Share Email Print

Proceedings Paper

3-D Rotation And Scale Invariant Object Recognition From Multiple Views
Author(s): Rong-Hwang Wu; Henry Stark
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Rotation invariant recognition of two-dimensional objects (e.g., images) can be done robustly using circular harmonic function (CHF) expansion coefficients.1-4 Scale (size) invariant recognition can be done using Mellin transforms.5 The two activities together can be combined into a single algorithm that efficiently enables scale and rotation invariant recognition. Such algorithms, whether based on CHF's or other methods, are described in the literature.6-7 The method used by the authors involves computing the Mellin transform of the CHF coefficients, generating an appropriate feature vector based on these objects, and comparing these vectors with a reference. If the test feature vector is near enough the reference then a match is declared. The procedure seems to be quite robust.

Paper Details

Date Published: 1 January 1987
PDF: 2 pages
Proc. SPIE 0813, Optics and the Information Age, (1 January 1987); doi: 10.1117/12.967305
Show Author Affiliations
Rong-Hwang Wu, Rensselaer Polytechnic Institute (United States)
Henry Stark, Rensselaer Polytechnic Institute (United States)

Published in SPIE Proceedings Vol. 0813:
Optics and the Information Age

© SPIE. Terms of Use
Back to Top