Blind quality assessment of gamut-mapped images via local and global statistical analysis

Abstract

Gamut mapping is a key technology to achieve high-quality cross-media color reproduction. To optimize a gamut mapping algorithm, an important step is to conduct an accurate evaluation of its psycho-visual performance. This paper presents an objective blind image quality assessment (BIQA) metric for gamut-mapped images based on natural scene statistics. Considering both the local and global aspects of distortions in gamut-mapped images, two categories of statistics are analyzed. Specifically, the local statistical features are used to portray structural and color distortions and features extracted from global statistics are utilized to characterize the naturalness of image. The proposed metric does not need ground truth quality scores for training, thus it is ”completely” blind. Experimental results on three gamut mapping databases demonstrate that our method outperforms the state-of-the-art general-purpose BIQA models. To further validate its effectiveness, the proposed metric is applied for benchmarking GMAs as an application and achieves encouraging performance.