This invention makes it possible to properly detect a detection object region in an image. For this purpose, an image processing apparatus according to this invention includes an image input unit configured to input an object image and a reference image different in pixel value component type from the object image, a detection unit configured to detect a detection object candidate region from the object image, an extraction unit configured to extract at least one feature amount from the detection object candidate region by using at least the reference image, and a selection unit configured to select the detection object candidate region based on the feature amount.