Current Trends and Advances in Image Quality Assessment

Abstract

Image quality assessment (IQA) is one of the constantly active areas of research in computer vision. Starting from the idea of Universal Image Quality Index (UIQI), followed by well-known Structural Similarity (SSIM) and its numerous extensions and modifications, through Feature Similarity (FSIM) towards combined metrics using the multi-metric fusion approach, the development of image quality assessment is still in progress. Nevertheless, regardless of new databases and the potential use of deep learning methods, some challenges remain still up to date. Some of the IQA metrics can also be used efficiently for alternative purposes, such as texture similarity estimation, quality evaluation of 3D images and 3D printed surfaces as well as video quality assessment.