Accession Number : ADA258277


Title :   A Mathematical Framework for Image Analysis


Descriptive Note : Final technical rept.


Corporate Author : BROWN UNIV PROVIDENCE RI DIV OF APPLIED MATHEMATICS


Personal Author(s) : Geman, Donald ; Geman, Stuart ; Gidas, Basilis ; Grenander, Ulf ; McClure, Donald E


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a258277.pdf


Report Date : Aug 1991


Pagination or Media Count : 55


Abstract : The results reported here were derived from the research project 'A Mathematical Framework for Image Analysis' supported by the Office of Naval Research, contract N00014-88-K-0289 to Brown University. A common theme for the work reported is the use of probabilistic methods for problems in image analysis and image reconstruction. Five areas of research are described: rigid body recognition using a decision tree/combinatorial approach; nonrigid body recognition using deformable templates; the construction of two and three dimensional shape models for complex recognition and interpretation tasks; three dimensional shape reconstruction; and texture analysis.


Descriptors :   *MATHEMATICAL MODELS , *IMAGES , *MAN COMPUTER INTERFACE , *DECISION AIDS , MODELS , PROBABILITY , NAVAL RESEARCH , BODIES , TEXTURE , RECOGNITION , TEMPLATES , SHAPE , THREE DIMENSIONAL


Subject Categories : Numerical Mathematics
      Statistics and Probability


Distribution Statement : APPROVED FOR PUBLIC RELEASE