#### DMCA

## An affine invariant interest point detector (2002)

### Cached

### Download Links

Venue: | In Proceedings of the 7th European Conference on Computer Vision |

Citations: | 1453 - 55 self |

### Citations

2662 | Object recognition from local scale-invariant features
- Lowe
- 1999
(Show Context)
Citation Context ...tures. The proposed improvements result in better repeatability and accuracy of interest points. Moreover, the scale invariant Harris-Laplace approach detects different regions than the DoG detector (=-=Lowe, 1999-=-). The latter one detects mainly blobs, whereas the Harris detector responds to corners and highly textured points, hence these detectors extract complementary features in images. If the scale change ... |

2422 | A combined corner and edge detector
- Harris, Stephens
- 1988
(Show Context)
Citation Context ...ormation content in these points is high. One of the first recognition techniques based on interest points has been proposed by Schmid and Mohr [14]. The points are extracted with the Harris detector =-=[5]-=- which is invariant to image rotation. To obtain invariance to scale changes interest points can be extracted in the scale space of an image [7]. Dufournaud et al. [3] use a multi-scale framework to m... |

1745 | A performance evaluation of local descriptors - Mikolajczyk, Schmid - 2005 |

1072 | The design and use of steerable filters
- Freeman, Adelson
- 1991
(Show Context)
Citation Context ...ves. Derivatives are computed on image patches normalized with the matrix U estimated for each point. Invariance to rotation is obtained by “steering” the derivatives in the direction of the gradient =-=[4]-=-. To obtain a stable estimation of the gradient direction, we use an average gradient orientation in a point neighbourhood. Invariance to affine intensity changes is obtained by dividing the derivativ... |

998 | Robust wide-baseline stereo from maximally stable extremal regions - Matas, Chum, et al. - 2004 |

710 | Feature detection with automatic scale selection
- Lindeberg
- 1998
(Show Context)
Citation Context ...orithm for recognition based on local extrema of difference-of-Gaussian filters in scale-space. Mikolajczyk and Schmid [11] use a multi-scale framework to detect points and then apply scale selection =-=[8]-=- to select characteristic points. These points are invariant to scale changes and allow matching and recognition in the presence of large scale factors. Tuytelaars and Van Gool [16] detect affine inva... |

613 | Scale-space theory in computer vision
- Lindeberg
- 1993
(Show Context)
Citation Context ...[14]. The points are extracted with the Harris detector [5] which is invariant to image rotation. To obtain invariance to scale changes interest points can be extracted in the scale space of an image =-=[7]-=-. Dufournaud et al. [3] use a multi-scale framework to match images at different scales. Interest points and descriptors are computed at several scales. A robust matching algorithm allows to select th... |

544 | Local grayvalue invariants for image retrieval
- Schmid, Mohr
- 1997
(Show Context)
Citation Context ...d reliably, are robust to partial visibility and the information content in these points is high. One of the first recognition techniques based on interest points has been proposed by Schmid and Mohr =-=[14]-=-. The points are extracted with the Harris detector [5] which is invariant to image rotation. To obtain invariance to scale changes interest points can be extracted in the scale space of an image [7].... |

408 | Evaluation of interest point detectors
- Schmid, Mohr, et al.
(Show Context)
Citation Context ...w for correspondences. Features which have proved to be particularly appropriate are interest points. However, the Harris interest point detector is not invariant to scale and affine transformations (=-=Schmid et al., 2000-=-). In this paper we give a detailed description of a scale and an affine invariant interest point detector introduced in Mikolajczyk and Schmid (2001, 2002). Our approach combines the Harris detector ... |

400 | Indexing based on scale invariant interest points
- Mikolajczyk, Schmid
- 2001
(Show Context)
Citation Context ...th images in order to allow for correspondences. Features which have shown to be particularly appropriate are interest points. Scale invariant interest points detectors have been presented previously =-=[10, 11]-=-. However, none of the existing interest point detectors is invariant to affine transformations. In this paper wespresent an affine invariant interest point detector. For each interest point we simult... |

305 | Reliable feature matching across widely separated views
- Baumberg
- 2000
(Show Context)
Citation Context ...mpute an affine invariant Fourier description of the intensity profile along a line connecting two points. The description is not robust unless the two points lie on the same planar surface. Baumberg =-=[2]-=- extracts interest points at several scales and then adapts the shape of the region to the local image structure using an iterative procedure based on the second moment matrix [9]. Their descriptors a... |

296 | A fast operator for detection and precise location of distinct points, corners and center of circular features - Förstner, Gülch |

216 | Wide baseline stereo matching based on local, affinely invariant regions
- Tuytelaars, Gool
(Show Context)
Citation Context ...ply scale selection [8] to select characteristic points. These points are invariant to scale changes and allow matching and recognition in the presence of large scale factors. Tuytelaars and Van Gool =-=[16]-=- detect affine invariant regions based on image intensities. However, the number of such regions in an image is limited and depends on the content. They use colour descriptors computed for these regio... |

207 | Class-specific, top-down segmentation - Borenstein, Ullman - 2002 |

202 |
Pattern Classification and Scene Analysis. Wiley-Interscience
- Duda, Hart
- 1973
(Show Context)
Citation Context ...) + L yy(x, σn)| (3) When the size of the LoG kernel matches with the size of a blob-like structure the response attains an extremum. The LoG kernel can therefore be interpreted as a matching filter (=-=Duda and Hart, 1973-=-). The LoG is well adapted to blob detection due to its circular symmetry, but it also provides a good estimation of the characteristic scale for other local structures such as corners, edges, ridges ... |

187 | Detecting salient blob-like image structures and their scales with a scale-space primal sketch : a method for focus-of-attention
- LINDEBERG
- 1993
(Show Context)
Citation Context ...c scale for other local structures such as corners, edges, ridges and multi-junctions. Many previous results confirm the usefulness of the Laplacian function for scale selection (Chomat et al., 2000; =-=Lindeberg, 1993-=-, 1998; Lowe, 1999). 2.2. Harris-Laplace Detector In the following we explain in detail our scale invariant feature detection algorithm. The Harris-Laplace detector uses the scale-adapted Harris funct... |

162 | Wide baseline stereo matching
- Pritchett, Zisserman
- 1998
(Show Context)
Citation Context ...tors (see Mikolajczyk and Schmid, 2003a for a performance evaluation of different descriptors computed for affine-invariant regions) or (ii) semi-local geometric consistency (Dufournaud et al., 2000; =-=Pritchett and Zisserman, 1998-=-; Tell and Carlsson, 2002). 6. Conclusions and Future Work In this paper we have proposed two novel approaches for scale and affine invariant interest point detection. Our algorithm simultaneously ada... |

153 | Invariant features from interest point groups - Brown, Lowe - 2002 |

131 | Giraudon: A Computational Approach for Corner and Vertex Detection, Int
- Deriche, G
- 1993
(Show Context)
Citation Context ...ts location relative to the detection scale in the gradient direction. One could determine the chain of points and select only one of them to represent the local structure (Alvarez and Morales, 1997; =-=Deriche and Giraudon, 1993-=-). Similar points are located in a small neighborhood and can be determined by comparing their descriptors. However, for local structures existing over a wide range of scales the information content c... |

118 | A framework for low level feature extraction - Forstner - 1994 |

109 | Content-based image retrieval based on local affinely invariant regions - Tuytelaars, Gool - 1999 |

106 | Viewpoint invariant texture matching and wide baseline stereo
- Schaffalitzky, Zisserman
- 2001
(Show Context)
Citation Context ... locations in scale space, converge to the same point location. The number of points is therefore reduced. The properties of the second moment matrix were also explored by Schaffalitzky and Zisserman =-=[13]-=-, but their goal was to obtain an affine invariant texture descriptor. 1.2 Our approach A uniform Gaussian scale-space is often used to deal with scale changes [3, 7, 10, 11]. However, an affine Gauss... |

104 | Representation for shape based on peaks and ridges in the difference of low-pass transform,” Robotics Institute - Crowley, Parker - 1983 |

102 | A sparse texture representation using affineinvariant regions - Lazebnik, Schmid, et al. - 2003 |

85 | Saliency and Image Description - Kadir, Brady, et al. - 2001 |

83 | 3D object modeling and recognition using affine-invariant patches and multi-view spatial constraints - Rothganger, Lazebnik, et al. - 2003 |

80 | Simulation of neural contour mechanisms: from simple to end-stopped cells - Heitger, Rosenthaler, et al. - 1992 |

76 | Matching Images with Different Resolutions
- Dufournaud, Schmid, et al.
(Show Context)
Citation Context ...tracted with the Harris detector [5] which is invariant to image rotation. To obtain invariance to scale changes interest points can be extracted in the scale space of an image [7]. Dufournaud et al. =-=[3]-=- use a multi-scale framework to match images at different scales. Interest points and descriptors are computed at several scales. A robust matching algorithm allows to select the correct scale. In the... |

71 | Shape-adapted smoothing in estimation of 3-d shape cues from affine distortions of local 2-d brightness structure
- Lindeberg, Garding
- 1997
(Show Context)
Citation Context ...ar surface. Baumberg [2] extracts interest points at several scales and then adapts the shape of the region to the local image structure using an iterative procedure based on the second moment matrix =-=[9]-=-. Their descriptors are affine invariant for fixed scale and location, that is the scale and the location of the points are not extracted in an affine invariant way. The points as well as the associat... |

62 |
Geometric information criterion for model selection
- Kanatani
- 1998
(Show Context)
Citation Context ...ased on RANdom SAmple Consensus (RANSAC) rejects inconsistent matches. For our experimental results the transformation used is either a homography or a fundamental matrix. A model selection algorithm =-=[6]-=- can be used to automatically decide which transformation is the most appropriate one. Database retrieval. A voting algorithm is used to select the most similar images in the database. This makes retr... |

62 |
Wide baseline point matching using affine invariants computed from intensity profiles
- Tell, Carlsson
(Show Context)
Citation Context ...mographies are obtained by matching regions bound by four line segments. This approach has been applied to wide baseline matching and it is clearly difficult to extend to retrieval. Tell and Carlsson =-=[15]-=- also address the problem of wide baseline matching and use an affine invariant descriptors for point pairs. They compute an affine invariant Fourier description of the intensity profile along a line ... |

53 | Multi-view matching for unordered image sets - Schaffalitzky, Zisserman - 2002 |

50 |
Finding geometric and relational structures in an image
- Horaud, Veillon
- 1990
(Show Context)
Citation Context ...int detectors presented in Schmid et al. (2000) demonstrate an excellent performance of the Harris detector compared to other existing approaches (Cottier, 1994; Forstner, 1994; Heitger et al., 1992; =-=Horaud et al., 1990-=-). However this detector is not invariant to scale changes. In this section we propose a new interest point detector that combines the reliable Harris detector (Harris and Stephens, 1988) with automat... |

47 | Fingerprint enhancement by shape adaptation of scale-space operators with automatic scale-selection
- Almansa, Lindeberg
- 2000
(Show Context)
Citation Context ...scale allows to obtain a reasonable eigenvalue ratio and allows convergence for pointsswhich would not converge if the ratio is too large. A similar approach for local scale selection was proposed in =-=[1]-=-. Spatial localization. It is well known that the local maxima of the Harris measure (equation 2) change their spatial location if the detection scale changes. This can also be observed if the scale c... |

44 | Combining appearance and topology for wide baseline matching - Tell, Carlsson - 2002 |

40 | Tracking of multi-state hand models using particle filtering and a hierarchy of multi-scale image features - Laptev, Lindeberg - 2001 |

32 | Feature tracking with automatic selection of spatial scales’, Computer Vision and Image Understanding 71(3 - Bretzner, Lindeberg - 1998 |

27 | A representation for visual information - Crowley - 1981 |

22 | Accuracy in image measure - Brand, Mohr - 1994 |

22 | Local scale selection for Gaussian based description techniques - Chomat, Verdiere, et al. - 2000 |

18 | Joint feature distributions for image correspondence - Triggs - 2001 |

13 |
Affine morphological multiscale analysis of corners and multiple junctions
- Alvarez, Morales
- 1997
(Show Context)
Citation Context ... image structure, changes its location relative to the detection scale in the gradient direction. One could determine the chain of points and select only one of them to represent the local structure (=-=Alvarez and Morales, 1997-=-; Deriche and Giraudon, 1993). Similar points are located in a small neighborhood and can be determined by comparing their descriptors. However, for local structures existing over a wide range of scal... |

7 |
Extraction et appariements robustes des points d’intérêts de deux images non étalonnés
- Cottier
- 1994
(Show Context)
Citation Context ...Interest Point Detector The evaluation of interest point detectors presented in Schmid et al. (2000) demonstrate an excellent performance of the Harris detector compared to other existing approaches (=-=Cottier, 1994-=-; Forstner, 1994; Heitger et al., 1992; Horaud et al., 1990). However this detector is not invariant to scale changes. In this section we propose a new interest point detector that combines the reliab... |

6 | Viewpoint invariant texture matching and wide baseline stereo - Schaalitzky, Zisserman - 2001 |

5 | Direct estimation of local surface shape in a fixating binocular vision system
- Garding, Lindeberg
- 1994
(Show Context)
Citation Context ...eighborhood of points xR and xL are normalized by transformations x′R = M1/2R xR and x′L = M1/2L xL , respectively, the normalized regions are related by a simple rotation x′L = Rx′R (Baumberg, 2000; =-=Garding and Lindeberg, 1994-=-). xR = AxL = M−1/2R RM1/2L xL , M1/2R xR = RM1/2L xL (9) The matrices M ′L and M ′R in the normalized frames are equal to a pure rotation matrix (see Fig. 4). In other words, the intensity patterns i... |

4 | Matching images with dierent resolutions - Dufournaud, Schmid, et al. - 2000 |

3 | Wide baseline point matching using ane invariants computed from intensity pro - Tell, Carlsson - 2000 |

3 | Interest point detection invariant to affine transformations - Mikolajczyk |

1 | Shape recognition with edge based features - Mikolajczyk, Schmid |

1 | of Computer Vision 60(1), pp 63–86. • [2] http://en.wikipedia.org/wiki/Harris-Affine last accessed 22/11/2012 • [3 - Mikolajczyk, Schmid - 2002 |