1. At first create a new folder and save it by .py extension.

2. Click on the terminal -> New terminal option.

3. Now enter the following two commands in the terminal section.

   # pip install opencv-python

   # pip install numpy

4. After that start typing the following code :

##importing opencv library   
import cv2    
##imorting numpy library as np                                                      
import numpy as np                                                 
##capturing frames from webcam
cap = cv2.VideoCapture(0)                                          

for i in range(60):   
     ##capture the background of range 60                                        
     ##dedicated to  bachground frame so that it could easily save the background image
     ret, background = cap.read()                                   
    if ret == False:
        continue
while True:
    ret,frame=cap.read()
    ##convert the color space from BGR to HSV
    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)                   
    
    ##Generate mask to detect blue color
    ##It works for blue color
    ## range of HSV value of colour (If something of that colour comes it becomes invisible)
    lb = np.array([110,50,50])                                    
    mask = cv2.inRange(hsv, lb, ub)

    #Dilate Filter
    ##basic image processing operator for accuracy
    mask = cv2.dilate(mask, np.ones((3, 3), np.uint8), iterations = 1)     

    #Closing Filter
    kernal = np.ones((3, 3), np.uint8)
    ##basic image processing operator for accuracy
    mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, kernal)             

    mask1 = cv2.bitwise_not(mask)
    
    ##generating the final output
    res1 = cv2.bitwise_and(background, background, mask = mask) 
    res2 = cv2.bitwise_and(frame, frame, mask = mask1)                    
    final_output = cv2.addWeighted(res1, 1, res2, 1, 0)    
    ##0 means saved video and if from webcam then 1                
    cv2.imshow('result',final_output)
    ## waitkey means setting the frame rate and q is the escapeor exit key
    if cv2.waitKey(25) & 0xFF == ord('q'):                              
         break