{"id":1062813,"date":"2024-12-31T15:55:14","date_gmt":"2024-12-31T07:55:14","guid":{"rendered":""},"modified":"2024-12-31T15:55:17","modified_gmt":"2024-12-31T07:55:17","slug":"python%e4%b8%ad%e5%a6%82%e4%bd%95%e5%af%bb%e6%89%be%e5%9b%be%e7%89%87%e4%b9%8b%e9%97%b4%e7%9a%84%e5%b7%ae%e5%bc%82","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1062813.html","title":{"rendered":"python\u4e2d\u5982\u4f55\u5bfb\u627e\u56fe\u7247\u4e4b\u95f4\u7684\u5dee\u5f02"},"content":{"rendered":"

\"python\u4e2d\u5982\u4f55\u5bfb\u627e\u56fe\u7247\u4e4b\u95f4\u7684\u5dee\u5f02\"<\/p>\n

\u5728Python\u4e2d\u5bfb\u627e\u56fe\u7247\u4e4b\u95f4\u7684\u5dee\u5f02\uff0c\u53ef\u4ee5\u4f7f\u7528\u56fe\u50cf\u5904\u7406\u5e93\uff08\u5982OpenCV\u548cPIL\uff09\u4ee5\u53ca\u56fe\u50cf\u6bd4\u8f83\u7b97\u6cd5\uff08\u5982\u7ed3\u6784\u76f8\u4f3c\u6027\u6307\u6570\uff08SSIM\uff09\u3001\u50cf\u7d20\u5dee\u5f02\u7b49\uff09<\/strong>\u3002\u5176\u4e2d\uff0c\u5e38\u7528\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528OpenCV\u7684absdiff\u51fd\u6570\u8ba1\u7b97\u7edd\u5bf9\u5dee\u5f02\u3001\u4f7f\u7528PIL\u5e93\u5bf9\u56fe\u50cf\u8fdb\u884c\u9010\u50cf\u7d20\u6bd4\u8f83\u3001\u4f7f\u7528SSIM\u8ba1\u7b97\u56fe\u50cf\u7684\u7ed3\u6784\u76f8\u4f3c\u6027\u6307\u6570<\/strong>\u3002\u672c\u6587\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u8fd9\u4e9b\u65b9\u6cd5\uff0c\u5e76\u63d0\u4f9b\u76f8\u5e94\u7684\u4ee3\u7801\u793a\u4f8b\u3002<\/p>\n<\/p>\n

\u4e00\u3001OpenCV\u4e2d\u7684absdiff\u51fd\u6570<\/h3>\n<\/p>\n

OpenCV\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u8ba1\u7b97\u673a\u89c6\u89c9\u5e93\uff0c\u53ef\u4ee5\u7528\u6765\u5904\u7406\u548c\u5206\u6790\u56fe\u50cf\u3002\u4f7f\u7528OpenCV\u7684absdiff<\/code>\u51fd\u6570\u53ef\u4ee5\u8ba1\u7b97\u4e24\u5e45\u56fe\u50cf\u4e4b\u95f4\u7684\u7edd\u5bf9\u5dee\u5f02\u3002<\/p>\n<\/p>\n

1. \u5b89\u88c5OpenCV<\/h4>\n<\/p>\n

\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5OpenCV\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528pip\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

pip install opencv-python<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u8bfb\u53d6\u548c\u5904\u7406\u56fe\u50cf<\/h4>\n<\/p>\n
\u4f7f\u7528OpenCV\u8bfb\u53d6\u56fe\u50cf\uff0c\u5e76\u8ba1\u7b97\u4e24\u5e45\u56fe\u50cf\u4e4b\u95f4\u7684\u7edd\u5bf9\u5dee\u5f02\uff1a<\/p>\n<\/p>\n
import cv2<\/p>\n
\u8bfb\u53d6\u56fe\u50cf<\/strong><\/h2>\n
image1 = cv2.imread('image1.jpg')<\/p>\n
image2 = cv2.imread('image2.jpg')<\/p>\n
\u786e\u4fdd\u56fe\u50cf\u5c3a\u5bf8\u76f8\u540c<\/strong><\/h2>\n
if image1.shape == image2.shape:<\/p>\n
    # \u8ba1\u7b97\u7edd\u5bf9\u5dee\u5f02<\/p>\n
    difference = cv2.absdiff(image1, image2)<\/p>\n
    # \u5c06\u5dee\u5f02\u7ed3\u679c\u8f6c\u4e3a\u7070\u5ea6\u56fe<\/p>\n
    gray_difference = cv2.cvtColor(difference, cv2.COLOR_BGR2GRAY)<\/p>\n
    # \u663e\u793a\u5dee\u5f02\u56fe\u50cf<\/p>\n
    cv2.imshow('Difference', gray_difference)<\/p>\n
    cv2.wAI<\/a>tKey(0)<\/p>\n
    cv2.destroyAllWindows()<\/p>\n
else:<\/p>\n
    print("The images have different sizes.")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001PIL\u5e93\u4e2d\u7684\u9010\u50cf\u7d20\u6bd4\u8f83<\/h3>\n<\/p>\n
PIL\uff08Python Imaging Library\uff09\u662f\u4e00\u4e2a\u7528\u4e8e\u56fe\u50cf\u5904\u7406\u7684\u5e93\uff0c\u53ef\u4ee5\u7528\u6765\u9010\u50cf\u7d20\u6bd4\u8f83\u4e24\u5e45\u56fe\u50cf\u7684\u5dee\u5f02\u3002<\/p>\n<\/p>\n
1. \u5b89\u88c5PIL<\/h4>\n<\/p>\n
PIL\u5df2\u88abPillow\u53d6\u4ee3\uff0c\u53ef\u4ee5\u4f7f\u7528pip\u5b89\u88c5Pillow\uff1a<\/p>\n<\/p>\n
pip install Pillow<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u8bfb\u53d6\u548c\u5904\u7406\u56fe\u50cf<\/h4>\n<\/p>\n
\u4f7f\u7528Pillow\u8bfb\u53d6\u56fe\u50cf\uff0c\u5e76\u9010\u50cf\u7d20\u6bd4\u8f83\u4e24\u5e45\u56fe\u50cf\uff1a<\/p>\n<\/p>\n
from PIL import Image, ImageChops<\/p>\n
\u8bfb\u53d6\u56fe\u50cf<\/strong><\/h2>\n
image1 = Image.open('image1.jpg')<\/p>\n
image2 = Image.open('image2.jpg')<\/p>\n
\u786e\u4fdd\u56fe\u50cf\u5c3a\u5bf8\u76f8\u540c<\/strong><\/h2>\n
if image1.size == image2.size:<\/p>\n
    # \u9010\u50cf\u7d20\u6bd4\u8f83<\/p>\n
    diff = ImageChops.difference(image1, image2)<\/p>\n
    # \u663e\u793a\u5dee\u5f02\u56fe\u50cf<\/p>\n
    diff.show()<\/p>\n
else:<\/p>\n
    print("The images have different sizes.")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528SSIM\u8ba1\u7b97\u56fe\u50cf\u7684\u7ed3\u6784\u76f8\u4f3c\u6027\u6307\u6570<\/h3>\n<\/p>\n
\u7ed3\u6784\u76f8\u4f3c\u6027\u6307\u6570\uff08SSIM\uff09\u662f\u4e00\u79cd\u8861\u91cf\u4e24\u5e45\u56fe\u50cf\u4e4b\u95f4\u76f8\u4f3c\u7a0b\u5ea6\u7684\u65b9\u6cd5\uff0c\u8003\u8651\u4e86\u56fe\u50cf\u7684\u4eae\u5ea6\u3001\u5bf9\u6bd4\u5ea6\u548c\u7ed3\u6784\u4fe1\u606f\u3002<\/p>\n<\/p>\n
1. \u5b89\u88c5scikit-image<\/h4>\n<\/p>\n
SSIM\u53ef\u4ee5\u901a\u8fc7scikit-image\u5e93\u8fdb\u884c\u8ba1\u7b97\uff0c\u9996\u5148\u9700\u8981\u5b89\u88c5\u8be5\u5e93\uff1a<\/p>\n<\/p>\n
pip install scikit-image<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u8bfb\u53d6\u548c\u5904\u7406\u56fe\u50cf<\/h4>\n<\/p>\n
\u4f7f\u7528scikit-image\u8ba1\u7b97\u4e24\u5e45\u56fe\u50cf\u7684SSIM\uff1a<\/p>\n<\/p>\n
from skimage.metrics import structural_similarity as ssim<\/p>\n
import cv2<\/p>\n
\u8bfb\u53d6\u56fe\u50cf<\/strong><\/h2>\n
image1 = cv2.imread('image1.jpg', cv2.IMREAD_GRAYSCALE)<\/p>\n
image2 = cv2.imread('image2.jpg', cv2.IMREAD_GRAYSCALE)<\/p>\n
\u786e\u4fdd\u56fe\u50cf\u5c3a\u5bf8\u76f8\u540c<\/strong><\/h2>\n
if image1.shape == image2.shape:<\/p>\n
    # \u8ba1\u7b97SSIM<\/p>\n
    ssim_index, diff = ssim(image1, image2, full=True)<\/p>\n
    print(f"SSIM: {ssim_index}")<\/p>\n
    # \u5c06\u5dee\u5f02\u7ed3\u679c\u8f6c\u4e3a\u53ef\u89c6\u5316\u56fe\u50cf<\/p>\n
    diff = (diff * 255).astype("uint8")<\/p>\n
    # \u663e\u793a\u5dee\u5f02\u56fe\u50cf<\/p>\n
    cv2.imshow('Difference', diff)<\/p>\n
    cv2.waitKey(0)<\/p>\n
    cv2.destroyAllWindows()<\/p>\n
else:<\/p>\n
    print("The images have different sizes.")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u7ed3\u5408\u591a\u79cd\u65b9\u6cd5\u8fdb\u884c\u56fe\u50cf\u5dee\u5f02\u68c0\u6d4b<\/h3>\n<\/p>\n
\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u53ef\u80fd\u9700\u8981\u7ed3\u5408\u591a\u79cd\u65b9\u6cd5\u6765\u8fdb\u884c\u56fe\u50cf\u5dee\u5f02\u68c0\u6d4b\uff0c\u4ee5\u83b7\u5f97\u66f4\u51c6\u786e\u7684\u7ed3\u679c\u3002\u4e0b\u9762\u662f\u4e00\u4e2a\u7ed3\u5408OpenCV\u548cSSIM\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import cv2<\/p>\n
from skimage.metrics import structural_similarity as ssim<\/p>\n
\u8bfb\u53d6\u56fe\u50cf<\/strong><\/h2>\n
image1 = cv2.imread('image1.jpg')<\/p>\n
image2 = cv2.imread('image2.jpg')<\/p>\n
\u786e\u4fdd\u56fe\u50cf\u5c3a\u5bf8\u76f8\u540c<\/strong><\/h2>\n
if image1.shape == image2.shape:<\/p>\n
    # \u8f6c\u4e3a\u7070\u5ea6\u56fe\u50cf<\/p>\n
    gray_image1 = cv2.cvtColor(image1, cv2.COLOR_BGR2GRAY)<\/p>\n
    gray_image2 = cv2.cvtColor(image2, cv2.COLOR_BGR2GRAY)<\/p>\n
    # \u8ba1\u7b97SSIM<\/p>\n
    ssim_index, diff = ssim(gray_image1, gray_image2, full=True)<\/p>\n
    print(f"SSIM: {ssim_index}")<\/p>\n
    # \u5c06\u5dee\u5f02\u7ed3\u679c\u8f6c\u4e3a\u53ef\u89c6\u5316\u56fe\u50cf<\/p>\n
    diff = (diff * 255).astype("uint8")<\/p>\n
    # \u8ba1\u7b97\u7edd\u5bf9\u5dee\u5f02<\/p>\n
    abs_diff = cv2.absdiff(image1, image2)<\/p>\n
    # \u663e\u793a\u5dee\u5f02\u56fe\u50cf<\/p>\n
    cv2.imshow('SSIM Difference', diff)<\/p>\n
    cv2.imshow('Absolute Difference', abs_diff)<\/p>\n
    cv2.waitKey(0)<\/p>\n
    cv2.destroyAllWindows()<\/p>\n
else:<\/p>\n
    print("The images have different sizes.")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u5e94\u7528\u573a\u666f\u548c\u4f18\u5316\u5efa\u8bae<\/h3>\n<\/p>\n
\u56fe\u50cf\u5dee\u5f02\u68c0\u6d4b\u5728\u8bb8\u591a\u5b9e\u9645\u5e94\u7528\u4e2d\u975e\u5e38\u6709\u7528\uff0c\u4f8b\u5982\u76d1\u63a7\u7cfb\u7edf\u4e2d\u7684\u5f02\u5e38\u68c0\u6d4b\u3001\u56fe\u50cf\u5904\u7406\u4e2d\u7684\u8d28\u91cf\u68c0\u6d4b\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u4f18\u5316\u5efa\u8bae\uff1a<\/p>\n<\/p>\n
1. \u56fe\u50cf\u9884\u5904\u7406<\/h4>\n<\/p>\n
\u5728\u8fdb\u884c\u5dee\u5f02\u68c0\u6d4b\u4e4b\u524d\uff0c\u53ef\u4ee5\u5bf9\u56fe\u50cf\u8fdb\u884c\u4e00\u4e9b\u9884\u5904\u7406\uff0c\u5982\u53bb\u566a\u3001\u5bf9\u9f50\u7b49\uff0c\u4ee5\u63d0\u9ad8\u68c0\u6d4b\u7cbe\u5ea6\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528OpenCV\u4e2d\u7684\u56fe\u50cf\u5e73\u6ed1\u51fd\u6570\u5bf9\u56fe\u50cf\u8fdb\u884c\u53bb\u566a\u5904\u7406\u3002<\/p>\n<\/p>\n
# \u56fe\u50cf\u53bb\u566a\u5904\u7406<\/p>\n
image1_denoised = cv2.GaussianBlur(image1, (5, 5), 0)<\/p>\n
image2_denoised = cv2.GaussianBlur(image2, (5, 5), 0)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u591a\u5c3a\u5ea6\u5206\u6790<\/h4>\n<\/p>\n
\u5bf9\u4e8e\u4e00\u4e9b\u7ec6\u8282\u5dee\u5f02\uff0c\u53ef\u4ee5\u4f7f\u7528\u591a\u5c3a\u5ea6\u5206\u6790\u65b9\u6cd5\uff0c\u5982\u91d1\u5b57\u5854\u56fe\u50cf\u5904\u7406\uff0c\u9010\u5c42\u6bd4\u8f83\u56fe\u50cf\u7684\u5dee\u5f02\uff0c\u4ee5\u83b7\u5f97\u66f4\u7cbe\u7ec6\u7684\u68c0\u6d4b\u7ed3\u679c\u3002<\/p>\n<\/p>\n
# \u6784\u5efa\u56fe\u50cf\u91d1\u5b57\u5854<\/p>\n
image1_pyramid = [image1]<\/p>\n
image2_pyramid = [image2]<\/p>\n
for i in range(3):<\/p>\n
    image1_pyramid.append(cv2.pyrDown(image1_pyramid[-1]))<\/p>\n
    image2_pyramid.append(cv2.pyrDown(image2_pyramid[-1]))<\/p>\n
\u9010\u5c42\u6bd4\u8f83\u5dee\u5f02<\/strong><\/h2>\n
for i in range(3, -1, -1):<\/p>\n
    diff = cv2.absdiff(image1_pyramid[i], image2_pyramid[i])<\/p>\n
    cv2.imshow(f'Pyramid Level {i} Difference', diff)<\/p>\n
    cv2.waitKey(0)<\/p>\n
cv2.destroyAllWindows()<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u7ed3\u5408\u673a\u5668\u5b66\u4e60<\/a>\u7b97\u6cd5<\/h4>\n<\/p>\n
\u5728\u66f4\u590d\u6742\u7684\u5e94\u7528\u573a\u666f\u4e2d\uff0c\u53ef\u4ee5\u7ed3\u5408\u673a\u5668\u5b66\u4e60\u7b97\u6cd5\u8fdb\u884c\u56fe\u50cf\u5dee\u5f02\u68c0\u6d4b\u3002\u4f8b\u5982\uff0c\u4f7f\u7528\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\uff08CNN\uff09\u8fdb\u884c\u56fe\u50cf\u7279\u5f81\u63d0\u53d6\u548c\u6bd4\u8f83\uff0c\u4ee5\u83b7\u5f97\u66f4\u51c6\u786e\u7684\u68c0\u6d4b\u7ed3\u679c\u3002<\/p>\n<\/p>\n
from keras.models import load_model<\/p>\n
import numpy as np<\/p>\n
\u52a0\u8f7d\u9884\u8bad\u7ec3\u7684CNN\u6a21\u578b<\/strong><\/h2>\n
model = load_model('pretrained_cnn.h5')<\/p>\n
\u63d0\u53d6\u56fe\u50cf\u7279\u5f81<\/strong><\/h2>\n
image1_features = model.predict(np.expand_dims(image1, axis=0))<\/p>\n
image2_features = model.predict(np.expand_dims(image2, axis=0))<\/p>\n
\u8ba1\u7b97\u7279\u5f81\u5dee\u5f02<\/strong><\/h2>\n
feature_difference = np.linalg.norm(image1_features - image2_features)<\/p>\n
print(f"Feature Difference: {feature_difference}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u603b\u7ed3<\/h3>\n<\/p>\n
\u5728Python\u4e2d\u5bfb\u627e\u56fe\u7247\u4e4b\u95f4\u7684\u5dee\u5f02\u53ef\u4ee5\u4f7f\u7528\u591a\u79cd\u65b9\u6cd5\uff0c\u5305\u62ecOpenCV\u7684absdiff\u51fd\u6570\u3001PIL\u5e93\u7684\u9010\u50cf\u7d20\u6bd4\u8f83\u3001SSIM\u8ba1\u7b97\u56fe\u50cf\u7684\u7ed3\u6784\u76f8\u4f3c\u6027\u6307\u6570<\/strong>\u7b49\u3002\u901a\u8fc7\u7ed3\u5408\u8fd9\u4e9b\u65b9\u6cd5\uff0c\u5e76\u8fdb\u884c\u9002\u5f53\u7684\u56fe\u50cf\u9884\u5904\u7406\u548c\u4f18\u5316\uff0c\u53ef\u4ee5\u5b9e\u73b0\u51c6\u786e\u7684\u56fe\u50cf\u5dee\u5f02\u68c0\u6d4b\u3002\u5728\u66f4\u590d\u6742\u7684\u5e94\u7528\u573a\u666f\u4e2d\uff0c\u53ef\u4ee5\u7ed3\u5408\u673a\u5668\u5b66\u4e60\u7b97\u6cd5\u8fdb\u884c\u56fe\u50cf\u7279\u5f81\u63d0\u53d6\u548c\u6bd4\u8f83\uff0c\u4ee5\u83b7\u5f97\u66f4\u7cbe\u786e\u7684\u7ed3\u679c\u3002\u5e0c\u671b\u672c\u6587\u5bf9\u60a8\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\u8fdb\u884c\u56fe\u50cf\u5dee\u5f02\u68c0\u6d4b\u6709\u6240\u5e2e\u52a9\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5728Python\u4e2d\u4f7f\u7528\u5e93\u6765\u6bd4\u8f83\u4e24\u5f20\u56fe\u7247\u7684\u5dee\u5f02\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u60a8\u53ef\u4ee5\u4f7f\u7528Pillow\u548cOpenCV\u7b49\u5e93\u6765\u6bd4\u8f83\u4e24\u5f20\u56fe\u7247\u3002Pillow\u63d0\u4f9b\u4e86\u7b80\u5355\u7684\u56fe\u50cf\u5904\u7406\u529f\u80fd\uff0c\u800cOpenCV\u5219\u66f4\u52a0\u590d\u6742\u548c\u5f3a\u5927\u3002\u60a8\u53ef\u4ee5\u52a0\u8f7d\u4e24\u5f20\u56fe\u7247\uff0c\u7136\u540e\u4f7f\u7528\u50cf\u7d20\u6bd4\u8f83\u7684\u65b9\u6cd5\u6765\u67e5\u627e\u4e0d\u540c\u4e4b\u5904\u3002\u6b64\u5916\uff0cOpenCV\u8fd8\u63d0\u4f9b\u4e86\u56fe\u50cf\u5dee\u5f02\u68c0\u6d4b\u7684\u51fd\u6570\uff0c\u53ef\u4ee5\u66f4\u9ad8\u6548\u5730\u8bc6\u522b\u53d8\u5316\u3002<\/p>\n
\u6709\u54ea\u4e9b\u5e38\u7528\u7684\u65b9\u6cd5\u53ef\u4ee5\u6709\u6548\u8bc6\u522b\u56fe\u7247\u4e4b\u95f4\u7684\u5dee\u5f02\uff1f<\/strong>
\u8bc6\u522b\u56fe\u7247\u5dee\u5f02\u7684\u5e38\u7528\u65b9\u6cd5\u5305\u62ec\u50cf\u7d20\u7ea7\u6bd4\u8f83\u3001\u76f4\u65b9\u56fe\u6bd4\u8f83\u548c\u56fe\u50cf\u7279\u5f81\u5339\u914d\u3002\u50cf\u7d20\u7ea7\u6bd4\u8f83\u662f\u6700\u76f4\u63a5\u7684\u65b9\u6cd5\uff0c\u901a\u8fc7\u9010\u50cf\u7d20\u68c0\u67e5\u6765\u53d1\u73b0\u4e0d\u540c\u4e4b\u5904\u3002\u76f4\u65b9\u56fe\u6bd4\u8f83\u5219\u901a\u8fc7\u5206\u6790\u989c\u8272\u5206\u5e03\u6765\u8bc6\u522b\u53d8\u5316\u3002\u56fe\u50cf\u7279\u5f81\u5339\u914d\u5219\u4f7f\u7528\u7b97\u6cd5\uff08\u5982SIFT\u6216ORB\uff09\u6765\u5bfb\u627e\u56fe\u7247\u4e2d\u7684\u5173\u952e\u70b9\u5e76\u8fdb\u884c\u5339\u914d\uff0c\u8fd9\u5bf9\u4e8e\u590d\u6742\u7684\u56fe\u50cf\u5dee\u5f02\u68c0\u6d4b\u975e\u5e38\u6709\u6548\u3002<\/p>\n
\u5728\u5904\u7406\u56fe\u7247\u5dee\u5f02\u65f6\uff0c\u5982\u4f55\u63d0\u9ad8\u6bd4\u8f83\u7684\u51c6\u786e\u6027\u548c\u6548\u7387\uff1f<\/strong>
\u63d0\u9ad8\u6bd4\u8f83\u7684\u51c6\u786e\u6027\u53ef\u4ee5\u901a\u8fc7\u9884\u5904\u7406\u56fe\u50cf\u6765\u5b9e\u73b0\uff0c\u4f8b\u5982\u8c03\u6574\u4eae\u5ea6\u3001\u5bf9\u6bd4\u5ea6\u548c\u5c3a\u5bf8\uff0c\u786e\u4fdd\u4e24\u5f20\u56fe\u7247\u5728\u540c\u4e00\u6807\u51c6\u4e0b\u8fdb\u884c\u6bd4\u8f83\u3002\u4f7f\u7528\u56fe\u50cf\u5dee\u5f02\u7b97\u6cd5\u65f6\uff0c\u9009\u62e9\u5408\u9002\u7684\u9608\u503c\u548c\u65b9\u6cd5\u4e5f\u4f1a\u5f71\u54cd\u7ed3\u679c\u3002\u4e3a\u4e86\u63d0\u9ad8\u6548\u7387\uff0c\u60a8\u53ef\u4ee5\u5728\u5904\u7406\u8fc7\u7a0b\u4e2d\u53ea\u5173\u6ce8\u611f\u5174\u8da3\u7684\u533a\u57df\uff0c\u800c\u4e0d\u662f\u5bf9\u6574\u4e2a\u56fe\u50cf\u8fdb\u884c\u5206\u6790\uff0c\u4ece\u800c\u51cf\u5c11\u8ba1\u7b97\u91cf\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\u5bfb\u627e\u56fe\u7247\u4e4b\u95f4\u7684\u5dee\u5f02\uff0c\u53ef\u4ee5\u4f7f\u7528\u56fe\u50cf\u5904\u7406\u5e93\uff08\u5982OpenCV\u548cPIL\uff09\u4ee5\u53ca\u56fe\u50cf\u6bd4\u8f83\u7b97\u6cd5\uff08\u5982\u7ed3\u6784\u76f8\u4f3c\u6027 […]","protected":false},"author":3,"featured_media":1062829,"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\/1062813"}],"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=1062813"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1062813\/revisions"}],"predecessor-version":[{"id":1062830,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1062813\/revisions\/1062830"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1062829"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1062813"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1062813"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1062813"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}