Handbook of Mathematical Models in Computer Vision

700 citations recorded by the source corpus.

How researchers see this paper

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

A Fast Algorithm for Edge-Preserving Variational Multichannel Image Restoration (2009, methodology): “For comparison, the “color-TV” proposed in [2] is It is easy to see from (2.1) and (2.2) that both MTV and CTV preserve the two basic properties of (1.5), namely, i) not overly penalizing discontinuities and ii) rotationally invariant.”
Dense image registration through MRFs and efficient linear programming (2008, methodology): “In particular, the graph-cut algorithm [2] which refers to an efficient implementation of the max-flow/min-cut approach in regular image grids has boosted the attention of the vision communities in MRFs.”
Localizing Region-Based Active Contours (2008, neutral): “A CTIVE contour methods have become very popular in recent years, and have found applications in a wide range of problems including visual tracking and image segmentation; see [1]–[4] and the references therein.”
An Augmented Lagrangian Approach to the Constrained Optimization Formulation of Imaging Inverse Problems (2009, background): “Arguably, the bes t known and most often used regularizer in analysis approache s to image restoration is the total variation (TV) norm [15], [ 47].”
Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis (2013, methodology): “However, because it is restrained by the optical 3In our approach, each region is described using V1-like features [33], which are effective biologically-inspired image descriptors.”