An image processing apparatus acquires an image including an object and divides the image into a plurality of superpixels based on similarity of adjacent pixels. There is an acquisition, from the superpixels, of a plurality of candidate areas acting as candidates of an area of the object. A feature quantity is extracted from each of the plurality of candidate areas and checked against registered information concerning a feature quantity of object area. The area of the object in the image is output, based on a checked result.