An image processing system includes an imaging unit for imaging an outside world to generate a captured image, a position and orientation estimation unit for estimating a position and orientation of the imaging unit, a feature point estimation unit for estimating a position of a feature point in the captured image, a clipping unit for clipping an image for combining, and clipping an image for feature detection, a measurement unit for detecting a feature point from the image for feature detection, and measuring a position and orientation of the imaging unit, a generation unit for generating a CG image based on the position and orientation measured by the measurement unit, a combining unit for combining the image clipped by the clipping unit with the CG image, and a display control unit for displaying the image combined by the combining unit on a display unit.