T
Tony Lindeberg
Researcher at Royal Institute of Technology
Publications - 169
Citations - 17027
Tony Lindeberg is an academic researcher from Royal Institute of Technology. The author has contributed to research in topics: Scale space & Scale (ratio). The author has an hindex of 50, co-authored 165 publications receiving 16241 citations. Previous affiliations of Tony Lindeberg include Microsoft.
Papers
More filters
Journal ArticleDOI
Invariance of visual operations at the level of receptive fields
TL;DR: The framework provides a mathematically well-founded and biologically plausible model for how basic invariance properties can be achieved already at the level of receptive fields and support invariant recognition of objects and events under variations in viewpoint, retinal size, object motion and illumination.
Journal ArticleDOI
Idealized computational models for auditory receptive fields
Tony Lindeberg,Anders Friberg +1 more
TL;DR: It is demonstrated how the presented framework allows for computation of basic auditory features for audio processing and that it leads to predictions about auditory receptive fields with good qualitative similarity to biological receptive fields measured in the inferior colliculus and primary auditory cortex of mammals.
Book ChapterDOI
Scale-Space for N-Dimensional Discrete Signals
TL;DR: This article shows how a (linear) scale-space representation can be defined for discrete signals of arbitrary dimension by convolving the original signal with a one-parameter family of symmetric smoothing kernels possessing a semi-group property.
Book ChapterDOI
Linear scale-space: II. early visual operations
TL;DR: A catalogue has been provided of what filter kernels are natural to use, as well as an extensive theoretical explanation of how different kernels of different orders and at different scales can be related, which forms the basis of a theoretically well-founded modeling of visual front-end operators with a smoothing effect.
Journal ArticleDOI
On scale and resolution in active analysis of local image structure
TL;DR: It is shown that foveation as simulated by controlled, active zooming in conjunction with scale-space techniques allows for robust detection and classification of junctions.