[1]:https://i.stack.imgur.com/0aien.jpg [2]: https://i.stack.imgur.com/x9fAv.jpg
So I have this two images as you can see in [2] image circle is cutted from above and below. I have data lots of [1] and [2] type images. What I want is to transform [1] type of images to [2] images such that the cutting of circles would be similar as in [2]. Meaning that if I for example train neural network on that data it wouldn't overfit just understanding they are cut in different way.
What I thought of doing is to find average angle of all [2] type of images as drawed and then cut somehow [1] type of images regard to that angle. I know the radius of the circle but have hard time finding the angle.