Accession Number : ADA139037

Title :   Machine Vision: Three Generations of Commercial Systems.

Descriptive Note : Interim rept.,

Corporate Author : CARNEGIE-MELLON UNIV PITTSBURGH PA ROBOTICS INST

Personal Author(s) : Crowley,J L

PDF Url : ADA139037

Report Date : 25 Jan 1984

Pagination or Media Count : 40

Abstract : Since 1980, machine vision systems for industrial application have enjoyed a rapidly expanding market. The first generation machines are two-dimensional binary vision systems, patterned after the SRI Vision Module. These systems will soon be joined by a second generation, based on edges description techniques. Both the first and second generation systems are pattern recognition machines. Research in machine vision is leading towards vision systems that will be able to dynamically model the three-dimensional (3-D) surfaces in a scene. This research will lead to a third generation of vision systems which will provide a dramatic increase in capabilities over the first two generations. This article describes these three generations of vision systems. The algorithms, data structures, and hardware architecture are presented for binary vision systems and edge-based systems. A framework is presented for the research problems which must be solved before a commercial vision system can be produced based on dynamic 3-D Scene analysis techniques. (Author)

Descriptors :   *Pattern recognition, *Machines, *Vision, *Computer applications, Data bases, Computer architecture, Edges, Two dimensional, Three dimensional, Surfaces, Images

Subject Categories : Computer Hardware
      Bionics

Distribution Statement : APPROVED FOR PUBLIC RELEASE