A Study of Texture Classification Using Spectral Features

Abstract

Prior spectral feature study was not successful because of inaccuracy in 2-D spectral estimation. In this report, a generalization of Lim-Malik method is used to accurately estimate the ring and wedge spectral features for classification of textural images with a typical performance of over 80 percent correct classification for six texture classes. The results compare favorably with other texture features but require less computation using iterative algorithm. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 04, 1982
Accession Number
ADA109408

Entities

People

  • Chia‐Hung Chen
  • Gia-kinh Young

Organizations

  • University of Massachusetts Dartmouth

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Autocorrelation
  • Classification
  • Computations
  • Databases
  • Directional
  • Discrete Fourier Transforms
  • Electrical Engineering
  • Engineering
  • Feature Selection
  • Frequency
  • Information Science
  • Military Research
  • Power Spectra
  • Spectra
  • Two Dimensional

Readers

  • Computer Vision.
  • Spectroscopy.