Differential geometric techniques for invariant feature set representation

Scott D. Brown; Richard L. Tutwiler

doi:10.1117/12.251789

30 September 1996 Differential geometric techniques for invariant feature set representation

Scott D. Brown, Richard L. Tutwiler

Proceedings Volume 2826, Vision Geometry V; (1996) https://doi.org/10.1117/12.251789
Event: SPIE's 1996 International Symposium on Optical Science, Engineering, and Instrumentation, 1996, Denver, CO, United States

Abstract

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.

Citation Download Citation

Scott D. Brown and Richard L. Tutwiler "Differential geometric techniques for invariant feature set representation", Proc. SPIE 2826, Vision Geometry V, (30 September 1996); https://doi.org/10.1117/12.251789

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available