Feature detection (computer vision): Difference between revisions

Revision as of 16:41, 20 September 2006

Revision as of 16:42, 20 September 2006

Line 84:

|}

== [[Feature Extractionextraction]] ==

Once features have been detected, the local image patch around the feature can be extracted. This extraction may involve quite considerable amounts of image processing. The result is known as a feature descriptor or feature vector. Among the approaches that are used to feature description, one can mention [[N-jet]]s and local histograms (see [[scale-invariant feature transform]] for one example of a local histogram descriptor).