OpenCV: Template Matching

保留正文与补采附件。源页面当前未重新核验；具体限制见交付清单。

In this chapter, you will learn Template Matching is a method for searching and finding the location of a template image in a larger image. OpenCV comes with a function cv.matchTemplate() for this purpose. It simply slides the template image over the input image (as in 2D convolution) and compares the template and patch of input image under the template image. Several comparison methods are implemented in OpenCV. (You can check docs for more details). It returns a grayscale image, where each pixel denotes how much does the neighbourhood of that pixel match with template. If input image is of size (WxH) and template image is of size (wxh), output image will have a size of (W-w+1, H-h+1). Once you got the result, you can use cv.minMaxLoc() function to find where is the maximum/minimum value. Take it as the top-left corner of rectangle and take (w,h) as width and height of the rectangle. That rectangle is your region of template.

Note
If you are using cv.TM_SQDIFF as comparison method, minimum value gives the best match. Here, as an example, we will search for Messi's face in his photo. So I created a template as below: image We will try all the comparison methods so that we can see how their results look like: import cv2 as cv import numpy as np from matplotlib import pyplot as plt

img = cv.imread('messi5.jpg', cv.IMREAD_GRAYSCALE) assert img is not None, "file could not be read, check with os.path.exists()" img2 = img.copy() template = cv.imread('template.jpg', cv.IMREAD_GRAYSCALE) assert template is not None, "file could not be read, check with os.path.exists()" w, h = template.shape[::-1]

methods = ['TM_CCOEFF', 'TM_CCOEFF_NORMED', 'TM_CCORR', 'TM_CCORR_NORMED', 'TM_SQDIFF', 'TM_SQDIFF_NORMED']

for meth in methods: img = img2.copy() method = getattr(cv, meth)

res = [cv.matchTemplate](../../df/dfb/group__imgproc__object.html#ga586ebfb0a7fb604b35a23d85391329be)(img,template,method)
min_val, max_val, min_loc, max_loc = [cv.minMaxLoc](../../d2/de8/group__core__array.html#gab473bf2eb6d14ff97e89b355dac20707)(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](../../d6/d6e/group__imgproc__draw.html#ga07d2f74cadcf8e305e810ce8eed13bc9)(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()

void minMaxLoc(InputArray src, double *minVal, double *maxVal=0, Point *minLoc=0, Point *maxLoc=0, InputArray mask=noArray()) Finds the global minimum and maximum in an array. Mat imread(const String &filename, int flags=IMREAD_COLOR_BGR) Loads an image from a file. void rectangle(InputOutputArray img, Point pt1, Point pt2, const Scalar &color, int thickness=1, int lineType=LINE_8, int shift=0) Draws a simple, thick, or filled up-right rectangle. void matchTemplate(InputArray image, InputArray templ, OutputArray result, int method, InputArray mask=noArray()) Compares a template against overlapped image regions. See the results below: image

image

image You can see that the result using cv.TM_CCORR is not good as we expected. In the previous section, we searched image for Messi's face, which occurs only once in the image. Suppose you are searching for an object which has multiple occurrences, cv.minMaxLoc() won't give you all the locations. In that case, we will use thresholding. So in this example, we will use a screenshot of the famous game Mario and we will find the coins in it. import cv2 as cv import numpy as np from matplotlib import pyplot as plt

img_rgb = cv.imread('mario.png') assert img_rgb is not None, "file could not be read, check with os.path.exists()" img_gray = cv.cvtColor(img_rgb, cv.COLOR_BGR2GRAY) template = cv.imread('mario_coin.png', cv.IMREAD_GRAYSCALE) assert template is not None, "file could not be read, check with os.path.exists()" w, h = template.shape[::-1]

res = cv.matchTemplate(img_gray,template,cv.TM_CCOEFF_NORMED) threshold = 0.8 loc = np.where( res >= threshold) for pt in zip(*loc[::-1]): cv.rectangle(img_rgb, pt, (pt[0] + w, pt[1] + h), (0,0,255), 2)

cv.imwrite('res.png',img_rgb) bool imwrite(const String &filename, InputArray img, const std::vector< int > ¶ms=std::vector< int >()) Saves an image to a specified file. void cvtColor(InputArray src, OutputArray dst, int code, int dstCn=0, AlgorithmHint hint=cv::ALGO_HINT_DEFAULT) Converts an image from one color space to another. Result: image