Abstract
A good objective metric of image quality assessment (IQA) should be consistent with the subjective judgment of human beings. In this paper, a four-stage perceptual approach for full reference IQA is presented. In the first stage, the visual features are extracted by 2-D Gabor filter that has the excellent performance of modeling the receptive fields of simple cells in the primary visual cortex. Then in the second stage, the extracted features are post-processed by the divisive normalization transform to reflect the nonlinear mechanisms in human visual systems. In the third stage, mutual information between the visual features of the reference and distorted images is employed to measure the visual quality. And in the last pooling stage, the mutual information is converted to the final objective quality score. Experimental results show that the proposed metic has a high correlation with the subjective assessment and outperforms other state-of-the-art metrics.
Similar content being viewed by others
References
Wang Z, Bovik A C. Mean squared error: love it or leave it?-A new look at signal fidelity measures. IEEE Signal Process Mag, 2009, 1: 98–117
Sheikh H R, Bovik A C, Veciana G. An information fidelity criterion for image quality assessment using natural scene statistics. IEEE Trans Image Process, 2005, 12: 2117–2128
Karam L J, Ebrahimi T, Hemami S S, et al. Introduction to the issue on visual media quality assessment. IEEE J Sel Top Signal Process, 2009, 3: 189–190
Liu H, Heynderickx I. Visual attention in objective image quality assessment: based on eye-tracking data. IEEE Trans Circ Syst Video Technol, 2011, 1: 971–982
Ferzli R, Karam L J. A no-reference objective image sharpness metric based on the notion of just noticeable blur (JNB). IEEE Trans Image Process, 2009, 4: 717–728
Ma L, Li S N, Zhang F, et al. Reduced-reference image quality assessment using reorganized DCT-based image representation. IEEE Trans Multimedia, 2011, 4: 824–829
Sheikh H R, Sabir M F, Bovik A C. A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Trans Image Process, 2006, 11: 3440–3451
Wang Z, Bovik A C. Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process, 2004, 4: 600–612
Moorthy A K, Bovik A C. Visual importance pooling for image quality assessment. IEEE J Sel Top Signal Process, 2009, 2: 193–200
Gao X B, Lu W, Tao D C, et al. Image quality assessment based on multiscale geometric analysis. IEEE Trans Image Process, 2009, 7: 1409–1423
Rao D V, Reddy L P. Contrast weighted perceptual structural similarity index for image quality assessment. J Electron Imag, 2010, 1: 011003-1–9
Wang Z, Li Q. Information content weighting for perceptual image quality assessment. IEEE Trans Image Process, 2011, 5: 1185–1198
Sampat M P, Wang Z, Gupta S, et al. Complex wavelet structural similarity: a new image similarity index. IEEE Trans Image Process, 2009, 11: 2385–2401
Shnayderman A, Gusev A, Eskicioglu A M. An SVD-based grayscale image quality measure for local and global assessment. IEEE Trans Image Process, 2006, 2: 422–429
Sheikh H R, Bovik A C. Image information and visual quality. IEEE Trans Image Process, 2006, 2: 430–444
Daugman J G. Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. J Opt Soc Am A-Opt Image Sci, 1985, 7: 1160–1169
David J F. Relation between the statistics of the natural images and the response properties of the cortical cells. J Opt Soc Am A-Opt Image Sci, 1987, 12: 2379–2394
Valois R L, Albrecht D G, Thorell L G. The orientation and direction selectivity of cells in macaque visual cortex. Vision Res, 1982, 5: 545–559
Grigorescu S E, Petkov N, Kruizinga P. Comparison of texture features based on Gabor filters. IEEE Trans Image Process, 2002, 10: 1160–1167
Schwartz O, Simoncelli E P. Natural signal statistics and sensory gain control. Nat Neurosci, 2001, 8: 819–825
Malo J, Epifanio I, Navarro R, et al. Non-linear image representation for efficient perceptual coding. IEEE Trans Image Process, 2006, 1: 68–80
Li Q, Wang Z. Reduced-reference image quality assessment using divisive normalization-based image representation. IEEE J Sel Top Signal Process, 2009, 2: 202–211
Zoran D, Weiss Y. The “tree-dependent components” of natural images are edge filters. Adv Neural Inf Process Syst, 2009, 22: 2340–2348
Pollen D A, Ronner S F. Phase relationships between adjacent simple cells in the visual cortex. Science, 1981, 4501: 1409–1411
Thevenaz P, Unser M. Optimization of mutual information for multiresolution image registration. IEEE Trans Image Process, 2000, 12: 2083–2099
Maes F, Collignon A, Vandermeulen D, et al. Multi-modality image registration by maximization of mutual information. IEEE Trans Med Imag, 1997, 2: 187–198
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ding, Y., Zhang, Y., Wang, X. et al. Perceptual image quality assessment metric using mutual information of Gabor features. Sci. China Inf. Sci. 57, 1–9 (2014). https://doi.org/10.1007/s11432-013-4881-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11432-013-4881-y