#### DMCA

## Semantic Object Recognition with Segment Faces (2013)

### Citations

3474 |
The Elements of Statistical Learning
- Hastie, Tibshirani, et al.
- 2001
(Show Context)
Citation Context ...tions of the segments in the image. The KI 2013 Workshop on Visual and Spatial Cognition 21 procedure employs methods from machine learning, namely k-means clustering and decision trees with boosting =-=[3, 5, 9]-=-, and from computer vision, e.g. image pyramid segmentation and contour signatures [4]. The rest of this paper is organized as follows: First, we introduce our procedure for semantic object recognitio... |

2738 | Object recognition from local scale-invariant features
- Lowe
- 1999
(Show Context)
Citation Context ...ted works. The survey [6] reviews literature on both the 3D model building process and techniques used to match and identify free-form objects from imagery, including recognition from 2D silhouettes. =-=[12]-=- presents an object recognition system that uses local image features, which are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D... |

642 | Some informational aspects of visual perception
- Attneave
- 1954
(Show Context)
Citation Context ...troduce our procedure for semantic object recognition based on clusters of image segment contours and discuss the problem of recognizing objects from different perspectives. 1 Introduction Already in =-=[2]-=-, it has been stated, that the contour points of an object, for instance of a cat, are of particular importance for human semantic object recognition. By semantic, we mean in this context that we do n... |

396 |
Learning OpenCV: Computer Vision with the OpenCV Library. O’Reilly
- Bradski, Kaehler
- 2008
(Show Context)
Citation Context ...procedure employs methods from machine learning, namely k-means clustering and decision trees with boosting [3, 5, 9], and from computer vision, e.g. image pyramid segmentation and contour signatures =-=[4]-=-. The rest of this paper is organized as follows: First, we introduce our procedure for semantic object recognition in some more detail (Sect. 2). After that, we consider the influence of perspective ... |

225 |
Data Mining Techniques For Marketing, Sales and Customer Support,
- Berry, Linoff
- 1996
(Show Context)
Citation Context ...tions of the segments in the image. The KI 2013 Workshop on Visual and Spatial Cognition 21 procedure employs methods from machine learning, namely k-means clustering and decision trees with boosting =-=[3, 5, 9]-=-, and from computer vision, e.g. image pyramid segmentation and contour signatures [4]. The rest of this paper is organized as follows: First, we introduce our procedure for semantic object recognitio... |

200 | A survey of free-form object representation and recognition techniques.
- Campbell, Flynn
- 2001
(Show Context)
Citation Context ... background. 5 Related Works The problem of recognizing and locating objects is very important in applications such as robotics and navigation. Therefore, there are numerous related works. The survey =-=[6]-=- reviews literature on both the 3D model building process and techniques used to match and identify free-form objects from imagery, including recognition from 2D silhouettes. [12] presents an object r... |

120 |
Classification and Regression Trees. Wadsworth Statistic/Probability Series
- Breiman, Friedman, et al.
- 1984
(Show Context)
Citation Context ...tions of the segments in the image. The KI 2013 Workshop on Visual and Spatial Cognition 21 procedure employs methods from machine learning, namely k-means clustering and decision trees with boosting =-=[3, 5, 9]-=-, and from computer vision, e.g. image pyramid segmentation and contour signatures [4]. The rest of this paper is organized as follows: First, we introduce our procedure for semantic object recognitio... |

106 | Semi-local affine parts for object recognition.
- Lazebnik, Schmid, et al.
- 2004
(Show Context)
Citation Context ... far above chance – are encouraging in this direction. To test and improve the first implemented algorithm in a controlled environment, it was used to classify images from the butterfly image dataset =-=[11]-=-. For all seven categories, the right category of an image is predicted with a success rate of 99.5% if the image is from the training set and 27.14% if the image is from the test set. A random guess ... |

43 | Qualitative Spatial Reasoning Using Orientation, Distance and Path Knowledge.
- Zimmermann, Freksa
- 1996
(Show Context)
Citation Context ...alitative relations of the line segments forming the contour of the polygon are considered during the object recognition phase. The approach is eventually based on the so-called double-cross calculus =-=[18]-=-. Each object is identified by exactly one contour built from more and more polygon vertices. The approach is successful, however it does not reflect the fact, that complex objects may consist of seve... |

14 |
MATLAB: An Introduction with Applications, 2nd Edition
- Gilat
- 2004
(Show Context)
Citation Context ...ograms (as described in Sect. 2) has been implemented in C++/OpenCV [4] by the first author. For the full treatment of perspective distortion (Sect. 3), so far only an implementation in Matlab/Octave =-=[8]-=- by the second author is available. All in all, our object recognition procedure works in practice: The segment neighborhood relations in the image segment tree remain invariant, even after perspectiv... |

11 | J.F.: Computer Graphics: Principles and Practice. - Foley, Dam, et al. - 1995 |

7 |
Digital image Processing. 6th revised and extended edition
- JÄHNE
- 2005
(Show Context)
Citation Context ...stance histograms, computed from the segment contour. A distance histogram consists of a vector of distances computed with several related methods: polar distance, contour signature, and ray distance =-=[1, 10, 15]-=- (see Fig. 2). 3. Compute/use cluster models over the feature vectors: During training, a cluster model with all feature vectors from all images of one category is created. Each cluster represents a f... |

3 |
Shape representation and retrieval using distance histograms
- Shuang
- 2001
(Show Context)
Citation Context ...stance histograms, computed from the segment contour. A distance histogram consists of a vector of distances computed with several related methods: polar distance, contour signature, and ray distance =-=[1, 10, 15]-=- (see Fig. 2). 3. Compute/use cluster models over the feature vectors: During training, a cluster model with all feature vectors from all images of one category is created. Each cluster represents a f... |

2 |
Use of contour signatures and classification methods to optimize the tool life in metal machining
- Alegre, Alaiz-Rodŕıguez, et al.
(Show Context)
Citation Context ...stance histograms, computed from the segment contour. A distance histogram consists of a vector of distances computed with several related methods: polar distance, contour signature, and ray distance =-=[1, 10, 15]-=- (see Fig. 2). 3. Compute/use cluster models over the feature vectors: During training, a cluster model with all feature vectors from all images of one category is created. Each cluster represents a f... |

1 | F.: Object recognition with multicopters
- Schmidsberger, Stolzenburg
(Show Context)
Citation Context ... neighborhood relations, among others. Therefore, we focus in our approach on segment contours and their adjacency relations. Our overall procedure of object recognition roughly works as follows (cf. =-=[13]-=-): Each object in an image is decomposed into segments with different shapes and colors. In order to recognize an object, e.g. a house, it is necessary to find out which segments are typical for this ... |

1 |
Shape retrieval with qualitative relations: The influence of part-order and approximation precision on retrieval performance and computational effort
- Schuldt
- 2011
(Show Context)
Citation Context ...ssful in practice. However, as already said in the introduction, here more or less only points of clouds and not groups of segment faces are considered, which appears to be more cognitively adequate. =-=[14]-=- performs shape retrieval by considering qualitative relations. This means the qualitative relations of the line segments forming the contour of the polygon are considered during the object recognitio... |

1 |
navigation based on qualitative angle information
- Stolzenburg, exploration
- 2010
(Show Context)
Citation Context ...aight lines. This implies that polygons remain polygons with the same number and order of vertices. Furthermore, left-right relations, which are important for localization, navigation and exploration =-=[16]-=-, stay invariant, provided that the polygons are always viewed from the same side, which is usually the outside of the object. From this it follows in particular, that convex edges remain convex and n... |