is there any works to speed up the code ?

[alexliyang]

I try this on some color document image, and the output is not good.
then I split the image to 3 channels and do three times, the output is good ,but the time is to long? any idea to speed up it?

[seungjun45]

Thank you for your interest.

I think you can boost the speed by simple parallel processing
(parallel processing for r,g,b channels)

in the algorithmic aspect, I don't have a good suggestion, :)

[alexliyang]

：） another question: how to keep the unshadowed area color unchanged after shadow removing, when I remove the shadow, other area colors will be changed.

[seungjun45]

Keep R,G,B ratio to be same before and after deshadowing.

[alexliyang]

excuse me, I donnot know this mean? how to keep R/G/B ration?

[seungjun45]

@alexliyang> excuse me, I donnot know this mean? how to keep R/G/B ration?

something like YCbCr? (e.g., Blue : Red ratio & Green : Red ratio)