In this paper, we propose a descriptor as a shape signature and the projective refinement as a verification method for recognizing 2D curved objects with occlusions from their partial views. For an extracted curve segment, we compute a series of the geometric invariance of equally spaced five co-planar points on the curve. Thus the resulting descriptor is invariant only under rotation, translation, and scale, but sufficient similarity is preserved even under large distortions. It is more stable and robust since it does not need derivatives. We use this transformation-invariant descriptor to index a hash table. We show the efficiency of the method through experiments using seriously distorted images of 2-D curved objects with occlusions.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Kyoung Sig ROH, In So KWEON, "2-D Curved Shape Recognition Using a Local Curve Descriptor and Projective Refinement" in IEICE TRANSACTIONS on Information,
vol. E81-D, no. 5, pp. 441-447, May 1998, doi: .
Abstract: In this paper, we propose a descriptor as a shape signature and the projective refinement as a verification method for recognizing 2D curved objects with occlusions from their partial views. For an extracted curve segment, we compute a series of the geometric invariance of equally spaced five co-planar points on the curve. Thus the resulting descriptor is invariant only under rotation, translation, and scale, but sufficient similarity is preserved even under large distortions. It is more stable and robust since it does not need derivatives. We use this transformation-invariant descriptor to index a hash table. We show the efficiency of the method through experiments using seriously distorted images of 2-D curved objects with occlusions.
URL: https://global.ieice.org/en_transactions/information/10.1587/e81-d_5_441/_p
Copy
@ARTICLE{e81-d_5_441,
author={Kyoung Sig ROH, In So KWEON, },
journal={IEICE TRANSACTIONS on Information},
title={2-D Curved Shape Recognition Using a Local Curve Descriptor and Projective Refinement},
year={1998},
volume={E81-D},
number={5},
pages={441-447},
abstract={In this paper, we propose a descriptor as a shape signature and the projective refinement as a verification method for recognizing 2D curved objects with occlusions from their partial views. For an extracted curve segment, we compute a series of the geometric invariance of equally spaced five co-planar points on the curve. Thus the resulting descriptor is invariant only under rotation, translation, and scale, but sufficient similarity is preserved even under large distortions. It is more stable and robust since it does not need derivatives. We use this transformation-invariant descriptor to index a hash table. We show the efficiency of the method through experiments using seriously distorted images of 2-D curved objects with occlusions.},
keywords={},
doi={},
ISSN={},
month={May},}
Copy
TY - JOUR
TI - 2-D Curved Shape Recognition Using a Local Curve Descriptor and Projective Refinement
T2 - IEICE TRANSACTIONS on Information
SP - 441
EP - 447
AU - Kyoung Sig ROH
AU - In So KWEON
PY - 1998
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E81-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 1998
AB - In this paper, we propose a descriptor as a shape signature and the projective refinement as a verification method for recognizing 2D curved objects with occlusions from their partial views. For an extracted curve segment, we compute a series of the geometric invariance of equally spaced five co-planar points on the curve. Thus the resulting descriptor is invariant only under rotation, translation, and scale, but sufficient similarity is preserved even under large distortions. It is more stable and robust since it does not need derivatives. We use this transformation-invariant descriptor to index a hash table. We show the efficiency of the method through experiments using seriously distorted images of 2-D curved objects with occlusions.
ER -