模板匹配是一种搜索和寻找模板图像在大图像中的位置的方法,OpenCV提供了cv.matchTemplate函数,其实质是将待匹配的小图像img1在img2上滑动,计算匹配度,得到不同区域的匹配度大小。
cv.matchTemplate()提供了许多计算匹配度的方法,此处给出演示结果,但是不详细解释。
对于原图像:
import cv2.cv2
import numpy as np
import cv2 as cv
from matplotlib import pyplot as plt
img = cv.imread(r'XXXX')
img2 = img.copy()
template = cv.imread(r'xxxx')
w= template.shape[0]
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)#由于meth是字符串,所以要进行处理
res = cv.matchTemplate(img,template,method)
min_val, max_val, min_loc, max_loc = cv.minMaxLoc(res)
if method in [cv.TM_SQDIFF, cv.TM_SQDIFF_NORMED]:
top_left = min_loc
else:
top_left = max_loc
bottom_right = (top_left[0] + w, top_left[1] + h)
cv.rectangle(img,top_left, bottom_right, 255, 2)
plt.subplot(121),plt.imshow(res,cmap = 'gray')
plt.title('Matching Result'), plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(img,cmap = 'gray')
plt.title('Detected Point'), plt.xticks([]), plt.yticks([])
plt.suptitle(meth)
plt.show()
res就是前文提到的匹配度的分布,在有的计算方式中,匹配度越高,计算值越低,例如cv.TM_SQDIFF, cv.TM_SQDIFF_NORMED,故需要特殊处理。
我们利用cv.minMaxLoc找到匹配度最高的地方,并由此在原图像中画出模板。
多模板匹配:
对于原图像:
import cv2.cv2
import numpy as np
import cv2 as cv
from matplotlib import pyplot as plt
img = cv.imread(r'XXXXX\marry.jpg')
img2 = img.copy()
template = cv.imread(r'XXXXX\marry1.jpg')
w= template.shape[0]
h= template.shape[1]
res = cv.matchTemplate(img2,template,cv.TM_CCOEFF_NORMED)
threshold = 0.8#设置阈值,大于阈值认为被匹配
loc = np.where( res >= threshold)
img = img2.copy()
for pt in zip(*loc[::-1]):
cv.rectangle(img, pt, (pt[0] + w, pt[1] + h), (0,0,255), 2)
cv.imwrite(r'XXXX\res.png',img)