Translator Disclaimer
30 September 1996 Differential geometric techniques for invariant feature set representation
Author Affiliations +
The analysis of simple elliptical image structures is accomplished by casting the image as a 3D surface so that the mathematics of surface analysis can be explained. Segmentation is performed by computing surface characteristics using differential geometry and classifying image regions based on local surface measures. The segmented image regions are classified by fitting a generalized conic section to the region boundary. A least squares method minimizes the total error between the segmented image and the ideal conic. Further image manipulations force this conic to be an ellipse for this application. The image analysis paradigm is tested with bubble images where each bubble region is assumed to have an elliptical shape.
© (1996) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Scott D. Brown and Richard L. Tutwiler "Differential geometric techniques for invariant feature set representation", Proc. SPIE 2826, Vision Geometry V, (30 September 1996);

Back to Top