When heuristic problem-solving programs are faced with large data bases that contain numbers of facts far in excess of those needed to solve any particular problem, their performance rapidly deteriorates.
To have a general-purpose machine vision capability, we must be able to recognize things; we argue that most natural objects have a part structure that we can recover from image data and thus use as the basis for "general-purpose" recognition.
Interpolating smooth surfaces from boundary conditions is a ubiquitous problem in early visual processing. We describe a solution for an important special case: the interpolation of surfaces that are locally spherical or cylindrical from initial orientation values and constraints on orientation.
We suggest that an appropriate role of early visual processing is to describe a scene in terms of intrinsic (vertical) characteristics?such as range, orientation, reflectance, and incident illumination?of the surface element visible at each point in the image.
This paper deals with a specific approach to the problem of reference that I call the descriptive model. In particular, I am going to examine some relations between this model and a certain distinction between referential and attributive uses of definite descriptions.
In this paper, we present a method for registering images of complex 3-D surfaces that does not require explicit correspondences between features across the images.
Stereo matching using a Lisp Machine implementation of the Baker stereo system developed at Stanford University. The processing is one of edge matching in a hierarchy of long to short image contours, finishing with interedge intensity correlation to yield a dense map of scene disparities.
We are only in the initial stages of our understanding of what Self-Aware Computer Systems means: what it means to be self-aware, what a self-aware system can do that other systems cannot do, and what are some of the immediate practical applications and challenge problems.
