Issue No. 08 - August (1998 vol. 20)

ISSN: 0162-8828

pp: 819-831

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.709598

ABSTRACT

<p><b>Abstract</b>—The proof of the generalized fundamental theorem of moment invariants (GFTMI) [<ref rid="bibi08191" type="bib">1</ref>] is presented for <it>n</it>-dimensional pattern recognition. In 1962, Hu [<ref rid="bibi08192" type="bib">2</ref>] formulated the fundamental theorem of moment invariants (FTMI) for two-dimensional pattern recognition, that is subjected to general linear transformation. In 1970, I showed that the FTMI was in fact incorrect, and the corrected FTMI (CFTMI) was formulated [<ref rid="bibi08193" type="bib">3</ref>], which was generalized by us for <it>n</it>-dimensional case in 1974 [<ref rid="bibi08191" type="bib">1</ref>] without proof. On the basis of GFTMI, the moment invariants of affine transformation and subgroups of affine transformation are constructed. Using these invariants, the conceptual mathematical theory of recognition of geometric figures, solids, and their <it>n</it>-dimensional generalizations is worked out. By means of this theory, it is possible for the first time to analyze scenes consisting not only of polygons and polyhedra, as so far, but also scenes consisting of geometric figures and solids with curved contours and surfaces, respectively. In general, it is the author's opinion that this theory is a useful step toward the essential development of robot vision and toward creating machine intelligence—to make machines able to think by means of geometric concepts of different generalities and dimensions, and by associations of these concepts.</p>

INDEX TERMS

n-ary quantics, algebraic invariants, affine transformation, n-dimensional moments, moment invariants, geometric concepts, n-dimensional solids, metric characteristics, affine classification.

CITATION

Alexander G. Mamistvalov, "n-Dimensional Moment Invariants and Conceptual Mathematical Theory of Recognition n-Dimensional Solids",

*IEEE Transactions on Pattern Analysis & Machine Intelligence*, vol. 20, no. , pp. 819-831, August 1998, doi:10.1109/34.709598