OpenCV Q&A Forum - RSS feedhttp://answers.opencv.org/questions/OpenCV answersenCopyright <a href="http://www.opencv.org">OpenCV foundation</a>, 2012-2018.Mon, 04 Dec 2017 22:01:04 -0600face recognition by Euclidean space distance seeking for helphttp://answers.opencv.org/question/179732/face-recognition-by-euclidean-space-distance-seeking-for-help/In the n dimensional Euclidean space,
If
The first point is **P1 [x1,x2,...,xn]**
The second point is **P2 [y1,y2,...,yn]**
so ，the Euclidean space distance from P1 to P2 is
**d(P1,P2) = sqrt ( (x1-y1)^2 + (x2-y2)^2 + ... + (xn-yn)^2 )**
so , in the face recognition field , for example , in many open source ，
every point have x coordinate value and y coordinate value ,
I think it is ,
The first face is **P1 [(x1,y1),(x2,y2),...,(xn,yn)]**
The second face is **P2 [(a1,b1),(a2,b2),...,(an,bn)]**
so ，the Euclidean space distance from P1 to P2 is ________________________________ ?
the result is too complex , even is unsolvable .
I don't know if I have a problem with my understanding ?strivingMon, 04 Dec 2017 22:01:04 -0600http://answers.opencv.org/question/179732/OpenCV Distance Metricshttp://answers.opencv.org/question/4601/opencv-distance-metrics/Hello everyone, I'm doing a benchmark test on keypoint detectors, descriptors and matching of those for a research project. I'm aware that there are great benchmark tests out there but this will be done for a specific experimental environment. Descriptors will be Orb and Freak and detectors are ORB, SURF and maybe FAST. I will use BruteForceMathcer.
So, in order to make the test fair, I decided I will use approximately same amount of keypoints and the same distances. But I can't seem to find a detailed explanation of the distance metrics used in opencv.
For instance; when I use "BruteForceMatcher<L2<float> > matcher;" when both keypoint detector and descriptor is orb, it gives me a correct match between two points with coordinates point1(130,339) and point2(130,340). Obviously the distance between those two is 1, but when I look at the matches vector, the distance value is 272.71964 which is very confusing for me.
My question is, is there any documentation that explains why this is the case? I googled it, but haven't found a decent explaination. If not, I would really appreciate if you could explain this.
Thank youaliciadominicaTue, 27 Nov 2012 02:47:13 -0600http://answers.opencv.org/question/4601/