Publication | Closed Access
Fractal-Based Description of Natural Scenes
1.8K
Citations
22
References
1984
Year
Scene AnalysisEngineering3D ModelingShape AnalysisNatural ImageryEarth ScienceNatural SurfacesImage AnalysisNatural ShapesComputational GeometryNatural ScenesGeometric ModelingMachine VisionGeographyComputer VisionScene InterpretationNatural SciencesRemote SensingTexture AnalysisShape ModelingFractal Analysis
Fractal functions effectively model 3‑D natural surfaces because many physical processes generate fractal shapes, fractals are widely used in graphics, and surveys show that a 3‑D fractal surface model, combined with image formation, accurately describes textured and shaded image regions. The paper aims to represent natural shapes such as mountains, trees, and clouds, and to compute their descriptions from image data by relating natural surfaces to their images. The authors employ a 3‑D fractal model that characterizes surfaces and their images, a verifiable and scale‑ and intensity‑stable representation. The 3‑D fractal model successfully performs texture segmentation and classification, estimates 3‑D shape information, and distinguishes perceptually smooth from textured surfaces.
This paper addresses the problems of 1) representing natural shapes such as mountains, trees, and clouds, and 2) computing their description from image data. To solve these problems, we must be able to relate natural surfaces to their images; this requires a good model of natural surface shapes. Fractal functions are a good choice for modeling 3-D natural surfaces because 1) many physical processes produce a fractal surface shape, 2) fractals are widely used as a graphics tool for generating natural-looking shapes, and 3) a survey of natural imagery has shown that the 3-D fractal surface model, transformed by the image formation process, furnishes an accurate description of both textured and shaded image regions. The 3-D fractal model provides a characterization of 3-D surfaces and their images for which the appropriateness of the model is verifiable. Furthermore, this characterization is stable over transformations of scale and linear transforms of intensity. The 3-D fractal model has been successfully applied to the problems of 1) texture segmentation and classification, 2) estimation of 3-D shape information, and 3) distinguishing between perceptually ``smooth'' and perceptually ``textured'' surfaces in the scene.
| Year | Citations | |
|---|---|---|
Page 1
Page 1