Image Similarity Using Mutual Information of Regions

By Daniel B. Russakoff, Carlo Tomasi, Torsten Rohlfing, Calvin R. Maurer Jr.. European Conference on Computer Vision, 2004

336 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/07b504c43c362738d07febc0a89040f9dffd28a5

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

Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool (2015, methodology): “Later, Russakoff et al. [32] used the MI as a similarity measure between image segmentations; in particular, they calculate the MI based on regions (segments) instead of individual pixels.”
Medical image registration: a review (2014, methodology): “Other solutions based on MI have also been proposed in Russakoff et al. (2004), Studholme et al. (2006), by deﬁning a regional MI, and in Loeckx et al. (2010), using the conditional MI. MI has proven to be a very robust and reliable similarity measure for intensity-based registration of multimodal…”
Text feature extraction based on deep learning: a review (2017, methodology): “Since this method does not require any hypotheses on the property of relationship between feature words and classes, it is exceedingly suitable for the registration of features of text classification and classes [14].”
Deformable Medical Image Registration: A Survey (2013, background): “[280] introduced Regional Mutual Information that pushed forward the previous idea by taking into account co-occurrences between regions.”
The SRI24 Multi-Channel Atlas of Normal Adult Human Brain Structure (2009, methodology): “To avoid the common issues with sparse histograms, our algorithm takes advantage of the fact that under certain assumptions, the marginal and joint entropies of the registered image channels are proportional to the determinants of appropriately computed covariance matrices [Russakoff et al., 2004].”
An Efficient Algorithm for Calculating the Exact Hausdorff Distance (2015, background): “Measures in the last two categories are known to be robust, but not sensitive to the spatial positions of the points and thus not suitable for applications where the positions of the individual points are important [23].”