所以我有一张图片
和一个模板
我想要找到图像中的模板图像,但我的代码什么也找不到。我试过缩小尺寸,但还是没有检测到。请给我举个例子:
import cv2
import imutils
import glob, os
import numpy as np
image = cv2.imread("mainimage.png")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
h, w = gray.shape[:2]
for file in glob.glob("template.png"):
template = cv2.imread(file)
template = cv2.cvtColor(template, cv2.COLOR_BGR2GRAY)
found = None
(tH, tW) = template.shape[:2]
cv2.imshow("Template", template)
for scale in np.linspace(1, 0.2, 20)[::-1]:
resized = imutils.resize(gray, width=int(gray.shape[1] * scale))
r = gray.shape[1] / float(resized.shape[1])
if resized.shape[0] < tH or resized.shape[1] < tW:
break
edged = cv2.Canny(resized, 50, 200)
result = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF)
(_, maxVal, _, maxLoc) = cv2.minMaxLoc(result)
if found is None or maxVal > found[0]:
found = (maxVal, maxLoc, r)
(_, maxLoc, r) = found
(startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r))
(endX, endY) = (int((maxLoc[0] + tW) * r), int((maxLoc[1] + tH) * r))
cv2.rectangle(image, (startX, startY), (endX, endY), (0, 0, 255), 2)
cv2.imshow("Image", image)
cv2.waitKey(0)
发布于 2018-06-03 02:37:28
你的代码大部分都是好的。在您发布的代码中,您的缩放方式是错误的。你在缩小主映像而不是扩大它。此外,您需要在模板和图像上执行Canny。
在您发布的图像中,模板(160x160)比mainimage中的区域( 88x88)大。如果缩放mainimage,则缩放因子应为1.818。扩展模板可能会快得多。
import cv2
# import imutils
import glob, os
import numpy as np
image = cv2.imread("mainimage.png")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
h, w = gray.shape[:2]
for file in glob.glob("template.png"):
template = cv2.imread(file)
template = cv2.cvtColor(template, cv2.COLOR_BGR2GRAY)
found = None
(tH, tW) = template.shape[:2]
# cv2.imshow("Template", template)
tEdged = cv2.Canny(template, 50, 200)
for scale in np.linspace(1, 2, 20):
# resized = imutils.resize(gray, width=int(gray.shape[1] * scale))
resized = cv2.resize(gray, dsize = (0,0), fx = scale, fy = scale)
r = gray.shape[1] / float(resized.shape[1])
if resized.shape[0] < tH or resized.shape[1] < tW:
break
edged = cv2.Canny(resized, 50, 200)
result = cv2.matchTemplate(edged, tEdged, cv2.TM_CCOEFF)
(_, maxVal, _, maxLoc) = cv2.minMaxLoc(result)
if found is None or maxVal > found[0]:
found = (maxVal, maxLoc, r)
(_, maxLoc, r) = found
(startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r))
(endX, endY) = (int((maxLoc[0] + tW) * r), int((maxLoc[1] + tH) * r))
cv2.rectangle(image, (startX, startY), (endX, endY), (0, 0, 255), 2)
# cv2.imshow("Image", image)
cv2.imwrite('output.jpg', image)
# ~ cv2.waitKey(0)
在我的电脑上,这段代码需要6秒才能运行。
关键点匹配+单应性
作为另一种选择,关键点匹配+单应性对比例不敏感。在下面的代码中,dst包含包含找到的模板的边界框的点。对我来说,下面的代码在0.06秒内执行:
import cv2
# import imutils
import glob, os
import numpy as np
import time
image = cv2.imread("mainimage.png")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
h, w = gray.shape[:2]
MIN_MATCH_COUNT = 3
start_time = time.time()
for file in glob.glob("template.png"):
template = cv2.imread(file, 0)
patchSize = 16
orb = cv2.ORB_create(edgeThreshold = patchSize,
patchSize = patchSize)
kp1, des1 = orb.detectAndCompute(template, None)
kp2, des2 = orb.detectAndCompute(gray, None)
FLANN_INDEX_LSH = 6
index_params= dict(algorithm = FLANN_INDEX_LSH,
table_number = 6,
key_size = 12,
multi_probe_level = 1)
search_params = dict(checks = 50)
flann = cv2.FlannBasedMatcher(index_params, search_params)
matches = flann.knnMatch(des1,des2,k=2)
# store all the good matches as per Lowe's ratio test.
good = []
for pair in matches:
if len(pair) == 2:
if pair[0].distance < 0.7*pair[1].distance:
good.append(pair[0])
print('len(good) ', len(good))
print('match %03d, min_match %03d, kp %03d' % (len(good), MIN_MATCH_COUNT, len(kp1)))
if len(good)>MIN_MATCH_COUNT:
src_pts = np.float32([ kp1[m.queryIdx].pt for m in good ]).reshape(-1,1,2)
dst_pts = np.float32([ kp2[m.trainIdx].pt for m in good ]).reshape(-1,1,2)
M, mask = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC,5.0)
matchesMask = mask.ravel().tolist()
h,w = template.shape
pts = np.float32([ [0,0],[0,h-1],[w-1,h-1],[w-1,0] ]).reshape(-1,1,2)
dst = cv2.perspectiveTransform(pts,M)
# dst contains points of bounding box of template in image.
# draw a close polyline around the found template:
image = cv2.polylines(image,[np.int32(dst)],
isClosed = True,
color = (0,255,0),
thickness = 3,
linetype = cv2.LINE_AA)
else:
print( "Not enough matches are found - {}/{}".format(len(good), MIN_MATCH_COUNT) )
matchesMask = None
draw_params = dict(matchColor = (0,255,0), # draw matches in green color
singlePointColor = None,
matchesMask = matchesMask, # draw only inliers
flags = 2)
if len(good)>MIN_MATCH_COUNT:
output2 = cv2.drawMatches(template,kp1,gray,kp2,good,None,**draw_params)
print('elapsed time ', time.time()-start_time)
# cv2.imshow("Image", image)
cv2.imwrite('output_homography.jpg', image)
cv2.imwrite('output2.jpg', output2)
来自cv2.drawMatches函数的output2
关键点检测的一个重要参数是patchSize。在代码中,我们对图像和模板都使用patchSize = 16
。当您将patchSize变小时,您将获得更多关键点。你能做的最小匹配是2。但是当你变得太小时,你开始得到不好的匹配。我不知道怎样才能找到最佳的位置。
https://stackoverflow.com/questions/50641197
复制相似问题