Three-dimensional object recognition by combination of perspective images

ABSTRACT This paper studies an object recognition problem, that is, the problem of determining whether a given perspectiveimage is obtained from a 3-D object to be recognized or not. As an extension of Uliman and Basri's approach, it isfound that any perspective image of an object can be expressed as a certain type of nonlinear combination of fourappropriate perspective 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 four perspective images and, whenever a new perspective image is given, determine whether it can beexpressed as a combination of the four images. This implies that we no longer need to recover the 3-D information ofan object explicitly under perspective projection. Our investigation shows that four perspective images have sufficientinformation to recognize a 3-D object. 1 INTRODUCTION It is thought that the human mechanism of recognizing an object through visual information is divided into twoprocedures: To recover 3-D physical information of an object from visual 2-D information, and to construct the 3-Dmodel of the object. This approach is based on the assumption that human beings always recover the 3-D informationin order to recognize an object. However, it is reported by some psychologists that human beings do not necessarily