Texture-Tone Study with Application to Digitized Imagery.

Abstract

An image data set of 54 scenes was obtained from 1/8 inch by 1/8 inch areas on a set of 1:20000 scale photography. The scenes, which consisted of 6 samples from each of the nine categories scrub, orchard, heavily wooded, urban, suburban, lake, swamp, marsh, and railroad yard, were analyzed manually and automatically. For the automatic analysis, a set of features measuring the spatial dependence of the grey tones of neighboring resolution cells was defined. On the basis of these features and a simple decision rule, which assumed that the features were independent and uniformly distributed, an identification accuracy of 70% was achieved by training on 53 samples and assigning an identification to the 54th sample and repeating the experiment 54 times. (Author)

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 1971
Accession Number
AD0737722

Entities

People

  • Delmar E. Anderson
  • Robert M. Haralick

Organizations

  • University of Kansas

Tags

DTIC Thesaurus Topics

  • Accuracy
  • Automatic
  • Cameras
  • Data Sets
  • Identification
  • Images
  • Optical Equipment
  • Photographic Equipment
  • Photographic Images
  • Photographic Materials
  • Photographic Recording Media
  • Photographs
  • Photography
  • Railroads
  • Training

Readers

  • Computer Vision.
  • Regression Analysis.
  • Wetland-Land-Environmental Management.