Blind quality assessment for tone-mapped images based on local and global features

In order to show high dynamic range (HDR) images by traditional displays, various tone-mapping operators have been designed to convert HDR images into low dynamic range (LDR) images recently. However, how to estimate the visual quality of LDR images effectively is still challenging. In this paper, we propose a novel blind quality assessment method for tone-mapped images with the consideration of naturalness and the perceptual characteristics of human visual system (HVS). First, we design parametric models that describe characteristics of chromatic information in tone-mapped images and extract quality-aware features based on global statistics model to characterize the naturalness of tone-mapped images. Second, motivated by perceptual characteristics that the HVS is highly adaptive to the image texture, we employ local texture features to capture the quality degradation of tone-mapped images. Support vector regression (SVR) is used to train the quality prediction model from features to human ratings. Experimental results indicate that the proposed metric can get better performance in predicting the visual quality of tone-mapped images than the state-of-the-art methods.