Visual pattern recognition by moment invariants Export

@article{citeulike:893635, 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.}, author = {Hu, Ming-Kuei}, citeulike-article-id = {893635}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/TIT.1962.1057692}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1057692}, doi = {10.1109/TIT.1962.1057692}, journal = {Information Theory, IEEE Transactions on}, keywords = {geometric, invariants, moments, pattern, recognition}, number = {2}, pages = {179--187}, posted-at = {2007-04-26 11:41:15}, priority = {5}, title = {Visual pattern recognition by moment invariants}, url = {http://dx.doi.org/10.1109/TIT.1962.1057692}, volume = {8}, year = {1962} }

TY - JOUR ID - citeulike:893635 L3 - citeulike-article-id:893635 N2 - 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. IS - 2 JF - Information Theory, IEEE Transactions on EP - 187 TI - Visual pattern recognition by moment invariants VL - 8 SP - 179 KW - geometric KW - invariants KW - moments KW - pattern KW - recognition AU - Hu, Ming-Kuei PY - 1962/// UR - http://dx.doi.org/10.1109/TIT.1962.1057692 ER -