An Underwater Image Quality Assessment Metric

Various image enhancement algorithms are adopted to improve underwater images that often suffer from visual distortions. It is critical assess the output quality of undergoing algorithms, and use results optimise imaging systems. In our previous study, we created a benchmark for assessment via subjective experiments. Building on benchmark, this paper proposes new objective metric can automatically enhancement, namely UWEQM. By characterising specific physics relevant properties human system, attributes computed combined yield an overall metric. Experimental show proposed UWEQM yields good performance in predicting as perceived by subjects.