The Experts below are selected from a list of 63 Experts worldwide ranked by ideXlab platform
Cordelia Schmid - One of the best experts on this subject based on the ideXlab platform.
-
a performance evaluation of local descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005Co-Authors: Krystian Mikolajczyk, Cordelia SchmidAbstract:In this paper, we compare the performance of descriptors computed for local interest regions, as, for example, extracted by the Harris-Affine detector [Mikolajczyk, K and Schmid, C, 2004]. Many different descriptors have been proposed in the literature. It is unclear which descriptors are more appropriate and how their performance depends on the interest region detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the detector. Our evaluation uses as criterion recall with respect to precision and is carried out for different image transformations. We compare shape context [Belongie, S, et al., April 2002], steerable filters [Freeman, W and Adelson, E, Setp. 1991], PCA-SIFT [Ke, Y and Sukthankar, R, 2004], differential invariants [Koenderink, J and van Doorn, A, 1987], spin images [Lazebnik, S, et al., 2003], SIFT [Lowe, D. G., 1999], complex filters [Schaffalitzky, F and Zisserman, A, 2002], moment invariants [Van Gool, L, et al., 1996], and cross-correlation for different types of interest regions. We also propose an extension of the SIFT descriptor and show that it outperforms the original method. Furthermore, we observe that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best. Moments and steerable filters show the best performance among the low dimensional descriptors.
-
a performance evaluation of local descriptors
Computer Vision and Pattern Recognition, 2003Co-Authors: Krystian Mikolajczyk, Cordelia SchmidAbstract:In this paper we compare the performance of interest point descriptors. Many different descriptors have been proposed in the literature. However, it is unclear which descriptors are more appropriate and how their performance depends on the interest point detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the point detector. Our evaluation uses as criterion detection rate with respect to false positive rate and is carried out for different image transformations. We compare SIFT descriptors (Lowe, 1999), steerable filters (Freeman and Adelson, 1991), differential invariants (Koenderink ad van Doorn, 1987), complex filters (Schaffalitzky and Zisserman, 2002), moment invariants (Van Gool et al., 1996) and cross-correlation for different types of interest points. In this evaluation, we observe that the ranking of the descriptors does not depend on the point detector and that SIFT descriptors perform best. Steerable filters come second ; they can be considered a good choice given the low dimensionality.
Krystian Mikolajczyk - One of the best experts on this subject based on the ideXlab platform.
-
a performance evaluation of local descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005Co-Authors: Krystian Mikolajczyk, Cordelia SchmidAbstract:In this paper, we compare the performance of descriptors computed for local interest regions, as, for example, extracted by the Harris-Affine detector [Mikolajczyk, K and Schmid, C, 2004]. Many different descriptors have been proposed in the literature. It is unclear which descriptors are more appropriate and how their performance depends on the interest region detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the detector. Our evaluation uses as criterion recall with respect to precision and is carried out for different image transformations. We compare shape context [Belongie, S, et al., April 2002], steerable filters [Freeman, W and Adelson, E, Setp. 1991], PCA-SIFT [Ke, Y and Sukthankar, R, 2004], differential invariants [Koenderink, J and van Doorn, A, 1987], spin images [Lazebnik, S, et al., 2003], SIFT [Lowe, D. G., 1999], complex filters [Schaffalitzky, F and Zisserman, A, 2002], moment invariants [Van Gool, L, et al., 1996], and cross-correlation for different types of interest regions. We also propose an extension of the SIFT descriptor and show that it outperforms the original method. Furthermore, we observe that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best. Moments and steerable filters show the best performance among the low dimensional descriptors.
-
a performance evaluation of local descriptors
Computer Vision and Pattern Recognition, 2003Co-Authors: Krystian Mikolajczyk, Cordelia SchmidAbstract:In this paper we compare the performance of interest point descriptors. Many different descriptors have been proposed in the literature. However, it is unclear which descriptors are more appropriate and how their performance depends on the interest point detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the point detector. Our evaluation uses as criterion detection rate with respect to false positive rate and is carried out for different image transformations. We compare SIFT descriptors (Lowe, 1999), steerable filters (Freeman and Adelson, 1991), differential invariants (Koenderink ad van Doorn, 1987), complex filters (Schaffalitzky and Zisserman, 2002), moment invariants (Van Gool et al., 1996) and cross-correlation for different types of interest points. In this evaluation, we observe that the ranking of the descriptors does not depend on the point detector and that SIFT descriptors perform best. Steerable filters come second ; they can be considered a good choice given the low dimensionality.
Jan B Koenderink - One of the best experts on this subject based on the ideXlab platform.
-
reconstruction of the complete ouabain binding pocket of na k atpase in gastric h k atpase by substitution of only seven amino acids
Journal of Biological Chemistry, 2005Co-Authors: Li Yan Qiu, Elmar Krieger, Gijs Schaftenaar, H G P Swarts, Peter H G M Willems, Jan Joep H H M De Pont, Jan B KoenderinkAbstract:Although cardiac glycosides have been used as drugs for more than 2 centuries and their primary target, the sodium pump (Na,K-ATPase), has already been known for 4 decades, their exact binding site is still elusive. In our efforts to define the molecular basis of digitalis glycosides binding we started from the fact that a closely related enzyme, the gastric H,K-ATPase, does not bind glycosides like ouabain. Previously, we showed that a chimera of these two enzymes, in which only the M3-M4 and M5-M6 hairpins were of Na,K-ATPase, bound ouabain with high affinity (Koenderink, J. B., Hermsen, H. P. H., Swarts, H. G. P., Willems, P. H. G. M., and De Pont, J. J. H. H. M. (2000) Proc. Natl. Acad. Sci. U. S. A. 97, 11209-11214). We also demonstrated that only three amino acids (Phe(783), Thr(797), and Asp(804)) present in the M5-M6 hairpin of Na,K-ATPase were sufficient to confer high affinity ouabain binding to a chimera which contained in addition the M3-M4 hairpin of Na,K-ATPase (Qiu, L. Y., Koenderink, J. B., Swarts, H. G., Willems, P. H., and De Pont, J. J. H. H. M. (2003) J. Biol. Chem. 278, 47240-47244). To further pinpoint the ouabain-binding site here we used a chimera-based loss-of-function strategy and identified four amino acids (Glu(312), Val(314), Ile(315), Gly(319)), all present in M4, as being important for ouabain binding. In a final gain-of-function study we showed that a gastric H,K-ATPase that contained Glu(312), Val(314), Ile(315), Gly(319), Phe(783), Thr(797), and Asp(804) of Na,K-ATPase bound ouabain with the same affinity as the native enzyme. Based on the E(2)P crystal structure of Ca(2+)-ATPase we constructed a homology model for the ouabain-binding site of Na,K-ATPase involving all seven amino acids as well as several earlier postulated amino acids.
Mikkel M Sigurd - One of the best experts on this subject based on the ideXlab platform.
-
Koenderink corner points
Lecture Notes in Computer Science, 2001Co-Authors: Mads Nielsen, Ole Fogh Olsen, Michael Sig, Mikkel M SigurdAbstract:Koenderink characterizes the local shape of 2D surfaces in 3D in terms of the shape index and the local curvedness. The index characterizes the local type of surface point: concave, hyperbolic, or convex. The curvedness expresses how articulated the local shape is, from flat towards very peaked. In this paper we define corner points as point on a shape of locally maximal Koenderink curvedness. These points can be detected very robustly based on integration indices. This is not the case for other natural corner points like extremal points. Umbilici can likewise be detected robustly by integral expressions, but does not correspond to intuitive corners of a shape. Furthermore, we show that Koenderink corner points do not generically coincide with other well-known shape features such as umbilici, ridges, parabolic lines, sub-parabolic lines, or extremal points. This is formalized through the co-dimension of intersection of the different structures.
Li Yan Qiu - One of the best experts on this subject based on the ideXlab platform.
-
reconstruction of the complete ouabain binding pocket of na k atpase in gastric h k atpase by substitution of only seven amino acids
Journal of Biological Chemistry, 2005Co-Authors: Li Yan Qiu, Elmar Krieger, Gijs Schaftenaar, H G P Swarts, Peter H G M Willems, Jan Joep H H M De Pont, Jan B KoenderinkAbstract:Although cardiac glycosides have been used as drugs for more than 2 centuries and their primary target, the sodium pump (Na,K-ATPase), has already been known for 4 decades, their exact binding site is still elusive. In our efforts to define the molecular basis of digitalis glycosides binding we started from the fact that a closely related enzyme, the gastric H,K-ATPase, does not bind glycosides like ouabain. Previously, we showed that a chimera of these two enzymes, in which only the M3-M4 and M5-M6 hairpins were of Na,K-ATPase, bound ouabain with high affinity (Koenderink, J. B., Hermsen, H. P. H., Swarts, H. G. P., Willems, P. H. G. M., and De Pont, J. J. H. H. M. (2000) Proc. Natl. Acad. Sci. U. S. A. 97, 11209-11214). We also demonstrated that only three amino acids (Phe(783), Thr(797), and Asp(804)) present in the M5-M6 hairpin of Na,K-ATPase were sufficient to confer high affinity ouabain binding to a chimera which contained in addition the M3-M4 hairpin of Na,K-ATPase (Qiu, L. Y., Koenderink, J. B., Swarts, H. G., Willems, P. H., and De Pont, J. J. H. H. M. (2003) J. Biol. Chem. 278, 47240-47244). To further pinpoint the ouabain-binding site here we used a chimera-based loss-of-function strategy and identified four amino acids (Glu(312), Val(314), Ile(315), Gly(319)), all present in M4, as being important for ouabain binding. In a final gain-of-function study we showed that a gastric H,K-ATPase that contained Glu(312), Val(314), Ile(315), Gly(319), Phe(783), Thr(797), and Asp(804) of Na,K-ATPase bound ouabain with the same affinity as the native enzyme. Based on the E(2)P crystal structure of Ca(2+)-ATPase we constructed a homology model for the ouabain-binding site of Na,K-ATPase involving all seven amino acids as well as several earlier postulated amino acids.
