Gopika S, D Malathi
Digital imaging and image-processing technologies have revolutionized the way in which we capture, store, receive, download, view, utilize, and share images. It is highly desirable to have a mechanism to assess the quality of the images that we encounter in our day to day life. The best way to assess the quality of an image is by doing subjective analysis (MOS). But human eye cannot distinguish the minor variations in image content downloaded from cloud. Also, the MOS method is too inconvenient, slow and expensive for practical usage. Here, we propose a natural scene statistic (NSS)-based image quality assessment (IQA) mechanism which operates in the spatial domain. This mechanism uses the scene statistics of normalized luminance coefficients to quantify the ‘naturalness’ (or lack thereof) in the image due to the presence of distortions.
NSS images , Gaussian Distribution , Luminance, MSCN Coeficients;