1
$\begingroup$

I'm working on denoising dirty image document. I want to create a dataset wherein synthetic noise will be added to simulate real-world, messy artifacts. Simulated dirt may include coffee stains, faded sun spots, dog-eared pages, lot of wrinkles and many more. How shall I do that?

Sample Clean Image:

enter image description here

After adding Random Noise :

enter image description here

enter image description here

enter image description here

enter image description here

How can I randomly achieve images shown above?

$\endgroup$
  • 1
    $\begingroup$ How did you get the images above? $\endgroup$ – Royi Nov 23 '19 at 12:28
  • $\begingroup$ @Royi - It was from Kaggle Challenge. kaggle.com/c/denoising-dirty-documents/overview/description $\endgroup$ – Alyssa Gono Nov 23 '19 at 13:20
  • 1
    $\begingroup$ I would say you need a generative model to generate those documents. $\endgroup$ – Royi Nov 23 '19 at 14:21
  • $\begingroup$ @Royi --> Can you link any research about generating images using genrative models? $\endgroup$ – Alyssa Gono Nov 25 '19 at 9:57
  • 1
    $\begingroup$ Anything which has GAN or Variational Auto Encoders in it. $\endgroup$ – Royi Nov 25 '19 at 14:50

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.