Symmetry Detection Based on Generalized Complex Moments

INVESTIGATORS

Dr. Horace H S Ip, Dr. Dinggang Shen, Mr. K T Cheung

Previous approaches to symmetry detection are usually suitable only for particular shapes or are time consuming. We exploit the phase angles of Generalized Complex moments to detect a few possible orientations of symmetric axes and verify them by a symmetric measure which can easily be computed.
Moreover, we extend the usefulness of symmetry by using a 3-class symmetry class. That is, we classify an object as symmetric, partial-symmetric and non-symmetric because we notice that there are many objects quite symmetric but not exactly.

N/A

1. D G Shen and Horace H S Ip, "Generalized Affine Invariant Image Normalization", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-19, No. 5, pp. 431-440, May 1997.
2. Kent K. T. Cheung and Horace H. S. Ip, "Symmetry Detection Using Complex Moments", Proc. 4th Intl. Conf. on Pattern Recognition, 16-20 Aug. 1998, Brisbane, Australia, vol. 2, pp. 1473-1475.
3. Horace H. S. Ip, Kent K. T. Cheung and Dinggang Shen, "Symmetry Detection for Binary Shapes based on Gneralized Complex Moments", Proc. of the 1998 Symposium on Image, Speech, Signal Processing and Robotics, 3-4 Sep. 1998, Hong Kong China, vol. 1, pp. I-237-I-240.
4. Dinggang Shen, Horace H. S. Ip, Kent K. T. Cheung and Eam Khwang Teoh, "Symmetry detection by generalized complex (GC) moments: a close-form solution", IEEE Trans. on PAMI, 22(5), 466-475(1999).
5. Dinggang Shen, Horace H S Ip, E K Teoh, "Robust Detection of Skewed Symmetries by Combining local and semi-local affine invariants", Pattern Recognition, Vol. 34, No.7, pp. 1417-1428, 2001.

Symmetry detection of non-symmetric figures

Symmetry detection of partial symmetric figures

Symmetry detection of symmetric figures