Rating Super-Resolution Microscopy Images With Deep Learning

With super-resolution optical microscopy, it is now possible to observe molecular mechanisms. The quality of the obtained images vary a lot depending on the samples and the imaging parameters. Moreover, evaluating this quality is a difficult task. In this work, we want to learn the quality function from scores provided by experts. We propose the use of a deep network that output a quality score for a given image. A user study evaluate the quality of the predictions against human expert scores.

Authors

• Louis-Émile Robitaille
• Audrey Durand Université Laval Canada CIFAR AI Chair
• Marc-André Gardner
• Christian Gagné IID Université Laval Mila Canada CIFAR AI Chair
• Paul De Koninck
• Flavie Lavoie-Cardinal

Keywords

No keywords are indexed for this paper.