Hi Philipp,
>From your description the "labelled" image sound like the mask image which
>indicate the ROI of the original image for training the NN.
Is this is the case, I think the labelled image must be going through the same
transform with the original image as well.
However, you
Dear Scilabers,
probably not the correct forum to ask this question, but i do not know
better.
Dealing with neural networks and image segmentation I write some Scilab
code for data augmentation.
This is to increase my training data set. ( = more images)
Data augmentation (for now) is done by:
Hi,
the 3rd argument was actually for an older version of imrotate which the
function is in pure Scilab script, however, it has not been used when we move
to opencv implementation.
please make a report here : https://github.com/tanchinluh/IPCV so that we could
put it into our future
Dear Experts,
using imrotate() from IPCV-toolbox:
imout = imrotate(im1,deg,crp)
crp : Returns only central portion output image which is the same size as
source if set to 1
My input image is 512x512 pixel.
The output image shall be of the same size.
For this I try crop = 1 and also crop = 0