Scale-Space Theory in Computer Vision¶
Lindeberg, T. (1994). Scale-Space Theory in Computer Vision. Kluwer Academic.
Cited by¶
2 citations across 2 artifacts.
Each citation links to the sentence it supports in the citing article.
Domain-specific¶
- Coastline Paradox
- and atlas disputes often reduce to a resolution disagreement. Surface-area estimation in materials and biology — porous catalysts, lung alveoli, coral, and root systems generalize the framework to surfaces with 2 < D < 3, where the "ruler" becomes the molecular probe of a BET adsorption measurement. Topography and remote sensing — terrain-ruggedness indices are scale-conditioned quantities keyed to pixel size, so a reported roughness requires its resolution. Catchment hydrology — total stream length used in hydrological modeling shifts with DEM resolution, the same drainage network yielding different totals at different scales. Image analysis and computer vision — edge- and contour-length measurements in segmentation pipelines are ruler-dependent, and scale-space analysis (Witkin, Lindeberg) is the principled response.
Supported in partVerified against a saved copy of the source
“"Scale-Space Theory in Computer Vision" describes a formal theory for representing the notion of scale in image data, and shows how this theory applies to essential problems in computer vision such as computation of image features and cues to surface shape.”
- and atlas disputes often reduce to a resolution disagreement. Surface-area estimation in materials and biology — porous catalysts, lung alveoli, coral, and root systems generalize the framework to surfaces with 2 < D < 3, where the "ruler" becomes the molecular probe of a BET adsorption measurement. Topography and remote sensing — terrain-ruggedness indices are scale-conditioned quantities keyed to pixel size, so a reported roughness requires its resolution. Catchment hydrology — total stream length used in hydrological modeling shifts with DEM resolution, the same drainage network yielding different totals at different scales. Image analysis and computer vision — edge- and contour-length measurements in segmentation pipelines are ruler-dependent, and scale-space analysis (Witkin, Lindeberg) is the principled response.
Mechanisms¶
- Gaussian Smoothing Kernel
- Each grid cell becomes a distance-weighted blend of nearby sensors, near ones dominating and far ones fading out, so the pollution "hot zones" emerge as smooth plumes instead of isolated spikes.
This sourceUses Gaussian convolution for scale-space smoothing, with influence greatest locally and decreasing with distance.
- Each grid cell becomes a distance-weighted blend of nearby sensors, near ones dominating and far ones fading out, so the pollution "hot zones" emerge as smooth plumes instead of isolated spikes.
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Read against the text for 1 of 2 citations: 1 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:e9196f10d0da · see in the full table