The images in my dataset look are as below:
The images have either a purple background or a white one. But the trained model (cnn) will be tested on images from the field ,that is, they will most probably have a green background with a lot of stray leaves.
So, should I remove the background of the training images by using a mask? The same mask will be applied to images that will be imported from the field.
If yes, then how to do create such a mask? I have a total of 54305 images. How can I apply it to all images.