No-Reference JPEG image quality assessment based on Visual sensitivity

Full Text (PDF, 454KB), PP.45-51

Views: 0 Downloads: 0


Zhang You-Sai 1,* Chen Zhong-Jun 1

1. School of Electrical Information Jiangsu University of science and technology, Zhen Jiang, China

* Corresponding author.


Received: 14 Oct. 2010 / Revised: 2 Nov. 2010 / Accepted: 23 Dec. 2010 / Published: 8 Feb. 2011

Index Terms

Human visual sensitivity, support vector regression, neural network, image quality, No-reference assessment


In this paper, a novel human visual sensitivity measurement approach is presented to assessment the visual quality of JPEG-coded images without reference image. The key features of human visual sensitivity (HVS) such as edge amplitude and length, background activity and luminance are extracted from sample images as input vectors. SVR-NN was used to search and approximate the functional relationship between HVS and mean opinion score (MOS). Then, the measuring of visual quality of JPEG-coded images was realized. Experimental results prove that it is easy to initialize the network structure and set parameters of SVR-NN. And the better generalization performance owned by SVR-NN can add the new features of the sample automatically. Compared with other image quality metrics, the experimental results of the proposed metric exhibit much higher correlation with perception character of HVS. And the role of HVS feature in image quality index is fully reflected.

Cite This Paper

Zhang You-Sai, Chen Zhong-Jun, "No-Reference JPEG image quality assessment based on Visual sensitivity", International Journal of Modern Education and Computer Science(IJMECS), vol.3, no.1, pp.45-51, 2011. DOI:10.5815/ijmecs.2011.01.07


[1]P.Gastaldo,R.Zunino, “No-Reference Quality Assessment of JPEG Images by Using CBP Neural Networks, ” IEEE Internationa1 Symposium on Circuits and Systems, pp.772-775, May2004.
[2]R. Venkatesh Babu, S. Suresh, Andrew Perkis, “No-reference JPEG-image quality assessment using GAP-RBF,” Signal Processing of ScienceDirect, A87, 2007, pp.1493-1593.
[3]S. Suresh, R. Venkatesh Babu, “H.J. Kim. No-reference image quality assessment using modified extreme learning machine classifier,” Applied Soft Computing of ScienceDirect, pp.541–552, September2009,
[4]S.A. Karunasekera, N.G. Kingsbury, A distortion measure for blocking artifacts in images based on human visual sensitivity, IEEE Transactions on Image Processing, 4th ed., pp.713-724, June1995.
[5]C-C Chuang, S-F Su, “Robust Support Vector Regression Networks for Function Approximation with Outliers,” IEEE Trans on Neural Networks, 13th ed., pp.1322-1330, June2002.
[6]C-C Chuang, S-F Su, C-C Hsiao, “The annealing robust backprogagation (ARBP) learning algorithms,” IEEE Trans on Neural Networks, 11th ed., pp.1067-1077, May2000.
[7]Li Jun, Liu Junhua, “Identification of dynamic systems using support vector regression neural networks,” Journal of Southeast University (English Edition), pp.228-233, June 2006,.
[8]H.R. Sheikh, Z. Wang, L. Cormack, A.C. Bovik, “Live image quality assessment database”, website:
[9]P.Gastaldo,R.Zunino, “No-Reference Quality Assessment of JPEG Images by Using CB PNeura1 Networks,” IEEE Internationa1 Symposium on Circuits and Systems, pp.772-775, May2004.
[10]Z. Wang, A.C. Bovik, H.R. Sheikh, E.P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Trans. Image Process. 3rd ed., pp.600-612, April2004.