Segmentation of FLIR Images by Pixel Classification

Abstract

Image segmentation can be treated as a point-wise classification problem. This classification may be done by measuring a set of features at each point and defining a decision surface in the feature space. This report presents some experiments in segmenting FLIR images by using the gray level and the edge value at each point as features.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 1977
Accession Number
ADA045334

Entities

People

  • Durga P. Panda

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Applied Computer Science
  • Artificial Intelligence
  • Boundaries
  • Buildings And Structures
  • Classification
  • Computer Science
  • Computer Vision
  • Computing-Related Activities
  • Databases
  • Gray Scale
  • Histograms
  • Image Segmentation
  • Night Vision
  • Normal Distribution
  • Segmented
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Image Processing and Computer Vision.
  • Theoretical Analysis.

Technology Areas

  • Space