-2

I'm doing object detection for texts in image and want to use Yolo to draw a bounding box where the text is in the image.

Then, how do you do data augmentation? Also, what is the difference between augmentation (contrast adjustment, gamma conversion, smoothing, noise, inversion, scaling, etc.) in ordinary image recognition?

If you have any useful website links, would you tell me plz :)

kitarikes
  • 1
  • 1

1 Answers1

0

If you mean by what should you use then, it just a regular object detection task, the common augment, like flips or crop, works fine.

For the difference, if you mean by what the output images will look like then look at this repo https://github.com/albumentations-team/albumentations

But of you mean by the model performance difference then there's probably no answer for that, you can only try several ways and see what's the best.

Natthaphon Hongcharoen
  • 2,244
  • 1
  • 9
  • 23