The Optimal Construction of Synthetic Discriminant Functions (SDF'S).
Abstract
Synthetic discriminant functions (SDF's) for optical matched filters have potential use for pattern recognition. Several digital computer programs were written to compute SDF's, subject to certain constraints, and to compare the resulting SDF's to each other. For example, one of the programs chooses the four best from 36 tank images and manufactures an SDF from them. A guiding principle throughout this work was that objective numerical criteria be applied to determine what is a good or optimal SDF. There are many interesting and important questions which remain to be investigated in this area of research. They are discussed in this report.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 1986
- Accession Number
- ADA168301
Entities
People
- Robert R. Kallman
Organizations
- University of North Texas