English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Image fusion helps in merging two or more images to construct a moreinformative single fused image. Recently, unsupervised learning basedconvolutional neural networks (CNN) have been utilized for different types ofimage fusion tasks such as medical image fusion, infrared-visible image fusionfor autonomous driving as well as multi-focus and multi-exposure image fusionfor satellite imagery. However, it is challenging to analyze the reliability ofthese CNNs for the image fusion tasks since no groundtruth is available. Thisled to the use of a wide variety of model architectures and optimizationfunctions yielding quite different fusion results. Additionally, due to thehighly opaque nature of such neural networks, it is difficult to explain theinternal mechanics behind its fusion results. To overcome these challenges, wepresent a novel real-time visualization tool, named FuseVis, with which theend-user can compute per-pixel saliency maps that examine the influence of theinput image pixels on each pixel of the fused image. We trained several imagefusion based CNNs on medical image pairs and then using our FuseVis tool, weperformed case studies on a specific clinical application by interpreting thesaliency maps from each of the fusion methods. We specifically visualized therelative influence of each input image on the predictions of the fused imageand showed that some of the evaluated image fusion methods are better suitedfor the specific clinical application. To the best of our knowledge, currently,there is no approach for visual analysis of neural networks for image fusion.Therefore, this work opens up a new research direction to improve theinterpretability of deep fusion networks. The FuseVis tool can also be adaptedin other deep neural network based image processing applications to make theminterpretable.

FuseVis: Interpreting neural networks for image fusion using per-pixel saliency visualization