Classification of Cartographic Features through Walsh Transforms.
Abstract
An Algorithm was used to classify and recognize a set of selected cartographic features, such as road intersections, straight-line roads, and rectangular objects, which were decomposed in the Walsh transform domain. The method was implemented digitally with an experimental system consisting of a solid state sensor array, a minicomputer as signal processor, and a computer-controlled translational stage as the image holder. Recognition examples for the set of cartographic features with respect to the window of inspection are presented. Nearly 90 percent recognition accuracy was obtained for the selected set of the cartographic features. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 1982
- Accession Number
- ADA116731
Entities
People
- Frederick W. Rohde
- Pi-fuay Chen
- William W. Seemuller
Organizations
- Geospatial Research Laboratory