Let's write a code that demonstrates the ORB feature detection and binary descriptor algorithm. An oriented FAST detection method and the rotated BRIEF descriptors are used by this algorithm. As compared to BRIEF, ORB is more scale and rotation invariant, but even this applies the Hamming distance metric for matching, which is more efficient. Hence, this method is preferred over BRIEF when considering real-time applications:
from skimage import transform as transformfrom skimage.feature import (match_descriptors, ORB, plot_matches)img1 = rgb2gray(imread('../images/me5.jpg'))img2 = transform.rotate(img1, 180)affine_trans = transform.AffineTransform(scale=(1.3, 1.1), ...