Concept
Bounding-box
A bounding-box is the smallest axis-aligned rectangle that fully encloses an object or region of interest in an image or document page. It is the standard spatial primitive in computer vision, used to say "the thing is here" without segmenting its exact outline.
The rest of “Bounding-box” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→