Active unsupervised texture segmentation on a diffusion based feature space

By Mikaël Rousson, Thomas Brox, Rachid Deriche. 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings., 2003

299 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/33d497f31e81a5e2890fc94e0ecb134e0cc333ae

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

Kernel Density Estimation and Intrinsic Alignment for Shape Priors in Level Set Segmentation (2006, background): “…al., 1995; Caselles et al., 1995; Kichenassamy et al., 1995), intensity homogeneity (Chan and Vese, 2001; Tsai et al., 2001), texture information (Paragios and Deriche, 2002; Rousson et al., 2003; Heiler and Schnörr, 2003; Brox and Weickert , 2004) and motion information (Cremers and Soatto, 2005).”
Natural Image Statistics for Natural Image Segmentation (2003, unknown): “, 2003) and non-parametric models (Tang and Ma, 2001; Rousson et al., 2003) come into play.”
A Review of Statistical Approaches to Level Set Segmentation: Integrating Color, Texture, Motion and Shape (2007, methodology): “For results on a wider range of texture images, we refer to [73].”
Robust Variational Segmentation of 3D Objects from Multiple Views (2006, methodology): “A similar energy functional was used in [2,16] for image segmentation purposes.”
An efficient local Chan-Vese model for image segmentation (2010, background): “Unfortunately, Gabor filters have the fatal drawback that they induce a lot of redundancies and thus lots of feature channels [30].”
Finding areas of motion in camera trap images (2016, background): “In 2003, scientists estimated that there are between 4,500 and 7,350 snow leopards in the wild, although this estimate may be too low because as population studies have expanded over the past decade, scientists are often finding more cats than expected [2].”
Active contours driven by local Gaussian distribution fitting energy (2009, methodology): “There are various approaches to model the probability densities pi;xðIðyÞÞ, including Gaussian density with fixed standard deviation [11], a full Gaussian density [32,15], or non-parametric Parzen estimator [33,34].”