{"componentChunkName":"component---src-templates-blog-post-js","path":"/blog/fine-grained-multi-focus-image-fusion-based-on-edge-features/","result":{"data":{"site":{"siteMetadata":{"title":"No Frills News"}},"contentfulNfnPost":{"postTitle":"Fine-grained multi-focus image fusion based on edge features","slug":"fine-grained-multi-focus-image-fusion-based-on-edge-features","createdLocal":"2023-02-12 14:30:49.509834","publishDate":"None","feedName":"Image Recognition","sourceUrl":{"sourceUrl":"https://www.nature.com/articles/s41598-023-29584-y"},"postSummary":{"childMarkdownRemark":{"html":"<p>Here, several different fusion images are selected to compare the sharpness of the fused local image and the difference between the fused image and the original image.\nDIFNet uses concat for image fusion also has the same problem, so the fused image still retains the information of the defocus region of the original image.\nFigure 5 Comparison of difference between fused image and original image 1(Lytro 735).\nFusion strategy analysissIn the image fusion task, an image fusion strategy based on edge feature graph is proposed in this paper.\n7 that the fusion strategy based on edge feature map proposed in this paper is used for image fusion task.</p>"}}}},"pageContext":{"slug":"fine-grained-multi-focus-image-fusion-based-on-edge-features"}}}