Digital image quality assessment using Structural Similarity index based on polynomial windows and transform-based measure using perceptually uniform colour spaces

• Autorzy: Okarma K.
• Konferencja: Scientific Conference on Computer Applications in Electrical Engineering [13; April 14-16, 2008; Poznan]
• Języki publikacji: EN

Abstrakty

EN

In the paper the possibilities of using polynomial window functions for objective image quality assessment based on the Structural Similarity (SSIM) approach are considered as well as the usage of perceptually uniform colour spaces such as CIELAB and CIELUV for colour image quality assessment. The method of image quality assessment based on SSIM index is one of the latest techniques quite well correlated with the Human Visual System (HVS), but the proper choice of the window function plays an important role for the obtained results. The influence of the 2-D polynomial window properties on the values of SSIM index are investigated in the first part of the paper. Some other recently presented full-reference transform-based image quality assessment metrics utilising DFT, DCT and DWT transforms as well as SVD-based measure are typically used only for luminance channel of the image calculated according to YUV or YIQ colour models. In the second part of this paper some extension possibilities of such measures in purpose to determine the quality of colour images with better correlation to Human Visual System (HVS) are presented.

Słowa kluczowe

EN

digital image quality; structural similarity index; polynomial windows; transform-based measures; colour image quality

• Wydawca: Wydawnictwo Politechniki Poznańskiej
• Czasopismo: Poznan University of Technology Academic Journals. Electrical Engineering
• Rocznik: 2009
• Tom: No 59
• Strony: 35--46
• Opis fizyczny: Bibliogr. 7 poz.

Twórcy

autor

Okarma K.

• Szczecin University of Technology

Bibliografia

• [1] Eskicioglu, A., Fisher, P., Chen,S.: Image Quality Measures and Their Performance, IEEE Trans. Communicat. 43 (12) (1995), pp. 2959-2965.
• [2] Girshtel, E., Slobodyan, V.,Weissman, J., Eskicioglu, A.: Comparison of Three Full-Reference Color Image Quality Measures, 18-th 1S&T/SP1E Annual Symposium on Electronic Imaging, Image Quality and System Performance, San Jose, CA, Proc. SPIE 6059 (2006).
• [3] Okarma K.: Polynomial Windows with Low Sidelobes' Level, Signal Processing 87 (4) (2007), pp. 782-788.
• [4] Shnayderman, A., Gusev, A., Eskicioglu, A.: A Multidimensional Image Quality Measure Using Singular Value Decomposition, Proceedings of SPIE Image Quality and System Performance 5294 (1) (2003), p. 82-92.
• [5] Shnayderman, A., Eskicioglu, A.: Assessment of Full Color Image Quality with Singular Value Decomposition, 17-th IS&T/SPIE Annual Symposium on Electronic Imaging, Image Quality and System Performance, San Jose, CA, Proc. SPIE 5668 (2005).
• [6] Wang, Z., Bovik, A.: A Universal Image Quality Index, IEEE Signal Processing Letters 9 (3) (2002), pp. 81-84.
• [7] Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image Quality Assessment: From Error Measurement to Structural Similarity, IEEE Transactions on Image Processing 13(4) (2004), pp. 600-612.