global threshold

One fixed cutoff T applied to every pixel in an image, foreground below it and background above it.

A global threshold classifies every pixel by the same rule, $g(x,y) = 255$ if $f(x,y)\le T$ else $0$ , for one fixed $T$ shared across the whole image. Cheap and effective when the image's true foreground and background occupy genuinely separate intensity bands everywhere -- and the first thing to fail once lighting varies across the frame (adaptive/local thresholding's own motivation).