Pattern Recognition, International Conference on (2006)
Aug. 20, 2006 to Aug. 24, 2006
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICPR.2006.599
Esa Rahtu , Univ. of Oulu, Finland
Mikko Salo , Univ. of Oulu, Finland
Janne Heikkil , Univ. of Oulu, Finland
Jan Flusser , Academy of Sciences of the Czech Republic, Prague 8, Czech Republic
This paper introduces a new way of extracting affine invariant features from image functions. The presented approach is based on combining affine moment invariants (AMI) with multiscale invariants, in particular multiscale autoconvolution (MSA) and spatial multiscale affine invariants (SMA). Our approach includes all of these invariants as special cases, but also makes it possible to construct new ones. According to the performed experiments the introduced features provide discriminating information for affine invariant object classification, clearly outperforming standard AMI, MSA, and SMA.
J. Heikkil, E. Rahtu, M. Salo and J. Flusser, "Generalized affine moment invariants for object recogn," 2006 18th International Conference on Pattern Recognition(ICPR), Hong Kong, 2006, pp. 634-637.