OpenCV 匹配图像上的多个帧

Question

我是 OpenCV 的新手，我想找到一种解决方案，在某个图像上找到多个带有文本的图像。将来我需要那些物品来获得认可。

首先，我有一帧图像用于搜索模板。它看起来像带有透明中心的框架。 我尝试了很多样本​​来匹配模板，但它们只给出一个搜索结果：只找到第一个或第二个项目，但我需要所有这些。

请帮助我找到解决问题的方法。

框架模板：

场景：

代码：

import cv2
import numpy as np

method = cv2.TM_CCOEFF_NORMED
threshold = 0.90

img_main = cv2.imread('images/garden.jpg')
template = cv2.imread('images/frame_trans.png', cv2.IMREAD_GRAYSCALE)
template_gray = template

img_main_gray = cv2.cvtColor(img_main, cv2.COLOR_BGR2GRAY)
w, h = template.shape[::-1]

res = cv2.matchTemplate(img_main_gray, template_gray, method)

cv2.normalize(res, res, 0., 1., cv2.NORM_MINMAX)
cv2.threshold(res, threshold, 1, cv2.THRESH_TOZERO)

i = 0
while i < 100:
    min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(res)
    if method in [cv2.TM_SQDIFF, cv2.TM_SQDIFF_NORMED]:
        top_left = min_loc
    else:
        top_left = max_loc

    if max_val > threshold:
        print(top_left)
        bottom_right = (top_left[0] + w, top_left[1] + h)
        cv2.rectangle(img_main, top_left, bottom_right, (0, 0, 255), 2)
        cv2.floodFill(img_main_gray, None, top_left, 0, 0.1, 1.0)
    else:
        break
    i += 1

cv2.imwrite('sample6_output.png', img_main)
cv2.imshow('sample6', img_main)
cv2.waitKey()

脚本的结果在这里...

PyDev console: starting.
Python 3.8.2 (tags/v3.8.2:7b3ab59, Feb 25 2020, 23:03:10) [MSC v.1916 64 bit (AMD64)] on win32
runfile('D:/MyProjects/PyHeroRecognition/sample6.py', wdir='D:/MyProjects/PyHeroRecognition')
(71, 45)
(71, 45)
(71, 45)
(71, 45)
(71, 45)
(71, 45)
(71, 45)
(71, 45)
(71, 45)
(71, 45)

结果图片：

Answer 1

对于模板匹配算法，只要找到相似度的最大值，就应该将创建的像素设置为零，如果不这样做，就像在每次迭代中通过cv2.minMaxLoc函数找到相同的像素一样。

您可能会遇到需要将最大像素周围的小区域设置为零以获得最佳效果的情况。

我为你的问题写了一个简单的代码，但是在这种情况下，模板匹配似乎不是很好

import cv2
import numpy as np

method = cv2.TM_CCORR_NORMED
threshold = 0.7


img_main = cv2.imread('images/garden.jpg')
template = cv2.imread('images/frame_trans.png', cv2.IMREAD_GRAYSCALE)
template_gray = template

img_main_gray = cv2.cvtColor(img_main, cv2.COLOR_BGR2GRAY)
w, h = template.shape[::-1]

res = cv2.matchTemplate(img_main_gray, template_gray, method)

cv2.normalize(res, res, 0., 1., cv2.NORM_MINMAX)
cv2.threshold(res, threshold, 1, cv2.THRESH_TOZERO)

i = 0

border=45  # I have added this line to control the area that must be zero
while i < 20:
    min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(res)
    print(max_val)
    if method in [cv2.TM_SQDIFF, cv2.TM_SQDIFF_NORMED]:
        top_left = min_loc
    else:
        top_left = max_loc

    if max_val > threshold:
#         print(top_left)
        bottom_right = (top_left[0] + w, top_left[1] + h)
#         cv2.circle(img_main,max_loc,5,(0,0,255),1)
        cv2.rectangle(img_main, top_left, bottom_right, (0, 0, 255), 5)
        cv2.floodFill(img_main_gray, None, top_left, 0, 0.1, 1.0)
    i += 1
    res[max_loc[1]-border:max_loc[1]+border,max_loc[0]-border:max_loc[0]+border]=0  # set zero the max loc

img_main=cv2.cvtColor(img_main,cv2.COLOR_BGR2RGB)
import matplotlib.pyplot as plt
plt.figure(figsize=(10,12))
plt.imshow(res)
plt.figure(figsize=(10,12))
plt.imshow(img_main)

Answer 2

这里是如何在 Python/OpenCV 中使用透明模板图像进行模板匹配。很抱歉使用 Imagemagick 图像，但我已经有那个例子了。

输入：

透明模板：

import cv2
import numpy as np

# read image
img = cv2.imread('logo.png')

# read template with alpha
tmplt = cv2.imread('hat_alpha.png', cv2.IMREAD_UNCHANGED)
hh, ww = tmplt.shape[:2]

# extract template mask as grayscale from alpha channel and make 3 channels
tmplt_mask = tmplt[:,:,3]
tmplt_mask = cv2.merge([tmplt_mask,tmplt_mask,tmplt_mask])

# extract templt2 without alpha channel from tmplt
tmplt2 = tmplt[:,:,0:3]

# do template matching
corrimg = cv2.matchTemplate(img,tmplt2,cv2.TM_CCORR_NORMED, mask=tmplt_mask)
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(corrimg)
max_val_ncc = '{:.3f}'.format(max_val)
print("correlation match score: " + max_val_ncc)
xx = max_loc[0]
yy = max_loc[1]
print('xmatch =',xx,'ymatch =',yy)

# draw red bounding box to define match location
result = img.copy()
pt1 = (xx,yy)
pt2 = (xx+ww, yy+hh)
cv2.rectangle(result, pt1, pt2, (0,0,255), 1)

cv2.imshow('image', img)
cv2.imshow('template2', tmplt2)
cv2.imshow('template_mask', tmplt_mask)
cv2.imshow('result', result)
cv2.waitKey(0)
cv2.destroyAllWindows()

# save results
cv2.imwrite('logo_hat_match2.png', result)

结果显示匹配位置的边界框：

Answer 3

@fmw42 非常感谢您的想法！我已经越过了你的代码和我的代码，但我只有一个结果（见下文）。 我的下一个问题：如何捕获少量结果？

import cv2
import numpy as np

method = cv2.TM_CCORR_NORMED
threshold = 0.90

# read scene image
main_img = cv2.imread('images/garden.jpg')

# read template with alpha
template = cv2.imread('images/frame_trans.png', cv2.IMREAD_UNCHANGED)
h, w = template.shape[:2]

# extract template mask as grayscale from alpha channel and make 3 channels
tmplt_mask = template[:, :, 3]
tmplt_mask = cv2.merge([tmplt_mask, tmplt_mask, tmplt_mask])

# extract templt2 without alpha channel from tmplt
tmplt2 = template[:, :, 0:3]

res = cv2.matchTemplate(main_img, tmplt2, method, mask=tmplt_mask)

output_img = main_img.copy()

i = 0
while i < 100:
    min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(res)
    if method in [cv2.TM_SQDIFF, cv2.TM_SQDIFF_NORMED]:
        top_left = min_loc
    else:
        top_left = max_loc

    if max_val > threshold:
        print("%s: %s" % (max_val, top_left))
        bottom_right = (top_left[0] + w, top_left[1] + h)
        cv2.rectangle(output_img, top_left, bottom_right, (0, 0, 255), 2)
        cv2.floodFill(res, None, top_left, 0, 0.1, 1.0)
    else:
        break
    i += 1

cv2.imwrite('sample8_output.png', output_img)
cv2.imshow('sample8', output_img)
cv2.waitKey()

控制台输出：

PyDev console: starting.
Python 3.8.2 (tags/v3.8.2:7b3ab59, Feb 25 2020, 23:03:10) [MSC v.1916 64 bit (AMD64)] on win32
runfile('D:/MyProjects/PyHeroRecognition/sample8_alpha.py', wdir='D:/MyProjects/PyHeroRecognition')
0.9918215870857239: (71, 45)
>>>

结果图像输出