A novel weight pooling method for objective image quality assessment with the luminance adaptation effect in the pixel intensity domain

Human Visual System (HVS) contains some important psychophysical characteristics and the most important among those are the contrast sensitivity function and luminance adaptation (LA) effect, that can potentially be used for modeling better image quality assessment (IQA) methods. As a result, some existing IQA methods have intrinsically adopted the Weber's law model to reflect the LA effects. But the authors have found that the way of adopting the LA effect was inappropriate. Recent psychophysical studies reveal that the Weber's law model is unable to be precisely fitted in the measured data for the LA effect. Furthermore, most IQA methods attempt to measure the quality in the pixel intensity domain, while the Weber's law works in the luminance domain and pixel intensity domain has a nonlinear relationship with the luminance domain. To address these problems, the authors derive a new LA effect model in the pixel intensity domain. Based on their derived LA effect model, the authors propose a new weight pooling method for the LA effect, denoted as LA-based Local weight Function (LALF). Their comprehensive experimental results prove that LALF can easily be applied in existing FR-IQA methods and it significantly improves the performance of the base methods in which LALF is applied.