Year: 2009
Type: report
Abstract: This paper aims to give a survey of full-reference image quality metrics,\nincluding metrics specifically designed to evaluate image quality, but\nalso metrics for image difference, image fidelity, and more. These metrics\nhave in common that they try to predict the perceived difference between\nan original image and a modified version of it, this modification can typically\nbe compression, halftoning and blurring. They output one numerical\nvalue and/or an image difference map. More than 100 image quality metrics\nhave been reviewed and categorized, and short descriptions and analysis of\nall metrics and their relationships are given. This should prove valuable to\nresearchers in various fields, to find the most appropriate metric for their application,\nand to give a better understanding of the state of the art of the field\nof image quality metrics.
Authors: Marius Pedersen, Jon Yngve Hardeberg
Institution: Gjøvik University College
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2474830469