An object in a target image to be combined with a combination region of a template image is determined. A plurality of extraction regions which include the determined object and have a shape similar to the shape of the combination region are defined. Among extraction images in the extraction regions, the extraction region in which the similarity between the impression of the template image and the impression of the extraction image is equal to or greater than a threshold value is determined. The extraction image in the determined extraction region is combined with the combination region of the template image.