The accuracy of estimating the category of an object in an image and its region is improved. The present invention detects as to whether each of a plural types of objects is included in an object image, forms a plurality of local regions in a region including the object detected, and calculates a feature quantity of the plurality of local regions formed. Furthermore, the present invention selects a discriminant criterion adapted to the type of the object detected, from a plurality of discriminant criteria for discriminating the plural types of objects, and determines, based on the discriminant criterion selected and the feature quantity calculated, a region of the object detected from the plurality of local regions.