Python Image Processing Cookbook

How to do it...

Follow these steps to implement the ECC algorithm using OpenCV-Python:

1. Since the color channels of an image are correlated more strongly in the gradient than in the intensity domain, we will run the ECC algorithm in the gradient domain. Define the get_gradient() function, which you will use shortly:

def get_gradient(im) : grad_x = cv2.Sobel(im,cv2.CV_32F,1,0,ksize=3) grad_y = cv2.Sobel(im,cv2.CV_32F,0,1,ksize=3) grad = cv2.addWeighted(np.absolute(grad_x), 0.5, \                np.absolute(grad_y), 0.5, 0) return grad

2. Read the input RGB image and plot the original image and its unaligned color channels:

im_unaligned = cv2.imread("images/me_unaligned.jpg")height, width = im_unaligned.shape[:2]print(height, width)# 992 610channels = ['B', ...