A multi-metric fusion approach to visual quality assessment

This paper presents a new methodology for objective visual quality assessment with multi-metric fusion (MMF). The current research is motivated by the observation that there is no single metric that gives the best performance scores in all situations. To achieve MMF, we adopt a regression approach. First, we collect a large number of image samples, each of which has a score labeled by human observers and scores associated with different metrics. The new MMF score is set to be the nonlinear combination of multiple metrics with suitable weights obtained by a training process. Furthermore, we divide image distortions into groups and perform regression within each group, which is called “context-dependent MMF” (CD-MMF). One task in CD-MMF is to determine the context automatically, which is achieved by a machine learning approach. It is shown by experimental results that the proposed MMF metric outperforms all existing metrics by a significant margin.