Nowadays, multiple image processing areas have shown the necessity of what is called image fidelity assessment, i.e., the objective assessment of differences between a reference and a test image. More specifically, the objective of image fidelity assessment is to determine if there are visual differences between a given test image and the corresponding reference image considering certain features and if so to quantify those differences. The variety of image domains requiring image fidelity assessment implies the need for application specific or even application-tailored methodology rather than a one-size-fits-all solution. While many candidate algorithms already exist, testing them and identifying the best ones for a given use case is far from an easy exercise. Thus, it often takes a lot of time and effort to even prepare the test environment for benchmarking, validation and/or developing.

The image Fidelity Assessment Software (Github: iFAS) is a software tool designed to assist researchers, engineers and other users in the process of image fidelity assessment.

iFAS provides easy access to a range of state-of-the-art methods as well as intuitive visualizations that aid data analysis. Also, iFAS offers a wide variety of image fidelity measures: five miscellaneous measures, twelve texture-based measures, five fidelity measures based on contrast and twenty-three image color difference measures. The software is freely available to all for non-commercial use.

iFAS includes a range of common mechanisms for image fidelity assessment including computation of fidelity measures on a single pair of images and/or in a full database, visualization of pixel-wise image differences and histogram of the image differences, scatter plots and correlation analysis between human scores and objective measures.