This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
That is because HOG is a gradient based approach on grayscale images, thus other colours do not influence the gradients. Machine learning is basically what you see is what you get, so if the model never saw scrambled backgrounds, then it will not know what to do with it. Providing transparacy in machine learning does not work, because we are running a pixel based evaluation....
