Share Email Print

Proceedings Paper

Gaussian kernels for affine-invariant iconic representation and object recognition by multidimensional indexing
Author(s): Jezekiel Ben-Arie; Zhiqian Wang; Raghunath K. Rao
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper describes an approach for affine-invariant object recognition by iconic recognition of image patches that correspond to object surfaces that are roughly planar. Each surface is recognized separately invariant to its 3D pose, employing novel affine-invariant spectral signatures (AISSs). The 3D-pose invariant recognition is achieved by convolving the image with a novel configuration of Gaussian kernels and extracting local spectral signatures. The local spectral signature of each image patch is then matched against a set of iconic models using multi-dimensional indexing (MDI) in the frequency domain. Affine-invariance of the signatures is achieved by a new configuration of Gaussian kernels with modulation in two orthogonal axes. The proposed configuration of kernels is Cartesian with varying aspect ratios in two orthogonal directions. The kernels are organized in subsets where each subset has a distinct orientation. Each subset spans the entire frequency domain and provides invariance to slant, scale and limited translation. The union of differently oriented subsets is utilized to achieve invariance in two additional degrees of freedom, i.e. rotation and tilt. Hence, complete affine-invariance is achieved by the proposed set of kernels. The indexing method provides robustness in partial distortion, background clutter, noise, illumination effects and lower image resolution. The localized nature of the Gaussian kernels allows independent recognition of adjacent shapes that correspond to object parts which could have different poses. The method has yielded high recognition rates in experiments over a wide range of slant, scale, rotation, and tilt with a library of 26 gray-level and infra-red models, in the presence of noise, clutter and other degradations.

Paper Details

Date Published: 27 February 1996
PDF: 12 pages
Proc. SPIE 2727, Visual Communications and Image Processing '96, (27 February 1996); doi: 10.1117/12.233228
Show Author Affiliations
Jezekiel Ben-Arie, Univ. of Illinois/Chicago (United States)
Zhiqian Wang, Illinois Institute of Technology (United States)
Raghunath K. Rao, Illinois Institute of Technology (United States)

Published in SPIE Proceedings Vol. 2727:
Visual Communications and Image Processing '96
Rashid Ansari; Mark J. T. Smith, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?