How to blend multiple images in OpenCV? - c++

Question

I have group of images and associated weights with it. I want to blend them together. I know there is a blend command in OpenCV to blend two images. But how do I blend multiple images together?

Answer 1

The blending can be done using the below code(This is in Java using OpenCV):
//Create a black-colored image
Mat mergedImage = new Mat(inputImageSize, inputImageType, new Scalar(0));
//Add each image from a vector<Mat> inputImages with weight 1.0/n where n is number of images to merge
for (Mat mat : inputImages) {
Core.addWeighted(mergedImage, 1, mat, 1.0/n, 0, mergedImage);
}
Edit:- The above code suffers from rounding error. If inputImageType is an integer type, division by 1/n will cause this issue. Thus, above code should be used only for floating matrices.

Answer 2

What about simple matrix operations, like the following?
blendedImage = weight_1 * image_1 + weight_2 * image_2 + ... + weight_n * image_n

Answer 3

Here is Python code to blend multiple images in a list. I used the basic formulation from Dennis' answer.
First, let's get three images.
import numpy as np
import cv2
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
dim = (425, 425)
apple = mpimg.imread('apple.jpg')
apple = cv2.resize(apple, dim)
banana = mpimg.imread('banana.jpg')
banana = cv2.resize(banana, dim)
orange = mpimg.imread('orange.jpg')
orange = cv2.resize(orange, dim)
_ = plt.imshow(apple)
_ = plt.show()
_ = plt.imshow(banana)
_ = plt.show()
_ = plt.imshow(orange)
_ = plt.show()
Here are the images:
Now let's blend them together equally. Since there are three images, the fraction of each image's contribution to the final output is 0.333.
def blend(list_images): # Blend images equally.
equal_fraction = 1.0 / (len(list_images))
output = np.zeros_like(list_images[0])
for img in list_images:
output = output + img * equal_fraction
output = output.astype(np.uint8)
return output
list_images = [apple, banana, orange]
output = blend(list_images)
_ = plt.imshow(output)
And here is the result: