Affine Invariant Pattern Recognition Using
Multi-Scale Autoconvolution
Esa Rahtu, Mikko Salo and Janne Heikkil
¨
a
Abstract
This article presents a new affine invariant image transform called Multi-Scale Au-
toconvolution (MSA). The proposed transform is based on a probabilistic interpretation
of the image function. The method is directly applicable to isolated objects and does
not require extraction of boundaries or interest points, and the computational load is
significantly reduced using the Fast Fourier Transform. The transform values can be
used as descriptors for affine invariant pattern classification, and in this article we
illustrate their performance in various object classification tasks. As shown by a com-
parison with other affine invariant techniques, the new method appears to be suitable
for problems where image distortions can be approximated with affine transformations.
Index Terms
Affine invariance, affine invariant features, pattern classification, target identifica-
tion, object recognition, image transforms.
E. Rahtu and J.Heikkil¨a are with the Machine Vision Group, Department of Electrical and Information Engineering, University
of Oulu. P.O. Box 4500, 90014 University of Oulu, Finland. E-mail: {erahtu,jth}@ee.oulu.fi
M. Salo is with the Rolf Nevanlinna Institute, Department of Mathemathics and Statistics, University of Helsinki. P.O. Box
68, 00014 University of Helsinki, Finland. E-mail: msa@rni.helsinki.fi