CODEWITHSUNDEEP
pythonimageopencvtemplate-matching
Jürgen K.
Jürgen K.

Reputation: 3487

Image Matching result in images where it shouldn't be one (Python opencv tutorial)

I'm working with the following python opencv example:

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

img = cv2.imread('messi5.jpg',0)
img2 = img.copy()
template = cv2.imread('template.jpg',0)
w, h = template.shape[::-1]

# All the 6 methods for comparison in a list
methods = ['cv2.TM_CCOEFF', 'cv2.TM_CCOEFF_NORMED', 'cv2.TM_CCORR',
            'cv2.TM_CCORR_NORMED', 'cv2.TM_SQDIFF', 'cv2.TM_SQDIFF_NORMED']

for meth in methods:
    img = img2.copy()
    method = eval(meth)

    # Apply template Matching
    res = cv2.matchTemplate(img,template,method)
    min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(res)

    # If the method is TM_SQDIFF or TM_SQDIFF_NORMED, take minimum
    if method in [cv2.TM_SQDIFF, cv2.TM_SQDIFF_NORMED]:
        top_left = min_loc
    else:
        top_left = max_loc
    bottom_right = (top_left[0] + w, top_left[1] + h)

    cv2.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()

The matching works pretty well on a set of chosen images, which clearly contained the template. My problem is that even in images which clearly doesn't contain the template a rectangle was drawn. How can I fit the source code, so it can handle image which doesn't match at all.

Thanks in advance

Upvotes: 0

Views: 726

Answers (2)

mspiller
mspiller

Reputation: 3839

Your code always shows the best match, regardless of how good the match is.

You could check the value of max_val (or min_val when SQDIFF is used) and only show the match when this value exceeds a certain threshold.

Upvotes: 1

Ha Bom
Ha Bom

Reputation: 2917

In the document:

It returns a grayscale image, where each pixel denotes how much does the neighbourhood of that pixel match with template

So set a threshold for the res, if there is no similarity in the image, it does nothing.

res = cv2.matchTemplate(img,template,method)
if res<0.8:
    return
...

Just like in the Template Matching with Multiple Objects part

Upvotes: 1

Related Questions