The variations in appearance of an object caused by the variations in a capturing
environment are estimated to be modeled, and the object model thus obtained is
previously registered in a database. Picture information of an object to be a recognition
target is input, and the input picture information is matched with the previously
registered object model. The similarity with respect to the registered object model
is determined, and the type of the object to be a recognition target is output,
which is determined to be most similar among the registered object models. Information
of a plurality of pictures captured by changing the relative position and posture
of an object is input, and the variations in appearance of an object caused by
the possible variations in a capturing environment are estimated to be modeled
based on the input information of a plurality of pictures.
