Representation and Three-Dimensional Interpretation of Image Texture: An Integrated Approach

Abstract

A perspective view of a slanted textured surface shows systematic changes in density, area and aspect-ratio of texture elements. The apparent changes in texture element properties can be analyzed to recover information about the physical layout of the scene. In practice it is difficult to identify texture elements, especially in images where the texture elements are partially occluded or are themselves textured at a finer scale. To solve this problem, it is necessary to integrate the extraction of texture elements with the recognition of scene layout. This paper presents a method for recovering the orientation of textured surfaces while simultaneously identifying texture elements. Candidate texture elements are constructed from overlapping circular regions of relatively uniform gray level. The uniform circular regions are found by convolving the image with Del sq G (Laplacian-of-Gaussian) masks over a range of scales, and comparing the convolution output to that expected for a circular disk of constant gray level. True texture elements are selected from the set of candidate texture elements by finding the planar surface that best predicts the properties of the candidate texture elements. A planar fit is evaluated by comparing the predicted texture-element areas to the actual areas of the candidate texture elements. The planar fit receiving support from the most regions is chosen as the correct interpretation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 1987
Accession Number
ADA182866

Entities

People

  • Dorothea Blostein
  • Narendra Ahuja

Organizations

  • University of Illinois Urbana–Champaign

Tags

Communities of Interest

  • Air Platforms

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Aspect Ratio
  • Birds
  • Change Detection
  • Computer Vision
  • Detectors
  • Geometry
  • Identification
  • Image Processing
  • Notation
  • Orientation (Direction)
  • Pattern Recognition
  • Psychology
  • Recognition
  • Shape
  • Three Dimensional
  • Two Dimensional

Readers

  • Computer Vision.
  • Finite Element Method (FEM) for solving Partial Differential Equations (PDEs)