To best of my knowledge, images are usually fed in pixel format to ML models. Is there any work that does image classification where the image format is SVG?

  • $\begingroup$ I'm not aware of the existence or non-existence of such work, but intuitively classifying images based on a procedural description of how they are drawn seems to be not very promising. SVG files with very similar structure may describe completely different images, and two files with very different structure might yield the same image. $\endgroup$ – Hans-Martin Mosner Aug 6 '20 at 19:30

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.