python image detection on screen

I'm trying to detect images on desktop screen. Here is my code below.

import cv2
import numpy as np
MIN_MATCH_COUNT=30

detector = cv2.xfeatures2d.SIFT_create()

FLANN_INDEX_KDITREE=0
flannParam=dict(algorithm=FLANN_INDEX_KDITREE,tree=5)
flann=cv2.FlannBasedMatcher(flannParam,{})

trainImg=cv2.imread("xxx.png",0)
trainKP,trainDesc=detector.detectAndCompute(trainImg,None)

cam=cv2.VideoCapture(0)
while True:
    ret, QueryImgBGR=cam.read()
    QueryImg=cv2.cvtColor(QueryImgBGR,cv2.COLOR_BGR2GRAY)
    queryKP,queryDesc=detector.detectAndCompute(QueryImg,None)
    matches=flann.knnMatch(queryDesc,trainDesc,k=2)

    goodMatch=[]
    for m,n in matches:
        if(m.distance<0.75*n.distance):
            goodMatch.append(m)
    if(len(goodMatch)>MIN_MATCH_COUNT):
        tp=[]
        qp=[]
        for m in goodMatch:
            tp.append(trainKP[m.trainIdx].pt)
            qp.append(queryKP[m.queryIdx].pt)
        tp,qp=np.float32((tp,qp))
        H,status=cv2.findHomography(tp,qp,cv2.RANSAC,3.0)
        h,w=trainImg.shape
        trainBorder=np.float32([[[0,0],[0,h-1],[w-1,h-1],[w-1,0]]])
        queryBorder=cv2.perspectiveTransform(trainBorder,H)
        cv2.polylines(QueryImgBGR,[np.int32(queryBorder)],True,(0,255,0),5)
    cv2.imshow('result',QueryImgBGR)
    if cv2.waitKey(10)==ord('q'):
        break
cam.release()
cv2.destroyAllWindows()

This code basically detects images from the webcam. But I want to change the code to detect images from the screen. How should I change my code?

I could think of two approaches,

  1. Capture a screenshot of desktop and detect images from the capture.
  2. real time image detection from the screen.

I think 2nd approach would be better but i have no idea for these 2 cases. Or if there is a better method or code, please let me know.

Thank you.