In evaluate.cpp file
computeRecallPrecisionCurve( const std::vector<std::vector<DMatch> >& matches1to2,
const std::vector<std::vector<uchar> >& correctMatches1to2Mask,
std::vector<Point2f>& recallPrecisionCurve )
class is used to calculate ROC curve for feature matching for benchmark estimation. How did it works, How the correctmatches1tomask is calculated.