## Recognition of 3-d objects using the extended gaussian image (1981)

Venue: | In IJCAI Conference |

Citations: | 27 - 8 self |

### BibTeX

@INPROCEEDINGS{Ikeuchi81recognitionof,

author = {Katsushi Ikeuchi},

title = {Recognition of 3-d objects using the extended gaussian image},

booktitle = {In IJCAI Conference},

year = {1981},

pages = {595--600}

}

### Years of Citing Articles

### OpenURL

### Abstract

propose to use an extended Gaussian imap,e (EGI) for interpreting 2-1/2-D representations for recognition of 3-D objects. The EGI is constructed by mapping each surface normals of an object to the Gaussian sphere. The freedom in viewer directions caused by incomplete observation Is greatly reduced by applying constraints derived from a global distribution of surface normals on the EGI. One constraint on the viewer direction is derived from the ratio of the projected area to the original surface area. The other constraint comes from the direction of the principal axis. After reducing the possible viewing directions with these constraints, we will apply a matching function to ESls of a candidate set for a final decision. We also propose an algorithm for reconstruction of the original shape of a convex polyhedron from its EGI. This algorithm is based on the analysis-by-synthesis method. 1 WHAT IS THE EXTENDED GAUSSIAN IMAGE A collection of local surface normals [1,2,3,4,5], sometimes referred to as a 2-1/2-D representation of an object [6], is often provided by machine vision at the low level. For example, an algorithm based on the propagation-of-constraints technique [2] provides local surface orientation from shading and occluding information. The same algorithm can also produce surface orientation from apparent distortion of known patterns based on a regular-pattern gradient map [A], The distortion of these small circles on the golf ball in Fig. 1 can be used to recover local surface orientation.

### Citations

449 |
Representation and recognition of the spatial organization of three-dimensional shapes
- Marr, Nishihara
- 1978
(Show Context)
Citation Context ...ocess is how to convert a local representation based on the viewer-centered coordinate system into a global description based on the object-centered coordinate system such as the generalized cylinder =-=[7,8]-=- or the spike model [1]. Each local representation depicted as a needle in the above example is obtained at a particular point expressed in viewer-centered coordinate system on the image plane. On the... |

194 |
Recovering intrinsic scene characteristics from images
- Barrow, Tenenbaum
- 1978
(Show Context)
Citation Context ...ion of the original shape of a convex polyhedron from its EGI. This algorithm is based on the analysis-by-synthesis method. 1 WHAT IS THE EXTENDED GAUSSIAN IMAGE A collection of local surface normals =-=[1,2,3,4,5]-=-, sometimes referred to as a 2-1/2-D representation of an object [6], is often provided by machine vision at the low level. For example, an algorithm based on the propagation-of-constraints technique ... |

190 | Horn,“Numerical shape from shading and occluding boundaries
- Ikeuchi, B
- 1981
(Show Context)
Citation Context ...ion of the original shape of a convex polyhedron from its EGI. This algorithm is based on the analysis-by-synthesis method. 1 WHAT IS THE EXTENDED GAUSSIAN IMAGE A collection of local surface normals =-=[1,2,3,4,5]-=-, sometimes referred to as a 2-1/2-D representation of an object [6], is often provided by machine vision at the low level. For example, an algorithm based on the propagation-of-constraints technique ... |

174 |
Visual perception by computer
- Binford
- 1971
(Show Context)
Citation Context ...ocess is how to convert a local representation based on the viewer-centered coordinate system into a global description based on the object-centered coordinate system such as the generalized cylinder =-=[7,8]-=- or the spike model [1]. Each local representation depicted as a needle in the above example is obtained at a particular point expressed in viewer-centered coordinate system on the image plane. On the... |

99 |
Determining surface orientations of specular surfaces by using the photometric stereo method
- Ikeuchi
- 1981
(Show Context)
Citation Context ...ion of the original shape of a convex polyhedron from its EGI. This algorithm is based on the analysis-by-synthesis method. 1 WHAT IS THE EXTENDED GAUSSIAN IMAGE A collection of local surface normals =-=[1,2,3,4,5]-=-, sometimes referred to as a 2-1/2-D representation of an object [6], is often provided by machine vision at the low level. For example, an algorithm based on the propagation-of-constraints technique ... |

31 |
Polyhedron Models
- Wenninger
- 1971
(Show Context)
Citation Context ...ng edges of a regular polyhedron inscribed in the sphere onto the surface of the sphere with respect to the center of the sphere. The resulting tessellation on the sphere is called as a geodesic dome =-=[12]-=-. Since we have no polyhedron of higher order than the icosahedron, we use a semi-regular geodesic dome constructed from a two frequency dodecahedron. (See Fig. 2.) Our tessellated sphere also has a h... |

20 |
Shape from texture
- Kender
- 1980
(Show Context)
Citation Context ...m is based on the analysis-by-synthesis method. 1 WHAT IS THE EXTENDED GAUSSIAN IMAGE A collection of local surface normals [1,2,3,4,5], sometimes referred to as a 2-1/2-D representation of an object =-=[6]-=-, is often provided by machine vision at the low level. For example, an algorithm based on the propagation-of-constraints technique [2] provides local surface orientation from shading and occluding in... |

12 | Private communication - Horn - 2009 |

5 | SEQUINS and QUILLS: representation for surface topography - Horn - 1979 |

5 | Using enhanced spherical images for object representation
- Smith
- 1979
(Show Context)
Citation Context ...ution of mass on the Gaussian sphere. This distribution of mass will be normalized. The resulting distribution of mass on the Gaussian sphere is called the extended Gaussian image (EGI) of the object =-=[1,9]-=-. 595 An EGI is independent on both the position of the origin and the scale of axes of the coordinate system. A coordinate system may be characterized using three components; the position of origin, ... |

4 |
Shape from regular patterns (An example of constraint propagation
- Ikeuchi
- 1980
(Show Context)
Citation Context ... surface orientation from shading and occluding information. The same algorithm can also produce surface orientation from apparent distortion of known patterns based on a regular-pattern gradient map =-=[A]-=-, The distortion of these small circles on the golf ball in Fig. 1 can be used to recover local surface orientation. RECOGNITION OF 3-D OBJECTS USING THE EXTENDED GAUSSIAN IMAGE Katsushi Ikeuchi Compu... |

4 |
Convex Figures and Polyhedra
- Lysternik
- 1963
(Show Context)
Citation Context ...arter point on the equator of the Gaussian sphere. The EGI may be regarded as a unique description, on treating only convex objects. An object has a unique EG1, when the object is a convex polyhedron =-=[10]-=-. Minkowski showed that: two convex polyhedra are identical if each pair of corresponding faces has an equal area and the same surface normal. IT RECOGNITION OF AN OBJECT USING AN EGI A. Data Structur... |

4 |
Three-dimensional Scene Analysis
- Bajcsy
- 1980
(Show Context)
Citation Context ...ototypes of candidates objects. The best fitting candidate will be selected as the object observed at that time. Even though a couple of non-convex objects among a candidate set may have the same EGI =-=[13]-=-, an EGI is still a helpful tool; after reducing the possible set of candidates and also determining possible spatial alignments of the candidates by using the EGI, the interpreter can make a final de... |