A no-reference underwater image quality evaluator via quality-aware features

In this paper, we propose a novel no-reference evaluator based on quality-aware features, called QA-UIQE, for underwater image quality assessment. QA-UIQE extracts and fuses a set of quality-aware features including naturalness, color, contrast, sharpness, and structure. Technically, we first present a new color-cast weighted colorfulness measurement as well as color consistency measurement to characterize color, and design a saliency-weighted contrast measurement to improve the distinguishing ability of measuring contrast. Also, the locally mean subtracted and contrast normalized, maximum local variation, and local entropy are incorporated to measure naturalness, sharpness and structure, respectively. Afterward, we integrate the feature vectors extracted from the training set into Gaussian process regression to predict the image quality. Moreover, we collect a real-world underwater image dataset for testing the generalization ability of our method. The experimental results illustrate that our QA-UIQE has a superior prediction accuracy and is highly consistent with human visual perception.