Perception of depth is a central problem in machine vision. Stereo is an attractive technique for depth perception because, compared to monocular techniques, it leads to more direct, unambiguous, and quantitative depth measurements.
This note discusses the adequacy of current computer architectures to serve as a base for building machine vision systems. Arguments are presented to show that perceptual problems cannot be completely formalized and dealt with in a closed abstract system.
This paper presents some programming facilities for modeling the semantics of a task domain and for describing the situations that occur in that domain as a task is being carried out.
In an effort to apply pattern-classification and scene-analysis techniques to medical problems, the Artificial Intelligence Center has digitized and processed a series of breast thermograms of positive patients.
R. Schrag, M. Pool, Vinay K. Chaudhri, R.C. Kahlert, J. Powers, Philip R. Cohen, J. Fitzgerald, & S. Mishra
We describe a large-scale experiment in which non-artificial intelligence subject matter experts - with neither artificial intelligence background nor extensive training in the task - author knowledge bases following a challenge problem specification with a strong question-answering component.
S. Houzelle, T.M. Strat, Pascal V. Fua, & M.A. Fischler
Two of the problems that the user of an image understanding system must continuously face are the choice of an appropriate algorithm and the setting of its associated parameters.
J.M. Tenenbaum, H.G. Barrow, Robert C. Bolles , M.A. Fischler, & H.C. Wolf
A map-guided approach to interpretation of remotely sensed imagery is described, with emphasis on applications involving continuous monitoring of predetermined ground sites.
This paper describes the results obtained in a research program ultimately concerned with deriving a physical sketch of a scene from one or more images.
