… A general-purpose computer vision system must be capable of recognizing threedimensional
(3-D) objects. This paper proposes a precise definition of the 3-D object recognition …

… Visual object recognition is complicated by the fact that the same 3D object can give rise
to a large variety of projected images that depend on the viewing conditions, such as viewing …

… information from the two-dimensional visual input. An … the recognition of three-dimensional
objects can most easily be carried out by matching against reconstructed three-dimensional …

… images of objects are encoded in a viewpoint-specific manner 12 and that object recognition
… Objects seen from viewpoints increasingly different from learned views will tend to project …

This paper describes an approach to the recognition of stacked objects with planar and
curved surfaces. The system works in two phases. In the learning phase, a scene containing a …

… object recognition methodologies. This paper provides a complete study of 3D object
recognition … methods and different techniques of pattern recognition. We have tried to summarize …

… recognition of three -dimensional objects. This paper describes a modeling scheme which
facilitates the recognition of arbitrarily positioned objects … hold the object in a known manner. …

… Our results raise physiological implications for the neural basis of object recognition. Suppose
that training to a particular view of a three-dimensional object creates a group of neurons …

… of a 3-D object can be matched by combinations of a small number of 2-D images. In this
section, I consider briefly how this property may be used in a process for 3-D object recognition. …

… 3-D object recognition algorithms on the Connection Machine and hypercube computers.
The book consists of three … vision, and 3-D object recognition in particular. The terminology is …