TY - JOUR
T1 - A New Framework for Evaluating Image Quality Including Deep Learning Task Performances as a Proxy
AU - Galles, Pau
AU - Takats, Katalin
AU - Hernandez-Cabronero, Miguel
AU - Berga, David
AU - Pega, Luciano
AU - Riordan-Chen, Laura
AU - Garcia, Clara
AU - Becker, Guillermo
AU - Garriga, Adan
AU - Bukva, Anika
AU - Serra-Sagrista, Joan
AU - Vilaseca, David
AU - Marin, Javier
N1 - Publisher Copyright:
© 2008-2012 IEEE.
PY - 2023/12/13
Y1 - 2023/12/13
N2 - 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.
AB - 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.
KW - Artificial intelligence
KW - data compression
KW - image analysis
KW - image processing
KW - image resolution
KW - image segmentation
KW - object detection
KW - quality control
KW - remote sensing
UR - http://www.scopus.com/inward/record.url?scp=85180326286&partnerID=8YFLogxK
U2 - 10.1109/JSTARS.2023.3342475
DO - 10.1109/JSTARS.2023.3342475
M3 - Article
AN - SCOPUS:85180326286
SN - 1939-1404
VL - 17
SP - 3285
EP - 3296
JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ER -