Extraction of Textured Regions in Aerial Imagery,

Abstract

In lieu of a complete segmentation approach, the author attempts a partial segmentation for natural scenes to extract the large textured regions. The usefulness of texture processing as an early stage in the overall system, however, heavily depends on the nature of the task and the image data. Therefore, as mentioned in an earlier report, a way of determining the presence or absence of texture should precede any attempt to perform a texture extraction operation. A simple method to predict texture presence or absence using a pyramid structure is presented. A new texture measure is defined and used in a region-growing extraction scheme.

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1983
Accession Number
ADP001218

Entities

People

  • Hye Young Lee

Organizations

  • University of Southern California

Tags

DTIC Thesaurus Topics

  • Aerial Photography
  • Computer Vision
  • Extraction
  • Identification
  • Image Processing
  • Image Recognition
  • Recognition
  • Virginia
  • Workshops

Readers

  • Computer Vision.
  • Systems Analysis and Design