## Soft shape context for iterative closest point registration (2004)

Venue: | In: Proc. IEEE Int. Conf. Image Proc |

Citations: | 4 - 0 self |

### BibTeX

@INPROCEEDINGS{Liu04softshape,

author = {David Liu and Tsuhan Chen},

title = {Soft shape context for iterative closest point registration},

booktitle = {In: Proc. IEEE Int. Conf. Image Proc},

year = {2004},

pages = {1081--1084}

}

### OpenURL

### Abstract

This paper introduces a shape descriptor, the soft shape context, motivated by the shape context method. Unlike the original shape context method, where each image point was hard assigned into a single histogram bin, we instead allow each image point to contribute to multiple bins, hence more robust to distortions. The soft shape context can easily be integrated into the iterative closest point (ICP) method as an auxiliary feature vector, enriching the representation of an image point from spatial information only, to spatial and shape information. This yields a registration method more robust than the original ICP method. The method is general for 2D shapes. It does not calculate derivatives, hence being able to handle shapes with junctions and discontinuities. We present experimental results to demonstrate the robustness compared with the standard ICP method. 1.

### Citations

2214 |
A method for registration of 3D shapes
- Besl, McKay
- 1992
(Show Context)
Citation Context ...to handle shapes with junctions and discontinuities. We present experimental results to demonstrate the robustness compared with the standard ICP method. 1. INTRODUCTION Iterative closest point (ICP) =-=[1]-=- registration is a popular method for aligning two point sets. The registration process iterates two steps repeatedly: find the best correspondence between the two point sets based on spatial distance... |

1247 | Shape matching and object recognition using shape contexts
- Belongie, Malik, et al.
(Show Context)
Citation Context ...It is natural to think that incorporating information about the shape should benefit the correspondence step. In the following sections we show how to do that. 3. SHAPE CONTEXT DESCRIPTOR The work in =-=[9]-=- introduced a pure shape based matching technique based on a shape descriptor, the shape context. Intuitively, consider any point di ∈ D as a reference point, and all the other Nd − 1 points as vector... |

732 | Gradient-based learning applied to document recognition
- Bengio, Haffner
(Show Context)
Citation Context ...) because each point contributes to only one bin. 4. THE PROPOSED SOFT SHAPE CONTEXT 4.1. Solving the problem of background clutter The shape context method achieved top recognition rate in the MNIST =-=[10]-=-[9] handwritten digit database, where digits are segmented, i.e., each image contains a single digit. However, for aligning an isolated object to a bunch of non-segmented objects, shape context become... |

310 | A metric for distributions with applications to image databases - Rubner, Tomasi, et al. |

97 | Shape context and Chamfer matching in cluttered scenes
- Thayananthan, Stenger, et al.
- 2003
(Show Context)
Citation Context ...en digit database, where digits are segmented, i.e., each image contains a single digit. However, for aligning an isolated object to a bunch of non-segmented objects, shape context becomes unreliable =-=[11]-=-. The reason is that the shape context will include outliers, and shape information becomes contaminated. We propose to use shape context at a small sc ale, with radiu s about 9 pixels for images of s... |

93 | Recognition of shapes by editing shock graphs
- Sebastian, Klein, et al.
- 2001
(Show Context)
Citation Context ...tion [3], and global features like moment invariants and spherical harmonics invariants [4]. In this paper we consider the registration of 2D point sets in general, as opposed to single closed curves =-=[5]-=- or simple polygons (polygons without holes)[6]. A 2D point set often has 3-way or 4-way junctions, and it is difficult Work supported in part by Telecommunication Lab, Chunghwa Telcom, Taiwan. to def... |

90 | ICP Registration using Invariant Features
- Sharp, Lee, et al.
- 2002
(Show Context)
Citation Context ...e step of finding correspondence by using extra cues like color [2], surface normal, curvature, gradient information [3], and global features like moment invariants and spherical harmonics invariants =-=[4]-=-. In this paper we consider the registration of 2D point sets in general, as opposed to single closed curves [5] or simple polygons (polygons without holes)[6]. A 2D point set often has 3-way or 4-way... |

90 | Robust registration of 2D and 3D point sets
- Fitzgibbon
- 2003
(Show Context)
Citation Context ...Updating the transformation, a : a k + 1 Instead of using = arg min a ε dist N d ∑ ε i= 1 dist φ ( i) (| x |) =|| x || ( m − T ( di ; a ) ) , other variations use the Huber robust estimator in Step 2 =-=[7]-=-, or exclude points with large errors at Step 1 [8]. Termination can be determined when the correspondences found in Step 1 no longer change. Convergence to local (not global) minimum is guaranteed, s... |

86 | Registration and integration of textured 3-D data
- Johnson, Kang
- 1997
(Show Context)
Citation Context ... valid assumption, thus making ICP sensitive to the initial alignment. To address this problem, methods have been proposed to improve the step of finding correspondence by using extra cues like color =-=[2]-=-, surface normal, curvature, gradient information [3], and global features like moment invariants and spherical harmonics invariants [4]. In this paper we consider the registration of 2D point sets in... |

78 | Representation and detection of deformable shapes
- Felzenszwalb
- 2003
(Show Context)
Citation Context ...iants and spherical harmonics invariants [4]. In this paper we consider the registration of 2D point sets in general, as opposed to single closed curves [5] or simple polygons (polygons without holes)=-=[6]-=-. A 2D point set often has 3-way or 4-way junctions, and it is difficult Work supported in part by Telecommunication Lab, Chunghwa Telcom, Taiwan. to define the gradient or curve normal at a junction,... |

34 |
From accurate range imaging sensor calibration to accurate model-based 3-d object localization
- Champleboux, Lavallee, et al.
- 1992
(Show Context)
Citation Context ... using = arg min a ε dist N d ∑ ε i= 1 dist φ ( i) (| x |) =|| x || ( m − T ( di ; a ) ) , other variations use the Huber robust estimator in Step 2 [7], or exclude points with large errors at Step 1 =-=[8]-=-. Termination can be determined when the correspondences found in Step 1 no longer change. Convergence to local (not global) minimum is guaranteed, since both steps reduce the error. A successful alig... |

1 | Registration of a curve on a surface using differential properties,” Research report RR-2145
- Gourdon, Ayache
- 1993
(Show Context)
Citation Context ...nitial alignment. To address this problem, methods have been proposed to improve the step of finding correspondence by using extra cues like color [2], surface normal, curvature, gradient information =-=[3]-=-, and global features like moment invariants and spherical harmonics invariants [4]. In this paper we consider the registration of 2D point sets in general, as opposed to single closed curves [5] or s... |