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)