An image processing apparatus comprises a detecting unit which detects an object from an input image, an extracting unit which extracts a feature amount of the object detected by the detecting unit, a similarity calculating unit which, in a case where a plurality of objects have been detected from the same input image by the detecting unit, calculates a degree of similarity of feature amounts of the plurality of objects, and an adjusting unit which adjusts a collating method of collating the plurality of objects based on respective feature amounts, on the basis of the degree of similarity calculated by the similarity calculating unit.