Natural Image Statistics for Natural Image Segmentation

By Matthias Heiler, Christoph Schnörr. 2003

550 citations recorded by the source corpus.

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

Finely-grained annotated datasets for image-based plant phenotyping (2016, methodology): “Our datasets can be used to learn suitable image statistics (Heiler and Schn¨orr, 2005), adapt and test counting algorithms with (Fiaschi et al., 2013) and without temporal information (Arteta et al., 2013; Lempitsky and Zisserman, 2010), segmentation algorithms (Chan and Vese, 2001), multi-label…”
Oriented edge forests for boundary detection (2014, background): “We chose the orientation binning so that bins 1 and 5 are centered at 90 and 0 degrees respectively, as these orientations are especially common in natural images [21].”
Kernel Density Estimation and Intrinsic Alignment for Shape Priors in Level Set Segmentation (2006, background): “Applications of explicit statistical shape models in image segmentation were among others proposed in Grenander et al. (1991) , Cootes et al. (1995), Cremers et al. (2002), Mio et al. (2004), Cremers et al. (2003).”
A nonparametric statistical method for image segmentation using information theory and curve evolution (2005, unknown): “In particular, the technique proposed by Heiler et al. [19] is motivated by recent work on natural image statistics [33], [20], and is based on parametric modeling of filter responses by generalized Laplacian distributions.”
Why does natural scene categorization require little attention? Exploring attentional requirements for natural and synthetic stimuli (2005, methodology): “The superb efficiency of this task has stimulated much research across the fields of neural psychophysics, physiology, and modelling (Biederman, 1972; Li et al., 2002; Potter & Levy, 1969; Thorpe, Fize, & Marlot, 1996; Torralba & Oliva, 2003; VanRullen & Thorpe, 2001).”
Annotated Image Datasets of Rosette Plants (2014, methodology): “We also do hope that this dataset and its future versions, would be used from the computer vision community to learn suitable image statistics [19], adapt and test counting algorithms with [20] and without temporal information [21, 22, 23], segmentation algorithms [24, 25, 26, 27, 28], multi-label s”
Shared Segmentation of Natural Scenes Using Dependent Pitman-Yor Processes (2008, background): “When examining low-level intensity statistics, power laws naturally arise from scale invariance properties [21].”
A Review of Statistical Approaches to Level Set Segmentation: Integrating Color, Texture, Motion and Shape (2007, background): “And in Heiler and Schnoerr (2003), the authors point out that the additional terms are negligible in the case of Laplacian distributions.”
TouchCut: Fast image and video segmentation using single-touch interaction (2014, unknown): “[32] also adopt Laplacan distributions for natural image segmentation.”
How long to get to the “gist” of real-world natural scenes? (2005, background): “Aside from colour, several combinations of low-level scene-based properties could potentially explain how subjects classified pictures in these two experiments (Oliva & Torralba, 2001; Torralba & Oliva, 2003).”