Scale-space filtering: A new approach to multi-scale description

By Andrew P. Witkin. 1984

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Signal Processing

Citations in the corpus

Holistically-Nested Edge Detection (2015, background): “This integrated learning of hierarchical features is in distinction to previous multi-scale approaches (Witkin 1984; Yuille and Poggio 1986; Ren 2008) in which scalespace edge fields are neither automatically learned nor hierarchically connected.”
An Analysis of Scale Invariance in Object Detection - SNIP (2017, background): “Scale space theory [35, 26] advocates learning representations that are invariant to scale and the theory has been applied to many problems in the history of computer vision [4, 30, 28, 21, 14, 5, 23].”
Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection (2022, methodology): “Firstly, for accurate object location, we employ scale space theory [23, 24, 43] to imitate zooming in and out strategy.”
Segmentation of blood vessels from red-free and fluorescein retinal images (2007, methodology): “The use of Gaussian kernels to generate multiscale information ensures that the image analysis is invariant with respect to translation, rotation and size (Koenderink, 1984; Witkin, 1984).”
Clustering by Scale-Space Filtering (2000, methodology): “For example, the scale-space theory is developed in image and signal processing [22], [ 23 ], [24], [25], [26], [27], [28].”
Multi-scale object candidates for generic object tracking in street scenes (2016, background): “This step is motivated by results from scale-space filtering [32], namely that the most scale-stable proposals also tend to be the most salient ones.”
Quantitative analysis of cryo-EM density map segmentation by watershed and scale-space filtering, and fitting of structures by alignment to regions (2010, methodology): “2 Grouping of regions by scale-space filtering—The process of successively smoothing a signal is known as scale-space filtering [17].”
AutoFocus: Efficient Multi-Scale Inference (2018, background): “Image pyramids [67] and convolutional neural networks [34] are fundamental building blocks in the computer vision pipeline.”