SOME ASPECTS OF PATTERN RECOGNITION BY COMPUTER.
Abstract
A computer may gather a lot of information from its environment in an optical or graphical manner, if a TV picture of a scene is transformed into a symbolic description of points and lines, or surfaces. This thesis describes several programs, written in the language CONVERT, for analyzing such descriptions in order to recognize, differentiate, and identify desired objects or classes of objects in a scene. Examples are given in each case. Important restrictions and suppositions are: (a) input is assumed perfect (noiseless) and in a symbolic format; (b) no perspective deformation is considered. A portion of this thesis is devoted to the study of models (symbolic representations) of the objects we want to identify, and different schemes, some of them already in use, are discussed. Focusing attention on the more general problem of identifying general objects when they substantially overlap, some schemes are proposed for such recognition, and some concurrent problems are analyzed. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 01, 1967
- Accession Number
- AD0656041
Entities
People
- Adolfo Guzman-arenas
Organizations
- Massachusetts Institute of Technology