Describing SURF features

The SURF algorithm, discussed in the preceding recipe, defines a location and a scale for each of the detected features. This scale factor can be used to define the size of a window around the feature point such that the defined neighborhood would include the same visual information no matter what scale the object to which the feature belongs has been pictured. In addition, the visual information included in this neighborhood can be used to characterize the feature point to make it distinguishable from the others.

This recipe will show you how to describe a feature point's neighborhood using compact descriptors. In feature matching, feature descriptors are usually N-dimensional vectors that describe a feature point, ideally ...

Get OpenCV 2 Computer Vision Application Programming Cookbook now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.