0 notes

RGB normalization
from top: original, red-normalized, rgb-normalized

pixel = [R G B] //each pixel is represented by 3 numbers in 0-255 range
sum = R+G+B
rgb_normalized_pixel = [ R*255/sum G*255/sum B*255/sum ]
red_normalized_pixel = [ R*255/sum G B ]

Amaze! Here’s the code.

I think this is a neat thing and surprisingly easy to do. Helps to ignore shadows if you are doing color-based object detection :)))

Filed under water lily image processing computer vision simplecv numpy no idea why I did this