Abstract
Affine-invariant feature vector, which captures local and semi-local features, was used in the detection of skewed symmetries. Here, the problem of symmetry axes detection has been formulated as a line detection problem, with known orientations within a local similarity matrix computed for a shape. Moreover, our technique allows all the local reflection-symmetries within an object to be detected. Experiments on detecting skewed symmetries of self-symmetric objects and generalized objects, under noises and occlusions, have demonstrated the effectiveness of this method.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - International Conference on Pattern Recognition |
| Pages | 1010-1013 |
| Number of pages | 4 |
| Volume | 15 |
| Edition | 3 |
| Publication status | Published - 2000 |
| Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Computer Vision and Pattern Recognition
- Hardware and Architecture
Cite this
Robust detection of skewed symmetries. / Shen, Dinggang; Ip, Horace H S; Teoh, Eam Khwang.
Proceedings - International Conference on Pattern Recognition. Vol. 15 3. ed. 2000. p. 1010-1013.Research output: Chapter in Book/Report/Conference proceeding › Chapter
}
TY - CHAP
T1 - Robust detection of skewed symmetries
AU - Shen, Dinggang
AU - Ip, Horace H S
AU - Teoh, Eam Khwang
PY - 2000
Y1 - 2000
N2 - Affine-invariant feature vector, which captures local and semi-local features, was used in the detection of skewed symmetries. Here, the problem of symmetry axes detection has been formulated as a line detection problem, with known orientations within a local similarity matrix computed for a shape. Moreover, our technique allows all the local reflection-symmetries within an object to be detected. Experiments on detecting skewed symmetries of self-symmetric objects and generalized objects, under noises and occlusions, have demonstrated the effectiveness of this method.
AB - Affine-invariant feature vector, which captures local and semi-local features, was used in the detection of skewed symmetries. Here, the problem of symmetry axes detection has been formulated as a line detection problem, with known orientations within a local similarity matrix computed for a shape. Moreover, our technique allows all the local reflection-symmetries within an object to be detected. Experiments on detecting skewed symmetries of self-symmetric objects and generalized objects, under noises and occlusions, have demonstrated the effectiveness of this method.
UR - http://www.scopus.com/inward/record.url?scp=33745811529&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33745811529&partnerID=8YFLogxK
M3 - Chapter
AN - SCOPUS:33745811529
VL - 15
SP - 1010
EP - 1013
BT - Proceedings - International Conference on Pattern Recognition
ER -