Beginner needs guidance. Machine Learning, preparing training data

i try to dip my feet into the field of computer vision and want to avoid mistakes along the way.

The problem I have to solve: Classifiy images of 3D dental scans.

For example:

I wrote a script to create images of theses files in blender so i have full control over the image dimensions, quality, resolution ect.

Now to my questions:

Whats the best way to prepare a training dataset if you have full control over the process?

  • Higher resolution and let the computer downscale or provide the correct resolution to begin with.
  • Same image in different rotations?
  • Same image with different backgrounds?
  • Same image blurred or sharpened?
  • Same image zoomed in or out?
  • Same image with different lighting angles?
  • Same object seen from slightly different angles (maybe 5-10° offset from a top down view) ?

Do any of these things help or are they just a waste of time? Maybe you could give a newbie to this topic some guidance.

Btw: Which Library/Model would you reccomend for such a task? (Maybe thats to big of a question to ask)

Topic image-preprocessing image-classification beginner dataset machine-learning

Category Data Science

About

Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.