Results 271 to 280 of about 1,001,350 (314)
Some of the next articles are maybe not open access.
IEEE Winter Conference on Applications of Computer Vision, 2014
The state-of-the-art SIFT flow has been widely adopted for the general image matching task, especially in dealing with image pairs from similar scenes but with different object configurations. However, the way in which the dense SIFT features are computed at a fixed scale in the SIFT flow method limits its capability of dealing with scenes of large ...
null Weichao Qiu +4 more
openaire +2 more sources
The state-of-the-art SIFT flow has been widely adopted for the general image matching task, especially in dealing with image pairs from similar scenes but with different object configurations. However, the way in which the dense SIFT features are computed at a fixed scale in the SIFT flow method limits its capability of dealing with scenes of large ...
null Weichao Qiu +4 more
openaire +2 more sources
Bildverarbeitung, 2011 Vor dem Hintergrund der fraktalen Geometrie wird in diesem Kapitel das scale space filtering erlautert. Dabei wird eine Oberflache in unterschiedlichen „ Vergroserungen“ betrachtet und untersucht, ob dabei sich wiederholende Strukturen auftreten. Als praktische Anwendung hat diese Technik gute Ergebnisse bei der Qualitatskontrolle von Oberflachen, z.B.
Alfred Nischwitz +3 more
openaire +2 more sources
International Joint Conference on Artificial Intelligence, 1987
The extrema in a signal and its first few derivatives provide a useful general-purpose qualitative description for many kinds of signals. A fundamental problem in computing such descriptions is scale: a derivative must be taken over some neighborhood, but there is seldom a principled basis for choosing its size.
A. Witkin
openaire +2 more sources
The extrema in a signal and its first few derivatives provide a useful general-purpose qualitative description for many kinds of signals. A fundamental problem in computing such descriptions is scale: a derivative must be taken over some neighborhood, but there is seldom a principled basis for choosing its size.
A. Witkin
openaire +2 more sources
Scale-Space Flow for End-to-End Optimized Video Compression
Computer Vision and Pattern Recognition, 2020Despite considerable progress on end-to-end optimized deep networks for image compression, video coding remains a challenging task. Recently proposed methods for learned video compression use optical flow and bilinear warping for motion compensation and ...
E. Agustsson +5 more
semanticscholar +1 more source
Gaussian Scale-Space Enhanced Local Contrast Measure for Small Infrared Target Detection
IEEE Geoscience and Remote Sensing Letters, 2020Robust small-target detection plays an important role in the infrared (IR) search and track system, but it is still a challenge to detect small IR target under complex background. In this letter, an effective method inspired by the scale-space theory and
Xuewei Guan +3 more
semanticscholar +1 more source
Image and Vision Computing, 1994
A generalization of linear Gaussian scale-space theory for scalar images is proposed, based on a particular type of metric transform preserving the intrinsic properties of the spatial domain. The existence of such a transformation defines an equivalence class.
Florack, Luc +4 more
openaire +1 more source
A generalization of linear Gaussian scale-space theory for scalar images is proposed, based on a particular type of metric transform preserving the intrinsic properties of the spatial domain. The existence of such a transformation defines an equivalence class.
Florack, Luc +4 more
openaire +1 more source
Scale-space approximated convolutional neural networks for retinal vessel segmentation
Comput. Methods Programs Biomed., 2019BACKGROUND AND OBJECTIVE Retinal fundus images are widely used to diagnose retinal diseases and can potentially be used for early diagnosis and prevention of chronic vascular diseases and diabetes.
Kyoung Jin Noh, S. Park, Soochahn Lee
semanticscholar +1 more source
Pseudo-Linear Scale-Space Theory
International Journal of Computer Vision, 1999It has been observed that linear, Gaussian scale-space, and nonlinear, morphological erosion and dilation scale-spaces generated by a quadratic structuring function have a lot in common. Indeed, far-reaching analogies have been reported, which seems to suggest the existence of an underlying isomorphism. However, an actual mapping appears to be missing.
Florack, L.M.J., Maas, R., Niessen, W.J.
openaire +3 more sources
A Dynamic Scale–Space Paradigm
Journal of Mathematical Imaging and Vision, 2001zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Salden, A.H. +2 more
openaire +3 more sources
From Gaussian scale-space to B-spline scale-space
1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258), 1999The Gaussian kernel has long been used in the classical multiscale analysis. The purpose of the paper is to propose the uniform B-spline as an alternative for the visual modeling. A general framework for various scale-space representations is formulated using the B-spline approach.
Wang, Yu-Ping, Lee, S.L.
openaire +1 more source