Revision history [back]

by default, a 1 nearest neighbour distance is used (that would be Rank 1, i guess)

but you can implement your own scoring scheme by accessing the complete results from the prediction

something like:

Ptr<PredictCollector> collector = StandardCollector::create();
recognizer->predict( img, collector );
std::vector< std::pair<int, double> >  = collector->getResults();

by default, a 1 nearest neighbour distance is used (that would be Rank 1, i guess)1)

but you can implement your own scoring ranking scheme by accessing the complete results from the prediction

something like:

Ptr<PredictCollector> collector = StandardCollector::create();
recognizer->predict( img, collector );
std::vector< std::pair<int, double> >  = collector->getResults();