Re:MLJ.jl: A Julia package for composable machine learning
by celrod on Sunday April 11, 2021 @10:37PM
(#26775611)
I'd also take a look at Images.jl:
https://juliaimages.org/latest/examples/
Noise removal example:
https://juliaimages.org/ImageFiltering.jl/stable/democards/d...
Re:MLJ.jl: A Julia package for composable machine learning
by doctoboggan on Sunday April 11, 2021 @11:49PM
(#26775913)
I can't really share any images with you as its my customers PII, but the cleanup stage involves a decent amount of artistic interpretation which is why I didn't think a normal image processing pipeline would work. They often come in smudged, missing lines, incomplete, or with some other error. Its not just a matter of playing with curves, levels, brightness, contrast, etc. I have to trace over them defining what I think the underlying print probably looked like.
Re:MLJ.jl: A Julia package for composable machine learning
by notagoodidea on Monday April 12, 2021 @03:07AM
(#26776720)
How far could you go with some automatic cleaning, something like `maptrace` [0] and some topology rules when you have your vector file to finish with some manual artistic polish? Because, i don't believe that you will achieve easily the "do-it-like-me" result expected from either GAN or VAE or autoencoders. In case of you want to look, the classic examples about style transfer (Photo to Van Gogh style, etc.) seems to be the way to go. Specific to Julia, you can look at Flux.jl or KNet.jl.
Re:MLJ.jl: A Julia package for composable machine learning
by syntaxing on Monday April 12, 2021 @09:49AM
(#26779385)
I think it's a common misconception that OpenCV is Photoshop in coding form. There's a ton of powerful that you can use for what you described but hard to say without seeing the pics. A good example is noise removal in the PSD domain (power spectrum density, not PSD photoshop files).
[1] https://docs.opencv.org/master/d2/d0b/tutorial_periodic_nois...
Re:MLJ.jl: A Julia package for composable machine learning
by foerbert on Monday April 12, 2021 @01:42AM
(#26776349)
Naively that doesn't seem like a major problem. I'd see it as largely setting up a bunch of constraints and methods to generate candidate solutions - after the initial image processing, obviously.
Re:MLJ.jl: A Julia package for composable machine learning
by tomrod on Sunday April 11, 2021 @09:26PM
(#26775284)
You're right on the VAE. Depending on output quality, my experience has been fewer samples are needed for VAE training.
Re:MLJ.jl: A Julia package for composable machine learning
by teruakohatu on Sunday April 11, 2021 @10:01PM
(#26775471)
I agree. For cleaning up a fingerprint I would think you could get good enough using Opencv. People have been cleanly vectoring raster images long before deep learning.
If you can automate it using a combination of Gimp filters + Inkscape, you probably can do it pretty easily convert that process into code.
Re:MLJ.jl: A Julia package for composable machine learning
by doctoboggan on Sunday April 11, 2021 @11:51PM
(#26775919)
I can and do simply rasterize images for some of my clean and proper fingerprints. The problem I am having is with smudges, incomplete prints, or other artifacts. In those cases I trace over and fix the print sometimes taking a decent amount of artistic license depending on the underlying quality of the image.
Re:MLJ.jl: A Julia package for composable machine learning
by bryanrasmussen on Monday April 12, 2021 @02:02AM
(#26776418)
maybe a quick mvp would be to detect smudged images, and separate those out for manual handling, and the non smudged automatically rasterized.
[1] https://www.mygreatlearning.com/blog/autoencoder/