Improving precision of objective image/video quality meters

Abstract Although subjective test is the most accurate image/video quality assessment tool, it extremely time demanding. In past two decades, a variety of objective measuring tools, such as SSIM, IW-SSIM, SPSIM, FSIM, etc., have been devised, that well correlate with tests results. However, main problem these methods they do not discriminate measured enough, especially at high range. this article we show how accuracy/precision Image Quality Assessment (IQA) meters can be increased by mapping them into Logistic Function (LF). The precisions are tested over databases. Our experimental indicate while used high-quality images discriminated 23% resolution on MOS scores, discrimination widely IQAs only 2%, but their mapped to range improved 9 − 17%, depending characteristics LF function. Moreover, precision low mid also improved. At range, 23.2%, those raw nearly 8.9%, adapted logistic functions very close MOS. image databases Pearson Linear Correlation Coefficient (PLCC) function 2 20% well.