{"id":1027227,"date":"2024-12-31T10:49:15","date_gmt":"2024-12-31T02:49:15","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1027227.html"},"modified":"2024-12-31T10:49:17","modified_gmt":"2024-12-31T02:49:17","slug":"python%e5%a6%82%e4%bd%95%e7%94%a8%e5%88%86%e6%b0%b4%e5%b2%ad%e8%bf%9b%e8%a1%8c%e5%88%87%e5%89%b2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1027227.html","title":{"rendered":"python\u5982\u4f55\u7528\u5206\u6c34\u5cad\u8fdb\u884c\u5207\u5272"},"content":{"rendered":"

\"python\u5982\u4f55\u7528\u5206\u6c34\u5cad\u8fdb\u884c\u5207\u5272\"<\/p>\n

Python\u8fdb\u884c\u5206\u6c34\u5cad\u5207\u5272\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528OpenCV\u5e93\u3001\u5229\u7528\u68af\u5ea6\u56fe\u50cf\u3001\u6807\u8bb0\u524d\u666f\u548c\u80cc\u666f\u3001\u6267\u884c\u5206\u6c34\u5cad\u53d8\u6362\u3002<\/strong> \u5728\u8fd9\u4e9b\u65b9\u6cd5\u4e2d\uff0c\u4f7f\u7528OpenCV\u5e93\u662f\u6700\u5e38\u89c1\u7684\uff0c\u56e0\u4e3a\u5b83\u63d0\u4f9b\u4e86\u4e00\u4e2a\u7b80\u4fbf\u7684\u63a5\u53e3\u6765\u5b9e\u73b0\u590d\u6742\u7684\u56fe\u50cf\u5904\u7406\u7b97\u6cd5\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528\u8fd9\u4e9b\u65b9\u6cd5\u8fdb\u884c\u5206\u6c34\u5cad\u5207\u5272\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528OpenCV\u5e93<\/p>\n<\/p>\n

OpenCV\uff08Open Source Computer Vision Library\uff09\u662f\u4e00\u4e2a\u5f00\u6e90\u8ba1\u7b97\u673a\u89c6\u89c9\u548c\u673a\u5668\u5b66\u4e60<\/a>\u8f6f\u4ef6\u5e93\u3002\u5b83\u5305\u542b\u4e86\u51e0\u767e\u4e2a\u8ba1\u7b97\u673a\u89c6\u89c9\u7b97\u6cd5\uff0c\u53ef\u4ee5\u7528\u4e8e\u56fe\u50cf\u5904\u7406\u3001\u89c6\u9891\u5904\u7406\u548c\u8ba1\u7b97\u673a\u89c6\u89c9\u4efb\u52a1\u3002\u8981\u4f7f\u7528OpenCV\u8fdb\u884c\u5206\u6c34\u5cad\u5207\u5272\uff0c\u9996\u5148\u9700\u8981\u5b89\u88c5OpenCV\u5e93\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

pip install opencv-python<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528OpenCV\u5e93\u8fdb\u884c\u5206\u6c34\u5cad\u5207\u5272\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
import cv2<\/p>\n
import numpy as np<\/p>\n
from matplotlib import pyplot as plt<\/p>\n
\u8bfb\u53d6\u56fe\u50cf<\/strong><\/h2>\n
image = cv2.imread('image.jpg')<\/p>\n
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)<\/p>\n
\u5e94\u7528\u9608\u503c<\/strong><\/h2>\n
ret, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)<\/p>\n
\u79fb\u9664\u566a\u58f0<\/strong><\/h2>\n
kernel = np.ones((3, 3), np.uint8)<\/p>\n
opening = cv2.morphologyEx(binary, cv2.MORPH_OPEN, kernel, iterations=2)<\/p>\n
\u786e\u5b9a\u80cc\u666f\u533a\u57df<\/strong><\/h2>\n
sure_bg = cv2.dilate(opening, kernel, iterations=3)<\/p>\n
\u786e\u5b9a\u524d\u666f\u533a\u57df<\/strong><\/h2>\n
dist_transform = cv2.distanceTransform(opening, cv2.DIST_L2, 5)<\/p>\n
ret, sure_fg = cv2.threshold(dist_transform, 0.7 * dist_transform.max(), 255, 0)<\/p>\n
\u786e\u5b9a\u672a\u77e5\u533a\u57df<\/strong><\/h2>\n
sure_fg = np.uint8(sure_fg)<\/p>\n
unknown = cv2.subtract(sure_bg, sure_fg)<\/p>\n
\u6807\u8bb0\u6807\u7b7e<\/strong><\/h2>\n
ret, markers = cv2.connectedComponents(sure_fg)<\/p>\n
\u589e\u52a0\u4e00\u4e2a\u6807\u7b7e\u4ee5\u786e\u4fdd\u80cc\u666f\u4e3a0\uff0c\u800c\u4e0d\u662f1<\/strong><\/h2>\n
markers = markers + 1<\/p>\n
\u6807\u8bb0\u672a\u77e5\u533a\u57df\u4e3a0<\/strong><\/h2>\n
markers[unknown == 255] = 0<\/p>\n
\u5e94\u7528\u5206\u6c34\u5cad\u7b97\u6cd5<\/strong><\/h2>\n
markers = cv2.watershed(image, markers)<\/p>\n
image[markers == -1] = [255, 0, 0]<\/p>\n
\u663e\u793a\u7ed3\u679c<\/strong><\/h2>\n
plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u5229\u7528\u68af\u5ea6\u56fe\u50cf<\/p>\n<\/p>\n
\u68af\u5ea6\u56fe\u50cf\u8868\u793a\u56fe\u50cf\u4e2d\u6bcf\u4e2a\u50cf\u7d20\u7684\u53d8\u5316\u7387\u3002\u901a\u8fc7\u8ba1\u7b97\u56fe\u50cf\u7684\u68af\u5ea6\uff0c\u53ef\u4ee5\u7a81\u51fa\u56fe\u50cf\u4e2d\u7684\u8fb9\u7f18\uff0c\u8fd9\u5bf9\u4e8e\u5206\u5272\u56fe\u50cf\u4e2d\u7684\u7269\u4f53\u975e\u5e38\u6709\u7528\u3002\u5728\u5206\u6c34\u5cad\u7b97\u6cd5\u4e2d\uff0c\u68af\u5ea6\u56fe\u50cf\u7528\u4e8e\u6807\u8bb0\u56fe\u50cf\u4e2d\u7684\u524d\u666f\u548c\u80cc\u666f\u533a\u57df\u3002<\/p>\n<\/p>\n
\u4f7f\u7528Sobel\u7b97\u5b50\u53ef\u4ee5\u8ba1\u7b97\u56fe\u50cf\u7684\u68af\u5ea6\u3002\u4ee5\u4e0b\u662f\u8ba1\u7b97\u68af\u5ea6\u56fe\u50cf\u7684\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
# \u8ba1\u7b97\u56fe\u50cf\u7684\u68af\u5ea6<\/p>\n
sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=3)<\/p>\n
sobely = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=3)<\/p>\n
gradient = cv2.magnitude(sobelx, sobely)<\/p>\n
plt.imshow(gradient, cmap='gray')<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u6807\u8bb0\u524d\u666f\u548c\u80cc\u666f<\/p>\n<\/p>\n
\u5728\u5e94\u7528\u5206\u6c34\u5cad\u7b97\u6cd5\u4e4b\u524d\uff0c\u9700\u8981\u786e\u5b9a\u56fe\u50cf\u4e2d\u7684\u524d\u666f\u548c\u80cc\u666f\u533a\u57df\u3002\u53ef\u4ee5\u4f7f\u7528\u5f62\u6001\u5b66\u64cd\u4f5c\uff08\u5982\u5f00\u8fd0\u7b97\u548c\u95ed\u8fd0\u7b97\uff09\u6765\u53bb\u9664\u566a\u58f0\uff0c\u5e76\u786e\u5b9a\u524d\u666f\u548c\u80cc\u666f\u533a\u57df\u3002<\/p>\n<\/p>\n
\u4ee5\u4e0b\u662f\u6807\u8bb0\u524d\u666f\u548c\u80cc\u666f\u533a\u57df\u7684\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
# \u79fb\u9664\u566a\u58f0<\/p>\n
kernel = np.ones((3, 3), np.uint8)<\/p>\n
opening = cv2.morphologyEx(binary, cv2.MORPH_OPEN, kernel, iterations=2)<\/p>\n
\u786e\u5b9a\u80cc\u666f\u533a\u57df<\/strong><\/h2>\n
sure_bg = cv2.dilate(opening, kernel, iterations=3)<\/p>\n
\u786e\u5b9a\u524d\u666f\u533a\u57df<\/strong><\/h2>\n
dist_transform = cv2.distanceTransform(opening, cv2.DIST_L2, 5)<\/p>\n
ret, sure_fg = cv2.threshold(dist_transform, 0.7 * dist_transform.max(), 255, 0)<\/p>\n
\u786e\u5b9a\u672a\u77e5\u533a\u57df<\/strong><\/h2>\n
sure_fg = np.uint8(sure_fg)<\/p>\n
unknown = cv2.subtract(sure_bg, sure_fg)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u6267\u884c\u5206\u6c34\u5cad\u53d8\u6362<\/p>\n<\/p>\n
\u5728\u6807\u8bb0\u524d\u666f\u548c\u80cc\u666f\u533a\u57df\u540e\uff0c\u53ef\u4ee5\u5e94\u7528\u5206\u6c34\u5cad\u53d8\u6362\u6765\u5206\u5272\u56fe\u50cf\u3002\u5206\u6c34\u5cad\u53d8\u6362\u4f1a\u5c06\u56fe\u50cf\u5212\u5206\u4e3a\u591a\u4e2a\u533a\u57df\uff0c\u6bcf\u4e2a\u533a\u57df\u5bf9\u5e94\u4e00\u4e2a\u6807\u8bb0\u3002<\/p>\n<\/p>\n
\u4ee5\u4e0b\u662f\u5e94\u7528\u5206\u6c34\u5cad\u53d8\u6362\u7684\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
# \u6807\u8bb0\u6807\u7b7e<\/p>\n
ret, markers = cv2.connectedComponents(sure_fg)<\/p>\n
\u589e\u52a0\u4e00\u4e2a\u6807\u7b7e\u4ee5\u786e\u4fdd\u80cc\u666f\u4e3a0\uff0c\u800c\u4e0d\u662f1<\/strong><\/h2>\n
markers = markers + 1<\/p>\n
\u6807\u8bb0\u672a\u77e5\u533a\u57df\u4e3a0<\/strong><\/h2>\n
markers[unknown == 255] = 0<\/p>\n
\u5e94\u7528\u5206\u6c34\u5cad\u7b97\u6cd5<\/strong><\/h2>\n
markers = cv2.watershed(image, markers)<\/p>\n
image[markers == -1] = [255, 0, 0]<\/p>\n
\u663e\u793a\u7ed3\u679c<\/strong><\/h2>\n
plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u603b\u7ed3\uff1a<\/p>\n<\/p>\n
\u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u548cOpenCV\u5e93\u8fdb\u884c\u5206\u6c34\u5cad\u5207\u5272\u3002\u5177\u4f53\u6b65\u9aa4\u5305\u62ec\u8bfb\u53d6\u56fe\u50cf\u3001\u8ba1\u7b97\u68af\u5ea6\u56fe\u50cf\u3001\u6807\u8bb0\u524d\u666f\u548c\u80cc\u666f\u533a\u57df\u3001\u5e94\u7528\u5206\u6c34\u5cad\u53d8\u6362\u3002\u6bcf\u4e2a\u6b65\u9aa4\u90fd\u6709\u8be6\u7ec6\u7684\u4ee3\u7801\u793a\u4f8b\uff0c\u53ef\u4ee5\u5e2e\u52a9\u8bfb\u8005\u7406\u89e3\u548c\u5b9e\u73b0\u5206\u6c34\u5cad\u5207\u5272\u3002\u5206\u6c34\u5cad\u7b97\u6cd5\u662f\u4e00\u79cd\u5f3a\u5927\u7684\u56fe\u50cf\u5206\u5272\u65b9\u6cd5\uff0c\u9002\u7528\u4e8e\u5404\u79cd\u56fe\u50cf\u5904\u7406\u4efb\u52a1\u3002\u5e0c\u671b\u8fd9\u7bc7\u6587\u7ae0\u5bf9\u60a8\u6709\u6240\u5e2e\u52a9\uff0c\u795d\u60a8\u5728\u56fe\u50cf\u5904\u7406\u9886\u57df\u53d6\u5f97\u6210\u529f\uff01<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5206\u6c34\u5cad\u7b97\u6cd5\u5728\u56fe\u50cf\u5904\u7406\u4e2d\u6709\u4ec0\u4e48\u5e94\u7528\uff1f<\/strong>
\u5206\u6c34\u5cad\u7b97\u6cd5\u5e7f\u6cdb\u5e94\u7528\u4e8e\u56fe\u50cf\u5206\u5272\uff0c\u5c24\u5176\u9002\u7528\u4e8e\u8bc6\u522b\u548c\u5206\u5272\u5177\u6709\u660e\u663e\u8fb9\u754c\u7684\u7269\u4f53\u3002\u5176\u4e3b\u8981\u5e94\u7528\u5305\u62ec\u533b\u5b66\u56fe\u50cf\u5206\u6790\u3001\u9065\u611f\u56fe\u50cf\u5904\u7406\u3001\u7269\u4f53\u8bc6\u522b\u7b49\u9886\u57df\u3002\u5728\u8fd9\u4e9b\u573a\u666f\u4e2d\uff0c\u5206\u6c34\u5cad\u7b97\u6cd5\u80fd\u591f\u6709\u6548\u5730\u5c06\u91cd\u53e0\u6216\u76f8\u90bb\u7684\u7269\u4f53\u5206\u5f00\uff0c\u4ece\u800c\u63d0\u9ad8\u540e\u7eed\u5904\u7406\u7684\u51c6\u786e\u6027\u3002<\/p>\n
\u5982\u4f55\u9009\u62e9\u5408\u9002\u7684\u53c2\u6570\u4ee5\u4f18\u5316\u5206\u6c34\u5cad\u7b97\u6cd5\u7684\u6548\u679c\uff1f<\/strong>
\u4f18\u5316\u5206\u6c34\u5cad\u7b97\u6cd5\u7684\u6548\u679c\u901a\u5e38\u9700\u8981\u8c03\u6574\u4e00\u4e9b\u53c2\u6570\uff0c\u5982\u5e73\u6ed1\u5ea6\u3001\u9608\u503c\u548c\u79cd\u5b50\u70b9\u7684\u9009\u62e9\u3002\u5e73\u6ed1\u5ea6\u53ef\u4ee5\u901a\u8fc7\u5e94\u7528\u9ad8\u65af\u6ee4\u6ce2\u7b49\u6280\u672f\u6765\u5b9e\u73b0\uff0c\u4ee5\u964d\u4f4e\u566a\u58f0\u5bf9\u5206\u5272\u7ed3\u679c\u7684\u5f71\u54cd\u3002\u9009\u62e9\u5408\u9002\u7684\u79cd\u5b50\u70b9\u4e5f\u81f3\u5173\u91cd\u8981\uff0c\u53ef\u4ee5\u901a\u8fc7\u624b\u52a8\u9009\u62e9\u6216\u81ea\u52a8\u68c0\u6d4b\u65b9\u6cd5\u6765\u83b7\u53d6\u521d\u59cb\u70b9\uff0c\u4ece\u800c\u5f71\u54cd\u6700\u7ec8\u7684\u5206\u5272\u6548\u679c\u3002<\/p>\n
\u5206\u6c34\u5cad\u7b97\u6cd5\u4e0e\u5176\u4ed6\u56fe\u50cf\u5206\u5272\u65b9\u6cd5\u76f8\u6bd4\uff0c\u6709\u54ea\u4e9b\u4f18\u52bf\u548c\u52a3\u52bf\uff1f<\/strong>
\u5206\u6c34\u5cad\u7b97\u6cd5\u7684\u4e3b\u8981\u4f18\u52bf\u5728\u4e8e\u5176\u80fd\u591f\u5904\u7406\u590d\u6742\u7684\u56fe\u50cf\u7ed3\u6784\uff0c\u7279\u522b\u662f\u5728\u7269\u4f53\u8fb9\u754c\u6a21\u7cca\u7684\u60c5\u51b5\u4e0b\uff0c\u80fd\u591f\u63d0\u4f9b\u8f83\u597d\u7684\u5206\u5272\u6548\u679c\u3002\u7136\u800c\uff0c\u5206\u6c34\u5cad\u7b97\u6cd5\u4e5f\u5b58\u5728\u4e00\u4e9b\u52a3\u52bf\uff0c\u6bd4\u5982\u5bf9\u566a\u58f0\u654f\u611f\uff0c\u5bb9\u6613\u4ea7\u751f\u8fc7\u5206\u5272\u95ee\u9898\u3002\u5728\u5904\u7406\u9ad8\u566a\u58f0\u56fe\u50cf\u65f6\uff0c\u53ef\u80fd\u9700\u8981\u7ed3\u5408\u5176\u4ed6\u7b97\u6cd5\uff0c\u5982\u5f62\u6001\u5b66\u5904\u7406\u6216\u533a\u57df\u751f\u957f\uff0c\u4ee5\u63d0\u5347\u5206\u5272\u8d28\u91cf\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u8fdb\u884c\u5206\u6c34\u5cad\u5207\u5272\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528OpenCV\u5e93\u3001\u5229\u7528\u68af\u5ea6\u56fe\u50cf\u3001\u6807\u8bb0\u524d\u666f\u548c\u80cc\u666f\u3001\u6267\u884c\u5206\u6c34\u5cad\u53d8\u6362\u3002 \u5728\u8fd9\u4e9b […]","protected":false},"author":3,"featured_media":1027233,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1027227"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1027227"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1027227\/revisions"}],"predecessor-version":[{"id":1027237,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1027227\/revisions\/1027237"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1027233"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1027227"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1027227"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1027227"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}