An efficient color image quality metric with local-tuned-global model

This paper investigates the problem of full-reference (FR) image quality assessment (IQA). In general, the ideal IQA metric should be effective and efficient, yet most of existing FR IQA methods cannot reach these two targets simultaneously. Under the supposition that the human visual perception to image quality depends on salient local distortion and global quality degradation, we introduce a novel effective and efficient local-tuned-global (LTG) model induced IQA metric. Extensive experiments are conducted on five publicly available subject-rated color image quality databases, including LIVE, TID2008, CSIQ, IVC and TID2013, to evaluate and compare our algorithm with classical and state-of-the-art FR IQA approaches. The proposed LTG is shown to work fast and outperform those competing methods.