No-reference local image quality evaluation

Abstract

The Image Quality Assessment (IQA) metrics are developed to measure the perceptual quality of images after distortion. In this paper several No-Reference (NR) metrics are tested for different distortion types. In order to see how each type of distortion affects the image quality measures, each image will have only one type of distortion. The experiments analysis is performed aiming to local image quality evaluation in agreement with both subjective and objective assessment. The obtained experimental results show the potential of considering local quality estimation for dealing with actual challenges in efficient IQA.