2

I know that the adaptive thresholding function and its parameters are given below:

cv2.adaptiveThreshold(src, maxValue, adaptiveMethod, thresholdType, blockSize, C)

And I understand in the documentation it says:

C – Constant subtracted from the mean or weighted mean (see the details below). 
    Normally, it is positive but may be zero or negative as well.

I vaguely get the idea that this C is to determine where to set the threshold relative to the neighbourhood mean. My question is: Why not use the mean value directly? Why subtract a constant? What does this subtraction operation stand for mathematically? Could anyone please briefly explain it or guide me where can I find related materials to dive deeper? Thanks!

Anthony
  • 43
  • 4
  • When the image has noise, use the mean value as threshold usually can't remove all the noise. The **C** value here can adjust the threshold to cover the noise value range. – VictorBian Oct 05 '21 at 02:25

0 Answers0