An Optical Image Segmentor Using Neural Based Wavelet Filtering Techniques

Abstract

This paper presents a neural based optical image segmentation scheme for locating potential targets in cluttered FLIR images. The advantage of such a scheme is speed, i.e., the speed of light. Such a design is critical to achieve real-time segmentation and classification for machine vision applications. The segmentation scheme used was based on texture discrimination and employed biologically based orientation specific filters (wavelet filters) as its amin component. These filters are well understood impulse response functions of mammalian vision systems from input to striate cortex. By usig the proper choice of aperture pair separation, dilation, and orientation, targets in FLIR imagery were optically segmented. Wavelet filtering is illustrated for glass template slides, as well as segmentation for static and real-time FLIR imagery displayed on a liquid crystal television.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 18, 1991
Accession Number
ADA242196

Entities

People

  • Christopher P. Veronin
  • Kevin L. Priddy
  • Kevin W. Ayer
  • Matthew Kabrisky
  • Steven K. Rogers

Organizations

  • Wright Laboratory

Tags

Communities of Interest

  • Air Platforms
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Classification
  • Computer Vision
  • Dimensionality Reduction
  • Discrimination
  • Electro-Optics
  • Filtration
  • Image Processing
  • Image Segmentation
  • Images
  • Neural Networks
  • Optical Images
  • Pattern Recognition
  • Recognition
  • Signal Processing
  • Two Dimensional
  • Video

Readers

  • Computer Vision.
  • Neuroscience