A New Framework for Evaluating Image Quality Including Deep Learning Task Performances as a Proxy

Pau Galles*, Katalin Takats, Miguel Hernandez-Cabronero, David Berga, Luciano Pega, Laura Riordan-Chen, Clara Garcia, Guillermo Becker, Adan Garriga, Anika Bukva, Joan Serra-Sagrista, David Vilaseca, Javier Marin

*Autor correspondiente de este trabajo

Producción científica: Contribución a una revistaArtículoInvestigaciónrevisión exhaustiva

1 Cita (Scopus)

Resumen

iquaflow is a framework that provides a set of tools to assess image quality. The user can add custom metrics that can be easily integrated and a set of unsupervised methods is offered by default. Furthermore, iquaflow measures quality by using the performance of AI models trained on the images as a proxy. This also helps to easily make studies of performance degradation of several modifications of the original dataset, for instance, with images reconstructed after different levels of lossy compression; satellite images would be a use case example, since they are commonly compressed before downloading to the ground. In this situation, the optimization problem involves finding images that, while being compressed to their smallest possible file size, still maintain sufficient quality to meet the required performance of the deep learning algorithms. Thus, a study with iquaflow is suitable for such case. All this development is wrapped in Mlflow: an interactive tool used to visualize and summarize the results. This document describes different use cases and provides links to their respective repositories. To ease the creation of new studies, we include a cookiecutter repository. The source code, issue tracker and aforementioned repositories are all hosted on GitHub.

Idioma originalInglés
Páginas (desde-hasta)3285-3296
Número de páginas12
PublicaciónIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Volumen17
DOI
EstadoPublicada - 13 dic 2023

Huella

Profundice en los temas de investigación de 'A New Framework for Evaluating Image Quality Including Deep Learning Task Performances as a Proxy'. En conjunto forman una huella única.

Citar esto