Thresholding and Binarization

← Back to Digital Image Processing Basics

Thresholding converts a grayscale image to binary:

\[\begin{split}g(x, y) = \begin{cases} 1 & \text{if } f(x,y) \geq T \\ 0 & \text{otherwise} \end{cases}\end{split}\]

• Global (Otsu’s method): automatically finds \(T\) by maximizing inter-class variance.

• Adaptive thresholding: computes \(T\) locally in each region, handling non-uniform illumination.

See also

• Edge Detection — a common input to thresholding

• Morphological Operations — cleaning up a mask after thresholding

• Otsu Multi-Threshold — Otsu extended to more than two classes

• Binarization and Thresholding — thresholding applied as a concrete preprocessing step

• Digital Image Processing Basics — every other basics topic