The Gaussian scale-space paradigm and the multiscale local jet

By Luc M. J. Florack, B. T. H. Romeny, Max A. Viergever, Jan J. Koenderink. 1996

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Fully convolutional networks for semantic segmentation (2014, background): “e them from shallower net outputs. Combining ﬁne layers and coarse layers lets the model make local predictions that respect global structure. By analogy to the multiscale local jet of Florack et al. [8], Figure 3. Our DAG nets learn to combine coarse, high layer information with ﬁne, l”
Zoom Better to See Clearer: Human Part Segmentation with Auto Zoom Net (2015, background): “…long studied by considering multiple cues, such as using 3D scene layouts (Hoiem et al., 2008), hierarchical region grouping (Arbelaez et al., 2011; Florack et al., 1996), and applying general or salient object proposals by using iterative localization, e.g., (Alexe et al., 2012; Zhu et al., 2015;…”
Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net (2015, background): “These include exploiting multiple cues [14], hierarchical region grouping [2,11], and applying general or salient object proposals combined with iterative localization [1,37,32].”
Statistical shape models for 3D medical image segmentation: A review (2009, methodology): “The most popular method to solve this problem for PDMs is the generalized Procrustes alignment (GPA), as described by Gower (1975) and Goodall (1991). The standard Procrustes match (termed after a figure from Greek mythology) minimizes the mean squared distance between two shapes and can be calculat”
Unsupervised Deep Learning Applied to Breast Density Segmentation and Mammographic Risk Scoring (2016, unknown): “Our model improved on two state-of-the-art methods in MT scoring: (i) the KNN method by Nielsen et al. [19] using multiscale local jet features [60], which so far had reported the best results on the texture dataset (results were communicated); (ii) a softmax clas-siﬁer on static histogram features…”
Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters (2019, background): “A complete set of derivatives is called LocalJet [33] and they approximate the signal in the local neighborhood as known from Taylor expansion: where g σ denotes the Gaussian of width σ centered at (cid:126)x = (cid:126) 0 , and i n denotes the direction.”
Active shape model segmentation with optimal features (2002, background): “The Taylor expansion of images is known as the local jet, or multiscale local jet in the case of the Taylor expansion of the scale-space of the image [33], [34].”
Performance evaluation of local colour invariants (2009, unknown): “Gaussian filters have interesting properties from an image processing point of view, among others, their robustness to noise [8], their rotational steerability [9], and their applicability in multi-scale settings [10].”