Applies Niblack thresholding to input image

dst = cv.niBlackThreshold(src, delta)
dst = cv.niBlackThreshold(src, delta, 'OptionName',optionValue, ...)

Input

• src Source 8-bit single-channel image.
• delta Constant multiplied with the standard deviation and subtracted from the mean (mean + k * std). Normally, it is taken to be a real number between 0 and 1.

Output

• dst Destination image of the same size and the same type as src.

Options

• MaxValue Non-zero value assigned to the pixels for which the condition is satisfied, used with the Binary and BinaryInv thresholding types. default 255
• Type Thresholding type, default 'Binary'. One of:
  • Binary dst(x,y) = (src(x,y) > thresh) ? maxValue : 0
  • BinaryInv dst(x,y) = (src(x,y) > thresh) ? 0 : maxValue
• BlockSize Size of a pixel neighborhood that is used to calculate a threshold value for the pixel: 3, 5, 7, and so on. default 5

The function transforms a grayscale image to a binary image according to the formulae:

• Binary

  | maxValue, if src(x,y) > T(x,y) dst(x,y) = | | 0, otherwise

• BinaryInv

  | 0, if src(x,y) > T(x,y) dst(x,y) = | | maxValue, otherwise

where T(x,y) is a threshold calculated individually for each pixel.

The threshold value T(x,y) is the mean minus delta times standard deviation of BlockSize x BlockSize neighborhood of (x,y).