A. Zelensky, K. Egiazarian, M. Carli, and F. Battisti. TID2008-a database for evaluation offull-reference visual quality assessment metrics. Advances of Modern Radioelectronics, 10(10):30–45, 2009. 4
[16] A. Rehman and Z. Wang. SSIM-based non-local means image denoising. In IEEE ICIP, pages 217–220, 2011. 1, 2
[17] A. Rehman, Z. Wang, D. Brunet, and E. R. Vrscay. SSIMinspired image denoising using sparse representations. In IEEE ICASSP, pages 1121–1 124, 2011. 1, 2
[18] H. Sheikh and A. Bovik. Image information and visual quality. TIP, 15(2):430–444, 2006. 2, 6, 7
[19] H. Sheikh, A. Bovik, and G. De Veciana. An information fidelity criterion for image quality assessment using natural scene statistics. TIP, 14(12):21 17–2128, 2005. 2, 6, 7
[20] H. Sheikh, Z. Wang, L. Cormack, and A. Bovik. Live image quality assessment database release 2 (2005). 4
[21] A. W. M. Smeulders, M. Worring, S. Santini, A. Gupta, and R. Jain. Content-Based image retrieval at the end of the early years. IEEE TPAMI, 22: 1349–1380, 2000. 1
[22] M. Spiegel, S. Lipcshutz, and D. Spellman. Vector Analysis (2nd Edition). Foundations and Trends in Communications and Information Theory, 2009. 8
[23] S. Wang, A. Rehman, Z. Wang, S. Ma, and W. Gao. RateSSIM optimization for video coding. In IEEEICASSP, pages 833–836, 2011. 1, 2
[24] Z. Wang and A. Bovik. Mean squared error: Love it or leave it? a new look at signal fidelity measures. Signal Processing Magazine, IEEE, 26(1):98–1 17, 2009. 1
[25] Z. Wang, A. Bovik, H. Sheikh, and E. Simoncelli. Image quality assessment: From error visibility to structural similarity. IEEE TIP, 13(4):600–612, 2004. 2, 6, 7
[26] Z. Wang and E. P. Simoncelli. Maximum differentiation (mad) competition: A methodology for comparing computational models of perceptual quantities. Journal of Vision, 8(12), 2008. 2
[27] Y. Wong, S. Chen, S. Mau, C. Sanderson, and B. C. Lovell. Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition. In CVPR, pages 74–81, 2011. 1
[28] W. Xue and X. Mou. An image quality assessment metric based on non-shift edge. In ICIP, pages 3309–33 12, 2011. 2, 4, 6, 7
[29] H. Yan, L. Cervino, X. Jia, and S. B. Jiang. A comprehensive study on the relationship between the image quality and imaging dose in low-dose cone beam CT. Physics in Medicine and Biology, 57:2063–2080, 2012. 1
[30] L. Zhang, L. Zhang, X. Mou, and D. Zhang. Fsim: a feature similarity index for image quality assessment. IEEE TIP, 20(8):2378–2386, 2011. 2, 6, 7 [3 1] M. Zhang, X. Mou, and L. Zhang. Non-shift edge based ratio (nser): An image quality assessment metric based on early vision features. IEEE SPL, (99): 1–1, 2011. 2, 4 771122