This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
There is no evident size of "patch" around descriptors for SIFT. The number of octave is deduce from the image resolution, but if you only need a debug/feedback visualization, used the size you want... It doesn't really matter, as your patches are centered around the keypoints. If you want to do it fast, I suggest using a ROI to copy the parts of image to a destination buffer.
