March 2017
Spotlight Summary by Roarke Horstmeyer
Multi-focus image fusion based on dictionary learning with rolling guidance filter
I think we all have taken a blurry picture before. When we’re in a rush to pull out our camera or cell phone, or when the light is low and it is hard to hold everything steady, the resulting image can look pretty disappointing. While camera autofocus methods can now dramatically improve the quality of our quick snapshots, it still seems that there are just too many blurry images in my photo albums. Here, Yan and colleagues address the issue of image blur by proposing a new post-processing algorithm. Instead of working to sharpen up just a single image, which has proven to be quite a challenge, the authors consider taking a set of two or more images, where each image is focused at a different depth. From this image set, the authors then compute a new photo that shows everything in sharp focus. Their “image fusion” technique first identifies the areas within each photo that are well resolved, and then blends these different areas together into the final result. Hopefully, with a technique like this, we can start to sharpen up some of the disappointing images that find their way into our photo albums!
You must log in to add comments.
Add Comment
You must log in to add comments.
Article Information
Multi-focus image fusion based on dictionary learning with rolling guidance filter
Xiang Yan, Hanlin Qin, and Jia Li
J. Opt. Soc. Am. A 34(3) 432-440 (2017) View: Abstract | HTML | PDF