Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention

By Tony Lindeberg. 1993

How researchers see this paper

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

Citations in the corpus

Beyond Gaussian Pyramid: Multi-skip Feature Stacking for action recognition (2014, methodology): “A multiscale key-point detector proposed by Lindeberg [14] and used in by Lowe [16] to detect scale invariant key points using Laplacian pyramid methods, in which Gaussian smoothing is used iteratively for each pyramid level.”
utomation of 3 D reconstruction of neural tissue from large volume of onventional serial section transmission electron micrographs (2008, background): “…over the kerel domain, and x is a point in the kernel domain), GSH admits ifferent normalizations such as C( ) = 1(G unity normalization), ( ) = 2/∑ |H ( x)| (band-pass normalization), C( ) = 3/4(scale pace analysis of ridges, Lindeberg, 1999), C( ) = 2 (derivatives imension, Lindeberg, 1993), etc.”
Linear scale-space (1994, methodology): “9 ) Interpolating for zero - crossings of I vv within the sign - constraints of I vvv gives a straightforward method for sub - pixel edge detection ( Lindeberg 1993 ) ; see gure 2 .”
Distinctive Image Features from Scale-Invariant Keypoints Abstract by Matthijs Dorst Based on the paper by (2011, methodology): “For scale selection work by Lindeberg [10][11] was used.”
Sampling Strategies for Bag-of-Features Image Classification (2006, unknown): “Laplacian of Gaussian (LoG): a multi-scale keypoint detector proposed by [21] and popularized by [8].”
Building the gist of a scene: the role of global image features in recognition. (2006, background): “Therefore, one cannot dismiss the possibility that the analysis of fine contours and texture characteristics could be performed at the very early stage of scene perception, either because low spatial frequency luminance boundaries bootstrap the perceptual organization of finer contours (Lindeberg, 1”
A Galaxy of Texture Features (2008, background): “(39) Voronoi tessellation (−♥ − −) Voronoi tessellation, introduced by Ahuja, 86 divides a domain into a number of polygonal regions based on a set of given points in this domain.”
Scale & Affine Invariant Interest Point Detectors (2004, unknown): “Many previous results confirm the usefulness of the Laplacian function for scale selection (Chomat et al., 2000; Lindeberg, 1993, 1998; Lowe, 1999).”
DeepFruits: A Fruit Detection System Using Deep Neural Networks (2016, methodology): “In order to have a fair comparison with the bounding box outputs of Faster R-CNN, we use a Laplacian of Gaussian (LoG) multi-scale blob detector [37] for the CRF-based method to produce detected fruit regions (i.e., bounding boxes).”
Human Detection Based on a Probabilistic Assembly of Robust Part Detectors (2004, background): “An excellent blob detector is the Laplacian operator [9].”
An Affine Invariant Salient Region Detector (2004, methodology): “Recently, inspired by the pioneering work of Lindeberg [14], scale and affine adapted versions have been developed [2, 18–20].”
Contextual Priming for Object Detection (2003, methodology): “For instance, Lindeberg (1993) proposed a method for scale selection for the detection of low-level features such as edges, junctions, ridges and blobs when no a priori information about the nature of the picture is available.”
Distinctive Image Features from Scale-Invariant Keypoints (2004, background): “The problem of identifying an appropriate and consistent scale for feature detection has been studied in depth by Lindeberg (1993, 1994).”