OpenCV 3 Computer Vision with Python Cookbook

How to do it...

You need to complete the following steps:

1. Import the modules:

import cv2import numpy as np

2. Generate an initial points set. Then create a set of rotated points by applying a rotation matrix to the initial points. Also, add a portion of noise to our rotated points:

pts = np.random.multivariate_normal([150, 300], [[1024, 512], [512, 1024]], 50)rmat = cv2.getRotationMatrix2D((0, 0), 30, 1)[:, :2]rpts = np.matmul(pts, rmat.transpose())rpts_noise = rpts + np.random.multivariate_normal([0, 0], [[200, 0], [0, 200]], len(pts))

3. Solve the orthogonal Procrustes problem using Singular Value Decomposition (SVD) and get an estimate of the rotation matrix:

M = np.matmul(pts.transpose(), rpts_noise)sigma, u, v_t = cv2.SVDecomp(M)rmat_est ...