SiftDescriptorExtractor

I have 2 questions about opencv SiftDescriptorExtractor:

  • How to convert descriptors from cv::Matto vector<float* >(i-th line = i-th descriptor)
  • How to determine the size (= dimension) of a SIFT descriptor?

Yes, I know the link to OpenCV, however I cannot get it to work. Can someone put a minimal working PLS example here?

+5
source share
2 answers

1-Conversion:

vector<float*> descriptor;
for(int i; i = 0; i < keypoints.size())
{
    descriptor.push_back(&keypoints.at<float>(i));
}

2-size SIFT:

You cannot, because the SIFT algorithm determines the size of blocks, bins, etc. What can you do? You can program your own screener. This is a difficult path, but I recommend you try it.

+6
source
+1

All Articles