Hello,
I have do some research about features detection and I manage to use ORB,SURF,SIFT correctly to dectect objects. But now, I have to write some explanation about how it works. I resume the work in few steps.
- Detect Keypoints in image and template
- Create Descriptors from the Keypoints
- Matches the descriptors of image and template
- Keep goodKeypoints from the matches
- Find object from the good Keypoints
But there is some points I can't explain very well. What is a Keypoint ? What represent the descriptor of a Keypoint ?
For me a Keypoint is a point of interest detected thanks to methods(SURF,ORB,etc...) which is equivalent to point of interest a human being can see in a image, but i'm not sure if it's the correct definition.
Best regards