A full reference Morphological Edge Similarity Index to account processing induced edge artefacts in magnetic resonance images

• Autorzy: Kuppusamy P. G. , Joseph J. , Sivaraman J.

Identyfikatory

DOI

10.1016/j.bbe.2016.12.008

• Języki publikacji: EN

Abstrakty

EN

An objective measure of edge similarity between the original and processed images to quantify the processing induced artefacts in medical image computing is proposed in this article. Globally accepted Image Quality Analysis (IQA) indices such as Peak Signal Noise Ratio (PSNR) and Structural Similarity Index Metric (SSIM) measure the structural similarity between the original and processed image and do not specifically reflect the resemblance of the edge content. Most of the IQA indices either do not comply with the subjective quality ratings or they are prone to noise level. In the proposed Morphological Edge Similarity Index (MESI), the binary edge maps of the reference and processed images are generated via gradient based threshold and these edge maps are objectively compared to yield a reliable edge quality metric. The index is found superior to Edge Preservation Index (EPI), Edge Strength Similarity based Image quality Metric (ESSIM) and SSIM in terms of dynamic variability, correlation with subjective quality ratings, robustness to noise and sensitivity to degradation in edge quality caused by blockiness artefacts in image compression. MESI exhibits a correlation of 0.9985, very close to unity, with the subjective quality ratings. It is useful for objectively evaluating the performance of denoising, sharpening and enhancement schemes and for the selection of optimum value of the arbitrary parameters used in them.

Słowa kluczowe

EN

Edge Similarity Index; blur metric; image quality analysis; Pratt's figure of merit; edge strength

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2017
• Tom: Vol. 37, no. 1
• Strony: 159--166
• Opis fizyczny: Bibliogr. 37 poz., rys., wykr.

Twórcy

autor

Kuppusamy P. G.

• Department of Electronics and Communication Engineering, Vel Tech Multi Tech Engineering College, Chennai, India

autor

Joseph J.

• Department of Applied Electronics & Instrumentation, St. Joseph's College of Engineering & Technology, Kerala, India

autor

Sivaraman J.

• Department of Biomedical Engineering, Vel Tech Multi Tech Engineering College, Avadi, Chennai 600062, India

Bibliografia

• [1] Molina CL, De Baets B, Bustince H. Quantitative error measures for edge detection. Pattern Recognit 2013;46 (4):1125–39.
• [2] Zhang L, Zhang L, Mou X, Zhang D. FSIM: a feature similarity index for image quality assessment. IEEE Trans Image Process 2011;20(8):2378–86.
• [3] Wang Z, Bovik AC. A universal image quality index. IEEE Signal Process Lett 2002;9(3):81–4.
• [4] Lu Q, Du L, Xiao X. An edge weighted RS image quality evaluation method. Proceedings of International Conference on Computer Science and Software Engineering, vol. 6; 2008. p. 197–200.
• [5] Chen GH, Yang CL, Po LM, Xie SL. Edge-based structural similarity for image quality assessment. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 2; 2006. p. 14–9.
• [6] Liu LX, Wang YQ. A mean-edge structural similarity for image quality assessment. Proceedings of the 6th International Conference on Fuzzy Systems and Knowledge Discovery, vol. 5; 2009. p. 311–5.
• [7] Liao B, Chen Y. An image quality assessment algorithm based on dual-scale edge structure similarity. Proceedings of the 2nd International Conference on Innovative Computing, Information and Control; 2007. p. 56.
• [8] Wang Z, Simoncelli EP, Bovik AC. Multiscale structural similarity for image quality assessment. Proceedings of International Conference on Signals, Systems and Computers, vol. 2; 2003. p. 1398–402.
• [9] Cui L, Allen AR. An image quality metric based on corner, edge and symmetry maps. Proceedings of British Machine Conference; 2008. p. 1–10.
• [10] Rao DV, Reddy LP. Weighted structural similarity based on edge strength for image quality assessment. Int J Comput Theory Eng 2009;1:1793–8201.
• [11] Li C, Bovik AC. Three-component weighted structural similarity index. Proceedings of SPIE 7242, Image Quality and System Performance VI; 2009. http://dx.doi.org/10.1117/12.811821.
• [12] Gore A, Kansal HK, Gupta S. A directional edge metric for image quality assessment. J Elect Electron Eng 2014;2:47–51.
• [13] Jang WD, Kim CS. SEQM: edge quality assessment based on structural pixel matching. Proceedings of Visual Communication and Image Processing; 2012. p. 1–6.
• [14] Xue W, Zhang L, Mou X, Bovik AC. Gradient magnitude similarity deviation: a highly efficient perceptual image quality index. IEEE Trans Image Process 2014;23:684–95.
• [15] Hofbauer H, Uhl A. An effective and efficient visual quality index based on local edge gradients. Proceedings of Workshop on Visual Performance Analysis; 2011. p. 162–7.
• [16] Chandler DM, Hemami SS. VSNR: a wavelet-based visual signal-to-noise ratio for natural images. IEEE Trans Image Process 2007;16:2284–98.
• [17] Sampat MP, Wang Z, Gupta S, Bovik AC, Markey MK. Complex wavelet structural similarity: a new image similarity index. IEEE Trans Image Process 2009;18:2385–401.
• [18] Sheikh HR, Bovik AC. Image information and visual quality. IEEE Trans Image Process 2006;15:430–44.
• [19] Cui Z, Kim DO, Park RH. Image quality assessment using the motif scan. Signal Image Process Int J 2012;3:41–55.
• [20] Zhang M, Mou X, Zhang D. Non-shift edge based ratio (NSER): an image quality assessment metric based on early vision features. IEEE Signal Process Lett 2011;18:315–8.
• [21] Xue W, Mou X. An image quality assessment metric based on non-shift edge. Proceedings of International Conference on Image Processing; 2011. p. 3309–12.
• [22] Kitchen L, Rosenfeld A. Edge evaluation using local edge coherence. IEEE Trans Syst Man Cybern 1981;11:597–605.
• [23] Strickland RN, Chang DK. Adaptable edge quality metric. Opt Eng 1993;32:944–51.
• [24] Khvorostov PV, Braun M, Poon CS. Edge quality metric for arbitrary two-dimensional images. Opt Eng 1996;35:3222–6.
• [25] Qiu F, Berglund J, Jensen JR, Thakkar P, Ren D. Speckle noise reduction in SAR imagery using a local adaptive median filter. J Geogr Inf Sci Remote Sens 2004;41:244–66.
• [26] Ni Z, Ma L, Zeng H, Cai C, Ma KK. Screen content image quality assessment using edge model. Proceedings of IEEE International Conference on Image Processing (ICIP); 2016. p. 81–5.
• [27] Sattar F, Floreby L, Salomonsson G, Lovstrom B. Image enhancement based on a nonlinear multiscale method. IEEE Trans Image Process 1997;6:888–95.
• [28] Yang X, Wu K, Tang Y. A new metric for measuring structure-preserving capability of despeckling of SAR images. ISPRS J Photogramm 2014;94:143–59.
• [29] Zhang X, Feng X, Wang W, Xue W. Edge strength similarity for image quality assessment. IEEE Signal Process Lett 2013;20(4):319–22.
• [30] Pratt WK. Digital image processing. New York: Wiley; 1977.
• [31] Ranjani JJ, Thiruvengadam SJ. Dual-tree complex wavelet transform based SAR despeckling using inter-scale dependence. IEEE Trans Geosci Remote Sens 2010;48:2723–31.
• [32] Gonzalez RC, Woods RE. Digital image processing. 2nd ed. Singapore: Pearson Education; 2002.
• [33] Agaian SS, Panetta KA, Nercessian SC, Danahy EE. Boolean derivatives with application to edge detection for imaging systems. IEEE Trans Syst Man Cybern B Cybern 2010;40:371–82.
• [34] Bao P, Zhang L, Wu X. Canny edge detection enhancement by scale multiplication. IEEE Trans Pattern Anal Mach Intell 2005;27:1485–90.
• [35] Trahanias P, Venetsanopoulos A. Vector order statistics operators as colour edge detectors. IEEE Trans Syst Man Cybern B Cybern 1996;26:135–43.
• [36] Evans AN, Liu XU. A morphological gradient approach to colour edge detection. IEEE Trans Image Process 2006;15:1454–63.
• [37] Wang Z, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 2004;13:600–12.

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017).