{
  "source_file": "0930",
  "source_platform": "技术平台",
  "author": "OpenCV",
  "title_listed": "Feature Detection and Description (SIFT/ORB)",
  "keywords": "SIFT,ORB,特征检测",
  "domain": "图像处理",
  "content_type": "官方教程",
  "is_paid_flag": "否",
  "url": "https://docs.opencv.org/4.x/db/d27/tutorial_py_table_of_contents_feature2d.html",
  "publish_date": "持续更新",
  "corpus_stage": "图像处理",
  "notes": "特征检测与描述",
  "id": "8d6bd2d319aa",
  "collected_at": "2026-10-02T18:37:51",
  "title": "OpenCV: Feature Detection and Description",
  "body_markdown": "|  | OpenCV 4.13.0    Open Source Computer Vision | \n[Understanding Features](../../df/d54/tutorial_py_features_meaning.html)\nWhat are the main features in an image? How can finding those features be useful to us?\n[Harris Corner Detection](../../dc/d0d/tutorial_py_features_harris.html)\nOkay, Corners are good features? But how do we find them?\n[Shi-Tomasi Corner Detector & Good Features to Track](../../d4/d8c/tutorial_py_shi_tomasi.html)\nWe will look into Shi-Tomasi corner detection\n[Introduction to SIFT (Scale-Invariant Feature Transform)](../../da/df5/tutorial_py_sift_intro.html)\nHarris corner detector is not good enough when scale of image changes. Lowe developed a breakthrough method to find scale-invariant features and it is called SIFT\n[Introduction to SURF (Speeded-Up Robust Features)](../../df/dd2/tutorial_py_surf_intro.html)\nSIFT is really good, but not fast enough, so people came up with a speeded-up version called SURF.\n[FAST Algorithm for Corner Detection](../../df/d0c/tutorial_py_fast.html)\nAll the above feature detection methods are good in some way. But they are not fast enough to work in real-time applications like SLAM. There comes the FAST algorithm, which is really \"FAST\".\n[BRIEF (Binary Robust Independent Elementary Features)](../../dc/d7d/tutorial_py_brief.html)\nSIFT uses a feature descriptor with 128 floating point numbers. Consider thousands of such features. It takes lots of memory and more time for matching. We can compress it to make it faster. But still we have to calculate it first. There comes BRIEF which gives the shortcut to find binary descriptors with less memory, faster matching, still higher recognition rate.\n[ORB (Oriented FAST and Rotated BRIEF)](../../d1/d89/tutorial_py_orb.html)\nSIFT and SURF are good in what they do, but what if you have to pay a few dollars every year to use them in your applications? Yeah, they are patented!!! To solve that problem, OpenCV devs came up with a new \"FREE\" alternative to SIFT & SURF, and that is ORB.\n[Feature Matching](../../dc/dc3/tutorial_py_matcher.html)\nWe know a great deal about feature detectors and descriptors. It is time to learn how to match different descriptors. OpenCV provides two techniques, Brute-Force matcher and FLANN based matcher.\n[Feature Matching + Homography to find Objects](../../d1/de0/tutorial_py_feature_homography.html)\nNow we know about feature matching. Let's mix it up with calib3d module to find objects in a complex image.",
  "metadata": {
    "title": "OpenCV: Feature Detection and Description",
    "engine": "curl_cffi"
  },
  "paywall": {
    "listed_paid": false,
    "detected": false,
    "marker": "",
    "public_only": false,
    "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙"
  },
  "crawl": {
    "success": true,
    "status_code": 200,
    "error": "",
    "retried": true,
    "engine": "curl_cffi+trafilatura"
  },
  "code_blocks": [],
  "images": [],
  "audio": [],
  "videos": [],
  "links": [
    {
      "type": "external",
      "href": "https://www.cloudflare.com"
    },
    {
      "type": "external",
      "href": "https://www.cloudflare.com/privacypolicy/"
    }
  ],
  "retry_at": "2026-10-03T08:12:24",
  "final_url": "https://docs.opencv.org/4.13.0/db/d27/tutorial_py_table_of_contents_feature2d.html",
  "repair_version": 2,
  "repaired_at": "2026-10-20T17:29:26Z",
  "source_url": "https://docs.opencv.org/4.x/db/d27/tutorial_py_table_of_contents_feature2d.html",
  "delivery_status": "unverified",
  "discovery_status": "http_403",
  "missing_reason": "http_403",
  "repair_error": "",
  "actual_video_files": [],
  "source_body_markdown": "|  | OpenCV 4.13.0    Open Source Computer Vision | \n[Understanding Features](../../df/d54/tutorial_py_features_meaning.html)\nWhat are the main features in an image? How can finding those features be useful to us?\n[Harris Corner Detection](../../dc/d0d/tutorial_py_features_harris.html)\nOkay, Corners are good features? But how do we find them?\n[Shi-Tomasi Corner Detector & Good Features to Track](../../d4/d8c/tutorial_py_shi_tomasi.html)\nWe will look into Shi-Tomasi corner detection\n[Introduction to SIFT (Scale-Invariant Feature Transform)](../../da/df5/tutorial_py_sift_intro.html)\nHarris corner detector is not good enough when scale of image changes. Lowe developed a breakthrough method to find scale-invariant features and it is called SIFT\n[Introduction to SURF (Speeded-Up Robust Features)](../../df/dd2/tutorial_py_surf_intro.html)\nSIFT is really good, but not fast enough, so people came up with a speeded-up version called SURF.\n[FAST Algorithm for Corner Detection](../../df/d0c/tutorial_py_fast.html)\nAll the above feature detection methods are good in some way. But they are not fast enough to work in real-time applications like SLAM. There comes the FAST algorithm, which is really \"FAST\".\n[BRIEF (Binary Robust Independent Elementary Features)](../../dc/d7d/tutorial_py_brief.html)\nSIFT uses a feature descriptor with 128 floating point numbers. Consider thousands of such features. It takes lots of memory and more time for matching. We can compress it to make it faster. But still we have to calculate it first. There comes BRIEF which gives the shortcut to find binary descriptors with less memory, faster matching, still higher recognition rate.\n[ORB (Oriented FAST and Rotated BRIEF)](../../d1/d89/tutorial_py_orb.html)\nSIFT and SURF are good in what they do, but what if you have to pay a few dollars every year to use them in your applications? Yeah, they are patented!!! To solve that problem, OpenCV devs came up with a new \"FREE\" alternative to SIFT & SURF, and that is ORB.\n[Feature Matching](../../dc/dc3/tutorial_py_matcher.html)\nWe know a great deal about feature detectors and descriptors. It is time to learn how to match different descriptors. OpenCV provides two techniques, Brute-Force matcher and FLANN based matcher.\n[Feature Matching + Homography to find Objects](../../d1/de0/tutorial_py_feature_homography.html)\nNow we know about feature matching. Let's mix it up with calib3d module to find objects in a complex image.",
  "body_base_path": "attachments/8d6bd2d319aa/pages/",
  "body_markdown_path": "attachments/8d6bd2d319aa/pages/archived-body.md",
  "local_html": "attachments/8d6bd2d319aa/pages/archived-body.html",
  "body_source": "prior_capture"
}