PROJECT TITLE :

No-Reference Image Sharpness Assessment in Autoregressive Parameter Space - 2015

ABSTRACT:

During this paper, we propose a brand new no-reference (NR)/ blind sharpness metric in the autoregressive (AR) parameter area. Our model is established via the analysis of AR model parameters, first calculating the energy- and distinction-variations in the regionally estimated AR coefficients in an exceedingly pointwise means, and then quantifying the image sharpness with percentile pooling to predict the general score. Over and above the luminance domain, we have a tendency to more take into account the inevitable impact of color info on visual perception to sharpness and thereby extend the above model to the widely used YIQ color house. Validation of our technique is conducted on the subsets with blurring artifacts from four giant-scale image databases (LIVE, TID2008, CSIQ, and TID2013). Experimental results make sure the superiority and efficiency of our methodology over existing NR algorithms, the state-of-the-art blind sharpness/blurriness estimators, and classical full-reference quality evaluators. Furthermore, the proposed metric can be additionally extended to stereoscopic pictures based mostly on binocular rivalry, and attains remarkably high performance on LIVE3D-I and LIVE3D-II databases.