11–20 of 75 posts
This problem is fundamentally different with stereo images; there is a hope of reconstructing the exact 3D geometry of the page before flattening, rather than inferring from content. An iPhone app that did this would do well.
I wonder if someone has tried to dewarp whole book from a video when flipping through it. I imagine that could be handy way to copy the whole book.
This is great! My wife is a music teacher and often scans sheet music so that it's more portable. She has been asking me for a while for something exactly like this. I'll have to tweak it to work on sheet music, since I imagine his methods to identify lines of text won't work for the music staff out of the box.
I wonder if someone has tried to dewarp whole book from a video when flipping through it. I imagine that could be handy way to copy the whole book.
Page warp becomes but a tiny part of the problem with a page-flip video – now you have motion blur, varying exposure, resolution, noise, and depth of field to worry about. Maybe if you had a camera capable of recording extremely high frame rates at high resolution (probably north of 120fps @ 1440p), a high-intensity, diffuse light source, and a lens with a tight aperture / narrow focal length, you’d at least have som…
Thanks for the feedback, everyone -- happy to answer questions here or in the Disqus comments on my blog.
If you decide to try to make this faster, check out ceres[0] a non-linear least squares optimisation framework that does automatic differentiation using a clever C++ template hack.
I've used it a few times to solve these kind of problems and found it to be very good!
This is great! My wife is a music teacher and often scans sheet music so that it's more portable. She has been asking me for a while for something exactly like this. I'll have to tweak it to work on sheet music, since I imagine his methods to identify lines of text won't work for the music staff out of the box.
This is great! My wife is a music teacher and often scans sheet music so that it's more portable. She has been asking me for a while for something exactly like this. I'll have to tweak it to work on sheet music, since I imagine his methods to identify lines of text won't work for the music staff out of the box.
Earlier quoted context omitted.
Page warp becomes but a tiny part of the problem with a page-flip video – now you have motion blur, varying exposure, resolution, noise, and depth of field to worry about. Maybe if you had a camera capable of recording extremely high frame rates at high resolution (probably north of 120fps @ 1440p), a high-intensity, diffuse light source, and a lens with a tight aperture / narrow focal length, you’d at least have som…
Doesn't that describe most modern cell phone cameras?