Dear friends of the SO community,
Hope you all welcome me to SO.
I just wanted to learn about function detectors, descriptors, and helpers.
I understood with the help of detectors and descriptors after my research work and found out that descriptors are used to describe the detectors found in the image. Descriptors must be rotatable, orientational, and large. Each descriptor has a corresponding detector, but not vice versa, since each function cannot be described using a descriptor. A clear explanation on this topic is described in opencv.org docs, and I read it.
Here are my doubts
After reading this binary descriptor guide
https://gilscvblog.com/2013/08/26/tutorial-on-binary-descriptors-part-1/
I understood what it is. In short
1) 512 Pairs of the patch in image A
2) Compare the intensity of each pair with the 1st value and with the second value in the pair. If the 1st value is greater than 1, or 0.
3) Now we will have about 512 binary digits of 1 and 0. Let it be
101010101010101010.....10101010
4) Repeat the above 3 steps on the patch with another image “B”, and also we have 512 binary digits. Let them say that
010101010101010101.....01010101
5) Now do the distance between these two binary strings (XOR operation)
6) Result after performing interference interval
111111111111111111.....11111111
Here are my questions?
1) What happens after this step?
2) How lines are drawn from one image to another image. I found out that we are using some kind of distance, matching something like that.
Feature Matching
, , (- - ).
.