Statistical hypothesis testing as a novel perspective of pooling for image quality assessment

Image quality assessment is usually achieved by pooling local scores. However, commonly used strategies, based on simple sample statistics, are not always sensitive to distortions. In this short communication, we propose a novel perspective of pooling: reliable through statistical hypothesis testing, which enables effective detection subtle changes population parameters when the underlying distribution scores affected To illustrate significance perspective, design new strategy utilising one-sided one-sample t-test. The experiments benchmark databases show reliability testing-based pooling, compared with state-of-the-art strategies.