How to use flann based matcher, or generally flann in opencv?

Question

http://opencv.willowgarage.com/documentation/cpp/features2d_common_interfaces_of_descriptor_matchers.html#flannbasedmatcher

Please can somebody show me sample code o

Answer 1

To reduce the number of false positives, you can compare the first most nearest neighbor to the second most nearest neighbor by taking the ratio of there distances. distance(query,mostnearestneighbor)/distance(query,secondnearestneighbor) < T, the smaller the ratio is, the higher the distance of the second nearest neighbor to the query descriptor. This thus is a translation of high distinctiveness. Used in many computer vision papers that envision registration.