Tariq BASHIR, Imran USMAN, Shahnawaz KHAN, Junaid ur REHMAN

Intelligent reorganized discrete cosine transform for reduced reference image quality assessment

Reduced reference image quality assessment does not require the presence of the original image for assessing the quality of a degraded image. This work proposes an intelligent method for reduced reference image quality assessment based on a reorganized discrete cosine transform (RDCT). A genetic algorithm (GA) is used to compute optimized estimation of the generalized Gaussian distribution (GGD), which then approximates the coefficient distribution in the RDCT domain. Experimental results validate that such an intelligent estimation produces far superior results compared to conventional empirical estimation methods as presented in the literature. We compare the proposed technique with a number of contemporary techniques in the literature and demonstrate the generalization capability and effectiveness of the proposed technique as compared to prior works.

PDF

___

[1] Zhou W, Bovik AC, Ligang L. Why is image quality assessment so difficult? In: IEEE International Conference on Acoustics, Speech and Signal Processing; 1317 May 2002; Orlando, FL, USA: IEEE. pp. 4:3313-3316.
[2] Sheikh HR, Bovik AC. Image information and visual quality. IEEE T Image Process 2006; 15: 430-444.
[3] Wang Z, Sheikh HR, Bovik AC. Objective video quality assessment. In: Furht B, Marqure O, editors. The Handbook of Video Databases: Design and Applications. New York, NY, USA: CRC Press, 2003. pp. 1041-1078.
[4] Kim HT, Raveendran P. A survey of image quality measures. In: International Conference for Technical Postgraduates; 1415 Dec. 2009; Kuala Lumpur, Malaysia: IEEE. pp. 1-4.
[5] Sheikh HR, Sabir MF, Bovik AC. A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms. IEEE T Image Process 2006; 15: 3440-3451.
[6] Wang Z, Bovik AC, Simoncelli E. Structural Approaches to Image Quality Assessment. In: Bovik AC, editor. Handbook of Image and Video Processing. New York, NY, USA: Academic Press, 2005. pp. 961-974.
[7] Zhou W, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: from error visibility to structural similarity. IEEE T Image Process 2004; 13: 600-612.
[8] Sanghoon L, Pattichis MS, Bovik AC. Foveated video quality assessment. IEEE T Multimedia 2002; 4: 129-132.
[9] Sheikh HR, Bovik AC, Cormack L. No-reference quality assessment using natural scene statistics: JPEG2000. IEEE T Image Process 2005; 14: 1918-1927.
[10] Gao X, Lu W, Tao D, Li X. Image quality assessment based on multiscale geometric analysis. IEEE T Image Process 2009; 18: 1409-1423.
[11] Wang Z, Simoncelli EP. Reduced-reference image quality assessment using a wavelet domain natural image statistics models. In: International Society for Optics and Photonics; 18 March 2005; San Jose, CA, USA. IS&T/SPIE. pp. 149-159.
[12] Tao D, Li X, Lu W, Gao X. Reduced-reference IQA in contourlet domain. IEEE T Syst Man Cy B 2009; 39: 1623-1627.
[13] Lin M, Songnan L, Fan Z, King NN. Reduced-reference image quality assessment using reorganized DCT-based image representation. IEEE T Multimedia 2011; 13: 824-829.
[14] Qiang L, Zhou W. Reduced-reference image quality assessment using divisive normalization-based image representation. IEEE J Sel Top Signa 2009; 3: 202-211.
[15] Li L, Tong CS, Choy SK. Texture classification using refined histogram. IEEE T Image Process 2010; 19: 1371-1378.
[16] Cover TM, Thomson JA. Elements of Information Theory. 2nd ed. Hoboken, NJ, USA: Wiley, 2006.
[17] Xiong Z, Guleryuz OG, Orchard MT. A DCT-based embedded image coder. IEEE Signal Proc Let 1996; 3: 289-290.
[18] Lam EY, Goodman JW. A mathematical analysis of the DCT coef?cient distributions for images. IEEE T Image Process 2000; 9: 1661-1666.
[19] Naheed T, Usman I, Khan TM, Dar AH, Shafique MF. Intelligent reversible watermarking technique in medical images using GA & PSO. International Journal for Light and Electron Optics 2011; 125: 2515-2525.
[20] Usman I, Khan A, Chamlawi R. Employing intelligence in the embedding and decoding stages of a robust watermarking system. AEU-International Journal of Electronics and Communications 2011; 65: 582-588.
[21] Simoncelli EP, Freeman WT, Adelson E H, Heeger DJ. Shiftable multi-scale transforms. IEEE T Inform Theory 1992; 38: 587-607.