Fast Anisotropic Gauss Filtering

By Jan-Mark Geusebroek, Arnold M. W. Smeulders, Joost van de Weijer. 2002

402 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Environmental Engineering

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Environmental Engineering

Citations in the corpus

Describing Textures in the Wild (2013, methodology): “The first one is the use of the SIFT descriptors, originally developed for object matching [20], that are more distinctive that local descriptors popular in texture analysis such as filter banks [13, 19, 36], local intensity patterns [23], and patches [35].”
Spherical Tensor Calculus for Local Adaptive Filtering (2009, methodology): “In [4] a technique for fast anisotropic filtering in 2D is proposed, unfor tunately the idea is not extendable to 3D.”
Visual Tracking: an Experimental Survey (2013, neutral): “Color invariants [81] reduce the influence of the fluctuations in the illumination, which play an important role in tracking [62], for which fast implementations [82], [83] exist.”
Lesion border detection in dermoscopy images (2009, methodology): “• Computational time: For the GF and MF, algorithms that perform in constant time independent of the mask size have been developed [13, 14].”
Deep Filter Banks for Texture Recognition, Description, and Segmentation (2015, methodology): “The filter bank MR8 of [41, 97] consists instead of 38 filters, similar to LM.”
Constant time O(1) bilateral filtering (2008, methodology): “This can be done by using of either an eigenvalue expansion of the 2D kernel [3] or application of Singular Value Decomposition [2].”
Multimodal Video Indexing: A Review of the State-of-the-art (2004, methodology): “Hidden Markov Models are frequently used as a statistical classification method for multimodal integration [2, 19, 20, 32].”
Learning Where to Classify in Multi-view Semantic Segmentation (2014, neutral): “This is a 16-dimensional feature vector containing the CIELAB Lab∗ color components, 8 responses of the MR8 filter bank [46, 47] in vector t, the height h defined as the distance from the ground plane, the depth d w.”
Empowering Visual Categorization With the GPU (2011, methodology): “Using recursive Gaussian filters [30], the computation of Gaussian derivatives at multiple scale required for these steps is possible”