V. Kruger. Gabor wavelet networks for object representation. Technical Report CS-TR-4245, University of Maryland, CFAR, May 2001. 20 Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Gabor Wavelet Networks for Efficient Head Pose Estimation - Krueger, Sommer (Correct)
....degree ranging from a coarse representation to an almost photo realistic one by simply varying the number of used wavelets. 5) By their very nature, GWNs are invariant to affine deformations without shear and homogeneous illumination changes[7; 8] Each single point is extensively discussed in [7] and will be addressed shortly in Section 2. The use of Gabor filters implies a model for the actual representation of the object information. In fact, as we will see, the GWN represents object information as a set of local image features, which leads to a higher level of abstraction and to ....
....image shows the positions, scales and orientations of the wavelets as little black line segments. By thresholding the weights, the more important wavelets may be selected, which leads to the right image. Ideally, each Gabor wavelet should be positioned exactly on the image line after optimization[7]. Furthermore, since a large weight indicates that the corresponding wavelet represents an edge segment (see Section 2.2) the wavelets encode local geometrical object information. In reality, however, interactions with other wavelets of the network have to be considered so that most wavelet ....
[Article contains additional citation context not shown here]
V. Kr uger, Gabor wavelet networks for object representation, Tech. Rep. CS-TR-4245, University of Maryland, CFAR (May 2001).
Efficient Real-Time Face Tracking in Wavelet Subspace - Feris, Cesar, Jr., Krueger (2001) (Correct)
....applications, as well as for tele conferencing and teleteaching tasks. For gesture, gaze and pose estimation applications, tracking has to be not only fast, but also precise. A variety of tracking approaches already exists [6, 2, 1] In this work, we will use Gabor Wavelet Networks (GWNs) [4, 5] in order to represent the face to be tracked. It is worth saying that we have already discussed a GWN based realtime tracking method in [6] The method discussed in the present paper differs from that approach in the sense that it is performed in a low dimensional wavelet subspace, posing a ....
V. Kr uger. Gabor Wavelet Networks for Object Representation. PhD thesis, Institute for Computer Science, University of Kiel, 2000.
Gabor Wavelet Networks for Efficient Head Pose Estimation - Krueger, Sommer Self-citation (Sommer) (Correct)
No context found.
V. Kr uger, G. Sommer, Gabor wavelet networks for object representation, in: Proc. of the Int. Dagstuhl 2000.
Gabor Wavelet Networks for Efficient Head Pose Estimation - Krueger, Sommer Self-citation (Sommer) (Correct)
....knowledge is given by the variances of pixel grey values, which means that the actual knowledge representation is given on a pixel basis; this is a representation that is independent of the object itself. In this paper we introduce an object representation that is based on Gabor Wavelet Networks [5] and show its advantages for the pose estimation problem. Gabor Wavelet Networks (GWNs) combine the advantages of Radial Basis Function (RBF) Preprint submitted to Elsevier Preprint networks and Gabor wavelets: GWNs represent an object as a linear combination of Gabor wavelets and the parameters ....
V. Kr uger, G. Sommer, Gabor wavelet networks for object representation, Tech. Rep. 2002.
Gabor Wavelet Networks for Object Representation and Face.. - Krüger, Sommer Self-citation (Sommer) (Correct)
....the continuity of T, we also find for any e 0 a 5 such that II(f 5) 112 e. 2.2 Symbolic Abstraction Generally, two different types of hierarchies can be distinguished [4] scale hierarchies abstraction hierarchies. GWNs allow an abstraction hierarchy of the coded data to some degree [7]. An abstraction hierarchy implies that the image can be considered as an expansion into image primitives, such as line or edge segments, that can be viewed as conceptual building blocks forming the image [4] In terms of an abstraction pyramid, we have the image itself at the first level, ....
V Kr/iger and G. Sommer. Gabor wavelet networks for object representation. In Deutsche Arbeitsgemeinschaft fiir Mustererkennung, 22. DAGM-Symposium, Kiel, Sept. 13-15, 2000. accepted for presentation.
Efficient Head Pose Estimation with Gabor Wavelet Networks - Krüger, Bruns, Sommer (2000) (2 citations) Self-citation (Kr Sommer) (Correct)
No context found.
V. Kruger and G. Sommer. Gabor wavelet networks for object representation. In Proc. of the Int. Dagstuhl 2000 Workshop, LNCS. Springer, 2000. to be published.
Gabor Wavelet Networks for Object Representation - Krüger, Sommer (2000) (4 citations) Self-citation (Sommer) (Correct)
No context found.
V Kruger and G. Sommer. Gabor wavelet networks for object representation. In Proc. of the Int. Dagstuhl 2000 Workshop, 2000. to be published.
Wavelet Networks for Face Processing - Krueger, Sommer (2002) (Correct)
No context found.
V. Kruger. Gabor wavelet networks for object representation. Technical Report CS-TR-4245, University of Maryland, CFAR, May 2001. 20
Wavelet Subspace Method for Real-time Face Tracking - Krueger, Feris (2004) (Correct)
No context found.
V. Kruger and G. Sommer. Gabor wavelet networks for object representation. In Tag. Bd. Deutsche Arbeitsgemeinschaft fur Mustererkennung, 22. DAGMSymposium, Kiel, Sept. 13-15, 2000.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC