{"id":1109476,"date":"2025-01-08T17:10:27","date_gmt":"2025-01-08T09:10:27","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1109476.html"},"modified":"2025-01-08T17:10:29","modified_gmt":"2025-01-08T09:10:29","slug":"python%e5%a6%82%e4%bd%95%e8%af%86%e5%88%ab%e4%ba%8c%e7%bb%b4%e7%a0%81%e8%be%b9%e6%a1%86","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1109476.html","title":{"rendered":"python\u5982\u4f55\u8bc6\u522b\u4e8c\u7ef4\u7801\u8fb9\u6846"},"content":{"rendered":"

\"python\u5982\u4f55\u8bc6\u522b\u4e8c\u7ef4\u7801\u8fb9\u6846\"<\/p>\n

Python\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528\u5404\u79cd\u5e93\u6765\u8bc6\u522b\u4e8c\u7ef4\u7801\u8fb9\u6846\uff0c\u4f8b\u5982OpenCV\u3001ZBar\u3001pyzbar\u3002\u63a8\u8350\u4f7f\u7528OpenCV\u5e93\uff0c\u56e0\u4e3a\u5b83\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u8ba1\u7b97\u673a\u89c6\u89c9\u529f\u80fd\u3001\u8bc6\u522b\u51c6\u786e\u7387\u9ad8\u3001\u5904\u7406\u901f\u5ea6\u5feb\u3002<\/strong><\/p>\n<\/p>\n

\u4f7f\u7528OpenCV\u5e93\u8bc6\u522b\u4e8c\u7ef4\u7801\u8fb9\u6846\u7684\u6b65\u9aa4\u4e3b\u8981\u5305\u62ec\uff1a\u56fe\u50cf\u9884\u5904\u7406\u3001\u4e8c\u7ef4\u7801\u68c0\u6d4b\u3001\u8fb9\u6846\u63d0\u53d6\u3002<\/strong><\/p>\n<\/p>\n

\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528Python\u548cOpenCV\u5e93\u6765\u8bc6\u522b\u4e8c\u7ef4\u7801\u8fb9\u6846\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u5b89\u88c5\u6240\u9700\u5e93<\/h3>\n<\/p>\n

\u5728\u5f00\u59cb\u7f16\u5199\u4ee3\u7801\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5OpenCV\u5e93\u3002\u5982\u679c\u8fd8\u6ca1\u6709\u5b89\u88c5OpenCV\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

pip install opencv-python<\/p>\n
pip install opencv-python-headless<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u8bfb\u53d6\u548c\u663e\u793a\u56fe\u50cf<\/h3>\n<\/p>\n
\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u8bfb\u53d6\u56fe\u50cf\u6587\u4ef6\u5e76\u663e\u793a\uff0c\u8fd9\u6837\u6211\u4eec\u53ef\u4ee5\u76f4\u89c2\u5730\u770b\u5230\u5904\u7406\u7684\u56fe\u50cf\u3002\u4e0b\u9762\u662f\u8bfb\u53d6\u548c\u663e\u793a\u56fe\u50cf\u7684\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
import cv2<\/p>\n
import numpy as np<\/p>\n
import matplotlib.pyplot as plt<\/p>\n
\u8bfb\u53d6\u56fe\u50cf<\/strong><\/h2>\n
image = cv2.imread('qrcode.png')<\/p>\n
\u5c06\u56fe\u50cf\u4eceBGR\u8f6c\u6362\u4e3aRGB<\/strong><\/h2>\n
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)<\/p>\n
\u663e\u793a\u56fe\u50cf<\/strong><\/h2>\n
plt.imshow(image_rgb)<\/p>\n
plt.axis('off')<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u56fe\u50cf\u9884\u5904\u7406<\/h3>\n<\/p>\n
\u4e3a\u4e86\u66f4\u597d\u5730\u68c0\u6d4b\u4e8c\u7ef4\u7801\uff0c\u6211\u4eec\u9700\u8981\u5bf9\u56fe\u50cf\u8fdb\u884c\u9884\u5904\u7406\u3002\u901a\u5e38\u7684\u9884\u5904\u7406\u6b65\u9aa4\u5305\u62ec\u7070\u5ea6\u8f6c\u6362\u3001\u4e8c\u503c\u5316\u7b49\u3002\u4e0b\u9762\u662f\u9884\u5904\u7406\u7684\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
# \u5c06\u56fe\u50cf\u8f6c\u6362\u4e3a\u7070\u5ea6\u56fe\u50cf<\/p>\n
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)<\/p>\n
\u5e94\u7528\u9ad8\u65af\u6a21\u7cca<\/strong><\/h2>\n
blurred = cv2.GaussianBlur(gray, (5, 5), 0)<\/p>\n
\u5e94\u7528\u81ea\u9002\u5e94\u9608\u503c<\/strong><\/h2>\n
thresh = cv2.adaptiveThreshold(blurred, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, 11, 2)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u68c0\u6d4b\u4e8c\u7ef4\u7801<\/h3>\n<\/p>\n
\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u4f7f\u7528OpenCV\u7684cv2.findContours<\/code>\u51fd\u6570\u6765\u68c0\u6d4b\u56fe\u50cf\u4e2d\u7684\u8f6e\u5ed3\u3002\u7136\u540e\uff0c\u6211\u4eec\u8fc7\u6ee4\u51fa\u4e8c\u7ef4\u7801\u7684\u8fb9\u6846\u3002\u4e0b\u9762\u662f\u68c0\u6d4b\u4e8c\u7ef4\u7801\u7684\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
# \u67e5\u627e\u8f6e\u5ed3<\/p>\n
contours, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAI<\/a>N_APPROX_SIMPLE)<\/p>\n
\u8fc7\u6ee4\u51fa\u4e8c\u7ef4\u7801\u8fb9\u6846<\/strong><\/h2>\n
for contour in contours:<\/p>\n
    # \u8ba1\u7b97\u8f6e\u5ed3\u7684\u5468\u957f<\/p>\n
    perimeter = cv2.arcLength(contour, True)<\/p>\n
    # \u4f7f\u7528\u591a\u8fb9\u5f62\u903c\u8fd1\u8f6e\u5ed3<\/p>\n
    approx = cv2.approxPolyDP(contour, 0.02 * perimeter, True)<\/p>\n
    # \u5982\u679c\u591a\u8fb9\u5f62\u67094\u4e2a\u9876\u70b9\uff0c\u5219\u53ef\u80fd\u662f\u4e8c\u7ef4\u7801\u7684\u8fb9\u6846<\/p>\n
    if len(approx) == 4:<\/p>\n
        cv2.drawContours(image, [approx], -1, (0, 255, 0), 3)<\/p>\n
\u663e\u793a\u68c0\u6d4b\u7ed3\u679c<\/strong><\/h2>\n
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)<\/p>\n
plt.imshow(image_rgb)<\/p>\n
plt.axis('off')<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u8fb9\u6846\u63d0\u53d6<\/h3>\n<\/p>\n
\u5728\u68c0\u6d4b\u5230\u4e8c\u7ef4\u7801\u7684\u8fb9\u6846\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u63d0\u53d6\u51fa\u8fb9\u6846\u7684\u5750\u6807\u3002\u4e0b\u9762\u662f\u63d0\u53d6\u8fb9\u6846\u5750\u6807\u7684\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
# \u63d0\u53d6\u8fb9\u6846\u5750\u6807<\/p>\n
for contour in contours:<\/p>\n
    perimeter = cv2.arcLength(contour, True)<\/p>\n
    approx = cv2.approxPolyDP(contour, 0.02 * perimeter, True)<\/p>\n
    if len(approx) == 4:<\/p>\n
        points = approx.reshape(4, 2)<\/p>\n
        print("\u4e8c\u7ef4\u7801\u8fb9\u6846\u5750\u6807: ", points)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u8fb9\u6846\u6821\u6b63\u548c\u63d0\u53d6\u4e8c\u7ef4\u7801\u5185\u5bb9<\/h3>\n<\/p>\n
\u6700\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u5bf9\u4e8c\u7ef4\u7801\u8fdb\u884c\u8fb9\u6846\u6821\u6b63\uff0c\u5e76\u63d0\u53d6\u4e8c\u7ef4\u7801\u5185\u5bb9\u3002\u4e0b\u9762\u662f\u6821\u6b63\u548c\u63d0\u53d6\u5185\u5bb9\u7684\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
# \u63d0\u53d6\u4e8c\u7ef4\u7801\u5185\u5bb9<\/p>\n
from pyzbar.pyzbar import decode<\/p>\n
\u6821\u6b63\u8fb9\u6846<\/strong><\/h2>\n
for contour in contours:<\/p>\n
    perimeter = cv2.arcLength(contour, True)<\/p>\n
    approx = cv2.approxPolyDP(contour, 0.02 * perimeter, True)<\/p>\n
    if len(approx) == 4:<\/p>\n
        # \u83b7\u53d6\u8fb9\u6846\u5750\u6807<\/p>\n
        points = approx.reshape(4, 2)<\/p>\n
        # \u5b9a\u4e49\u4e8c\u7ef4\u7801\u7684\u5bbd\u5ea6\u548c\u9ad8\u5ea6<\/p>\n
        width, height = 200, 200<\/p>\n
        # \u5b9a\u4e49\u76ee\u6807\u70b9<\/p>\n
        dst_points = np.array([<\/p>\n
            [0, 0],<\/p>\n
            [width - 1, 0],<\/p>\n
            [width - 1, height - 1],<\/p>\n
            [0, height - 1]<\/p>\n
        ], dtype='float32')<\/p>\n
        # \u8ba1\u7b97\u900f\u89c6\u53d8\u6362\u77e9\u9635<\/p>\n
        M = cv2.getPerspectiveTransform(np.float32(points), dst_points)<\/p>\n
        # \u900f\u89c6\u53d8\u6362<\/p>\n
        warped = cv2.warpPerspective(image, M, (width, height))<\/p>\n
        # \u663e\u793a\u6821\u6b63\u540e\u7684\u4e8c\u7ef4\u7801<\/p>\n
        warped_rgb = cv2.cvtColor(warped, cv2.COLOR_BGR2RGB)<\/p>\n
        plt.imshow(warped_rgb)<\/p>\n
        plt.axis('off')<\/p>\n
        plt.show()<\/p>\n
        # \u89e3\u7801\u4e8c\u7ef4\u7801\u5185\u5bb9<\/p>\n
        decoded_info = decode(warped)<\/p>\n
        for info in decoded_info:<\/p>\n
            print("\u4e8c\u7ef4\u7801\u5185\u5bb9: ", info.data.decode('utf-8'))<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u6211\u4eec\u6210\u529f\u5730\u4f7f\u7528Python\u548cOpenCV\u5e93\u8bc6\u522b\u4e86\u4e8c\u7ef4\u7801\u8fb9\u6846\uff0c\u5e76\u63d0\u53d6\u4e86\u4e8c\u7ef4\u7801\u5185\u5bb9\u3002\u8fd9\u79cd\u65b9\u6cd5\u4e0d\u4ec5\u51c6\u786e\u7387\u9ad8\uff0c\u800c\u4e14\u5904\u7406\u901f\u5ea6\u5feb\uff0c\u9002\u7528\u4e8e\u5404\u79cd\u5e94\u7528\u573a\u666f\u3002<\/strong><\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5728Python\u4e2d\u4f7f\u7528\u5e93\u8bc6\u522b\u4e8c\u7ef4\u7801\u7684\u8fb9\u6846\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528OpenCV\u5e93\u7ed3\u5408\u5176\u4ed6\u4e8c\u7ef4\u7801\u8bc6\u522b\u5e93\uff08\u5982pyzbar\u6216opencv-python\uff09\u6765\u8bc6\u522b\u4e8c\u7ef4\u7801\u7684\u8fb9\u6846\u3002OpenCV\u63d0\u4f9b\u4e86\u56fe\u50cf\u5904\u7406\u7684\u5f3a\u5927\u529f\u80fd\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u68c0\u6d4b\u548c\u63d0\u53d6\u4e8c\u7ef4\u7801\u7684\u8fb9\u6846\u3002\u901a\u8fc7\u8fb9\u7f18\u68c0\u6d4b\u548c\u8f6e\u5ed3\u63d0\u53d6\uff0c\u7a0b\u5e8f\u80fd\u591f\u627e\u5230\u4e8c\u7ef4\u7801\u7684\u8fb9\u754c\uff0c\u5e76\u8fdb\u4e00\u6b65\u8fdb\u884c\u89e3\u7801\u3002<\/p>\n
\u8bc6\u522b\u4e8c\u7ef4\u7801\u8fb9\u6846\u7684\u5e38\u7528\u6280\u672f\u6709\u54ea\u4e9b\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u8bc6\u522b\u4e8c\u7ef4\u7801\u8fb9\u6846\u901a\u5e38\u4f7f\u7528\u8fb9\u7f18\u68c0\u6d4b\uff08\u5982Canny\u7b97\u6cd5\uff09\u3001\u8f6e\u5ed3\u68c0\u6d4b\u548c\u900f\u89c6\u53d8\u6362\u7b49\u6280\u672f\u3002\u8fb9\u7f18\u68c0\u6d4b\u5e2e\u52a9\u627e\u51fa\u56fe\u50cf\u4e2d\u7684\u8fb9\u7f18\uff0c\u800c\u8f6e\u5ed3\u68c0\u6d4b\u5219\u80fd\u8bc6\u522b\u51fa\u4e8c\u7ef4\u7801\u7684\u5f62\u72b6\u3002\u901a\u8fc7\u7ed3\u5408\u8fd9\u4e9b\u6280\u672f\uff0c\u80fd\u591f\u6709\u6548\u5730\u63d0\u53d6\u548c\u8bc6\u522b\u4e8c\u7ef4\u7801\u7684\u8fb9\u6846\u3002<\/p>\n
\u5982\u4f55\u63d0\u9ad8\u4e8c\u7ef4\u7801\u8fb9\u6846\u8bc6\u522b\u7684\u51c6\u786e\u6027\uff1f<\/strong>
\u4e3a\u4e86\u63d0\u9ad8\u4e8c\u7ef4\u7801\u8fb9\u6846\u7684\u8bc6\u522b\u51c6\u786e\u6027\uff0c\u53ef\u4ee5\u8003\u8651\u4ee5\u4e0b\u51e0\u70b9\uff1a\u786e\u4fdd\u8f93\u5165\u56fe\u50cf\u7684\u8d28\u91cf\u826f\u597d\uff0c\u907f\u514d\u6a21\u7cca\u6216\u4f4e\u5bf9\u6bd4\u5ea6\u7684\u56fe\u50cf\uff1b\u8c03\u6574\u56fe\u50cf\u5904\u7406\u53c2\u6570\uff0c\u4f8b\u5982Canny\u8fb9\u7f18\u68c0\u6d4b\u7684\u9608\u503c\uff1b\u5728\u8bc6\u522b\u524d\u5bf9\u56fe\u50cf\u8fdb\u884c\u9884\u5904\u7406\uff0c\u5982\u7070\u5ea6\u5316\u548c\u53bb\u566a\u58f0\u3002\u6b64\u5916\uff0c\u4f7f\u7528\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u8fdb\u884c\u66f4\u590d\u6742\u7684\u56fe\u50cf\u5206\u6790\u4e5f\u80fd\u63d0\u5347\u8bc6\u522b\u6548\u679c\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528\u5404\u79cd\u5e93\u6765\u8bc6\u522b\u4e8c\u7ef4\u7801\u8fb9\u6846\uff0c\u4f8b\u5982OpenCV\u3001ZBar\u3001pyzbar\u3002\u63a8\u8350\u4f7f\u7528OpenCV […]","protected":false},"author":3,"featured_media":1109479,"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\/1109476"}],"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=1109476"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1109476\/revisions"}],"predecessor-version":[{"id":1109480,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1109476\/revisions\/1109480"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1109479"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1109476"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1109476"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1109476"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}