Hello, I am junior in the fields of image processing, and object detection and would appreciate some help-
I am trying to detect some vessels in neuroimages, using ilastik.
In the training phase, I have labeled the original images by hand (for about 20 images). Now, the result is not great, and I wish to improve it. Since I can detect (by eye) the objects much better on the images after Histogram Equalization, I thought that might be a good input to add to ilastik.
Well, is it? (Since it is non-linear, it might give different results right?)
And if so, Is there an easy way to use the same labels I already drew for the equalized images?