我想检查opencv中的模板是否匹配

Question

我想检查模板匹配是否正确

就像这样：

import cv2 as cv
import numpy as np
from matplotlib import pyplot as plt

img = cv.imread('messi5.jpg',0)
img2 = img.copy() 
template = cv.imread('template.jpg',0)
w, h = template.shape[::-1]
methods = ['cv.TM_CCOEFF', 'cv.TM_CCOEFF_NORMED', 'cv.TM_CCORR',
            'cv.TM_CCORR_NORMED', 'cv.TM_SQDIFF', 'cv.TM_SQDIFF_NORMED']
for meth in methods:
    img = img2.copy()
    method = eval(meth)
    res = cv.matchTemplate(img,template,method)
    min_val, max_val, min_loc, max_loc = cv.minMaxLoc(res)

    if template_match:
        //do something

我读过这篇文章，但我不明白

谢谢你的回答

Answer 1

1. 获取模板的功能

---

• An image features, such as edges and interest points, provide rich information on the image content. source

  ---

• 例如：如果下面是你的模板，那么找到它的特征

  

   import numpy as np
   import imutils
   import glob
   import cv2
  
   template = cv2.imread("template.jpg")
   template = cv2.cvtColor(template, cv2.COLOR_BGR2GRAY)
   template = cv2.Canny(template, 50, 200)
   (h, w) = template.shape[:2]
  

1. 获取图像的特征

---

• 

1. 检查模板特征是否与图像特征匹配

---

result = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF)

• cv2.TM_CCOEFF只是一个选项，您可以使用许多其他templates

1. 查找result变量的最小值和最大值

---

(_, maxVal, _, maxLoc) = cv2.minMaxLoc(result)

1. 现在，您可以检查模板匹配是否正确

---

found = (maxVal, maxLoc, r)

因此，如果检测到模板，found变量返回长度为3的元组，这意味着模板匹配。例如：

(495.000, (148, 26), 1)

• 495.000是数组中的最大值

• （148，26）正在开始查找对象的(x, y)坐标

• 1.0是半径