Visual pattern recognition by moment invariants. Hu, M. IRE Transactions on Information Theory, 8(2):179–187, February, 1962. Conference Name: IRE Transactions on Information Theory
doi  abstract   bibtex   
In this paper a theory of two-dimensional moment invariants for planar geometric figures is presented. A fundamental theorem is established to relate such moment invariants to the well-known algebraic invariants. Complete systems of moment invariants under translation, similitude and orthogonal transformations are derived. Some moment invariants under general two-dimensional linear transformations are also included. Both theoretical formulation and practical models of visual pattern recognition based upon these moment invariants are discussed. A simple simulation program together with its performance are also presented. It is shown that recognition of geometrical patterns and alphabetical characters independently of position, size and orientation can be accomplished. It is also indicated that generalization is possible to include invariance with parallel projection.
@article{hu_visual_1962,
	title = {Visual pattern recognition by moment invariants},
	volume = {8},
	issn = {2168-2712},
	doi = {10.1109/TIT.1962.1057692},
	abstract = {In this paper a theory of two-dimensional moment invariants for planar geometric figures is presented. A fundamental theorem is established to relate such moment invariants to the well-known algebraic invariants. Complete systems of moment invariants under translation, similitude and orthogonal transformations are derived. Some moment invariants under general two-dimensional linear transformations are also included. Both theoretical formulation and practical models of visual pattern recognition based upon these moment invariants are discussed. A simple simulation program together with its performance are also presented. It is shown that recognition of geometrical patterns and alphabetical characters independently of position, size and orientation can be accomplished. It is also indicated that generalization is possible to include invariance with parallel projection.},
	number = {2},
	journal = {IRE Transactions on Information Theory},
	author = {Hu, Ming-Kuei},
	month = feb,
	year = {1962},
	note = {Conference Name: IRE Transactions on Information Theory},
	keywords = {Artificial intelligence, Bibliographies, Character recognition, Decision theory, Distribution functions, Information theory, Pattern recognition, Senior members, Shape},
	pages = {179--187},
}

Downloads: 0