Blend (mix) refers to mixing images with a weighted sum of 1



In [1]:

    
import cv2



In [2]:

    
import matplotlib.pyplot as plt



In [3]:

    
img1 = cv2.imread('demo1.jpg', cv2.IMREAD_GRAYSCALE)



In [4]:

    
img2 = cv2.imread('nature.jpg', cv2.IMREAD_GRAYSCALE)



In [5]:

    
plt.figure(figsize=(10,8))









    Out[5]:





<matplotlib.figure.Figure at 0x7f99679ecd68>



In [6]:

    
plt.subplot(1,2,1)









    Out[6]:





<matplotlib.axes._subplots.AxesSubplot at 0x7f99679ecd30>



In [7]:

    
plt.title('Shooter')









    Out[7]:





<matplotlib.text.Text at 0x7f9967709320>



In [8]:

    
plt.imshow(img1, cmap='gray')









    Out[8]:





<matplotlib.image.AxesImage at 0x7f99676b3278>



In [9]:

    
plt.subplot(1,2,2)









    Out[9]:





<matplotlib.axes._subplots.AxesSubplot at 0x7f99676b3320>



In [10]:

    
plt.title('Nature')









    Out[10]:





<matplotlib.text.Text at 0x7f9967683be0>



In [11]:

    
plt.imshow(img2, cmap='gray')









    Out[11]:





<matplotlib.image.AxesImage at 0x7f99676367b8>



In [12]:

    
plt.show()

Say we want more of nature than shooter, let alpha = 0.3 for shooter. Therefore, for nature, it will be 1 - alpha = 0.7



In [13]:

    
alpha = 0.3



In [14]:

    
img = (alpha*img1) + ((1-alpha)*img2)



In [15]:

    
plt.imshow(img, cmap='gray')









    Out[15]:





<matplotlib.image.AxesImage at 0x7f99644b5ef0>



In [16]:

    
plt.show()

See, isn't it look like a camouflaged shooter in nature. Similarly, we can play with the alpha value to get the desired blend of images