A framework for segmentation using physical models of image formation
- 1 January 1994
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 361-368
- https://doi.org/10.1109/cvpr.1994.323852
Abstract
This paper presents a new approach to segmentation using explicit hypotheses about the physics that creates images. We propose an initial segmentation that identifies image regions exhibiting constant color; but possibly varying intensity. For each region, we propose a set of hypotheses, each of which specifically models the illumination, reflectance, and shape of the 3-D patch which caused that region. Each hypothesis represents a distinct, plausible explanation for the color and intensity variation of that patch. Hypotheses for adjacent patches can be compared for similarity and merged when appropriate, resulting in more global hypotheses which group elementary regions.Keywords
This publication has 7 references indexed in Scilit:
- Segmentation by minimal descriptionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Segmenting textured 3D surfaces using the space/frequency representationSpatial Vision, 1994
- A comprehensive physical model for light reflectionPublished by Association for Computing Machinery (ACM) ,1991
- A physical approach to color image understandingInternational Journal of Computer Vision, 1990
- Using color for geometry-insensitive segmentationJournal of the Optical Society of America A, 1989
- Method for computing the scene-illuminant chromaticity from specular highlightsJournal of the Optical Society of America A, 1986
- Using color to separate reflection componentsColor Research & Application, 1985