Akihiro SUGIMOTO, Kazuo MUROTA
Recognition by Combinations of
Paraperspective Images
Abstract:This paper studies an object recognition problem under paraperspective projection, that
is, the problem of determining whether a given paraperspective image is obtained from a 3-D object to be recognized or not. It is found that any paraperspective image of an object
can be expressed as a linear combination of three appropriate paraperspective images of the
same object. We show that any image of an object with not only a rigid 3-D transformation
but also a nonrigid transformation has this property. In order to recognize a 3-D object, we
have only to store three paraperspective images and, whenever a new paraperspective image
is given, determine whether it can be expressed as a combination of the three images. This
implies that we no longer need to recover the 3-D information of an object explicitly under
paraperspective projection. Our investigation shows that three paraperspective images have
sufficient information to recognize a 3-D object.