A positional calibration is enabled between an imaging device and a stage structure including X and Y stages that move independently of each other. An image processing apparatus performs the positional calibration of a camera coordinate system for an imaging device with a stage coordinate system using a reference position in a first image coordinate space indicating a position of a mark in an image captured when an X-stage is at a reference position, a displaced position in the first image coordinate space indicating a position of the mark in an image captured when the X-stage is at a first displaced position to which the X-stage moves in X-direction from the first reference position, and a virtual position in the first image coordinate space indicating a position of the mark in an image calculated using the characteristic value of a Y-stage.