Title: Multiple distortion pooling image quality assessment

Authors: Prateek Gupta; Neha Tripathi; Vikrant Bhateja

Addresses: Department of Electronics and Communication Engineering, SRMGPC, Lucknow, India ' Tata Consultancy Services, Trivandrum, Kerala, India ' Department of Electronics and Communication Engineering, SRMGPC, Lucknow, India

Abstract: This paper presents a quality assessment method which pools some basic image quality assessment parameters and empirically combines them in such a manner to evaluate across different distortion types. The proposed quality metric (Q) is formulated by modelling an image distortion as a combined effect of structural distortion, contrast distortion and edge distortion, which may occur on account of deteriorations due to noise contamination, contrast manipulations, blurring, rotation or compression. The values of the correlation coefficient prove that this metric provides an accurate estimation for the above mentioned distortions in comparison to mean squared error (MSE) and structural similarity measure (SSIM). Results of subjective evaluation also validate the efficiency of the proposed quality assessment method and its ability to quantify the effect of different distortions under a single quality metric.

Keywords: contrast improvement index; CII; human visual system; HVS; mean squared error; MSE; quality metric; mean opinion score; MOS; multiple distortion pooling; image quality assessment; human vision; modelling; image distortion; structural distortion; contrast distortion; edge distortion; structural similarity measure.

DOI: 10.1504/IJCONVC.2013.054655

International Journal of Convergence Computing, 2013 Vol.1 No.1, pp.60 - 72

Received: 25 Feb 2012
Accepted: 14 Mar 2012
Published online: 19 Jul 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article