{"id":46595,"date":"2024-12-02T15:21:23","date_gmt":"2024-12-02T07:21:23","guid":{"rendered":"https:\/\/fwq.ai\/blog\/46595\/"},"modified":"2024-12-02T15:21:23","modified_gmt":"2024-12-02T07:21:23","slug":"%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8%e5%87%bd%e6%95%b0%e5%bc%8f%e7%bc%96%e7%a8%8b%e4%bc%98%e5%8c%96%e5%9b%be%e5%83%8f%e5%a4%84%e7%90%86%e7%ae%97%e6%b3%95","status":"publish","type":"post","link":"https:\/\/fwq.ai\/blog\/46595\/","title":{"rendered":"\u5982\u4f55\u4f7f\u7528\u51fd\u6570\u5f0f\u7f16\u7a0b\u4f18\u5316\u56fe\u50cf\u5904\u7406\u7b97\u6cd5"},"content":{"rendered":"

<\/b> <\/p>\n

\u5982\u4f55\u4f7f\u7528\u51fd\u6570\u5f0f\u7f16\u7a0b\u4f18\u5316\u56fe\u50cf\u5904\u7406\u7b97\u6cd5<\/h1>\n

\u4f60\u5728\u5b66\u4e60\u6587\u7ae0<\/span>\u76f8\u5173\u7684\u77e5\u8bc6\u5417\uff1f\u672c\u6587\u300a\u5982\u4f55\u4f7f\u7528\u51fd\u6570\u5f0f\u7f16\u7a0b\u4f18\u5316\u56fe\u50cf\u5904\u7406\u7b97\u6cd5\u300b<\/span>\uff0c\u4e3b\u8981\u4ecb\u7ecd\u7684\u5185\u5bb9\u5c31\u6d89\u53ca\u5230<\/span>\uff0c\u5982\u679c\u4f60\u60f3\u63d0\u5347\u81ea\u5df1\u7684\u5f00\u53d1\u80fd\u529b\uff0c\u5c31\u4e0d\u8981\u9519\u8fc7\u8fd9\u7bc7\u6587\u7ae0\uff0c\u5927\u5bb6\u8981\u77e5\u9053\u7f16\u7a0b\u7406\u8bba\u57fa\u7840\u548c\u5b9e\u6218\u64cd\u4f5c\u90fd\u662f\u4e0d\u53ef\u6216\u7f3a\u7684\u54e6\uff01<\/p>\n

\"\u5982\u4f55\u4f7f\u7528\u51fd\u6570\u5f0f\u7f16\u7a0b\u4f18\u5316\u56fe\u50cf\u5904\u7406\u7b97\u6cd5\u63d2\u56fe\"<\/p>\n

\u5982\u4f55\u4f7f\u7528\u51fd\u6570\u5f0f\u7f16\u7a0b\u4f18\u5316\u56fe\u50cf\u5904\u7406\u7b97\u6cd5<\/h2>\n

\u5f15\u8a00<\/strong><\/p>\n

\u51fd\u6570\u5f0f\u7f16\u7a0b\u662f\u4e00\u79cd\u7f16\u7a0b\u8303\u4f8b\uff0c\u5b83\u5f3a\u8c03\u4f7f\u7528\u4e0d\u53ef\u53d8\u6570\u636e\u548c\u7eaf\u51fd\u6570\u3002\u4e0e\u4f20\u7edf\u7684\u9762\u5411\u5bf9\u8c61\u7f16\u7a0b\u76f8\u6bd4\uff0c\u51fd\u6570\u5f0f\u7f16\u7a0b\u5728\u56fe\u50cf\u5904\u7406\u4e2d\u5177\u6709\u8bb8\u591a\u6f5c\u5728\u7684\u597d\u5904\uff0c\u5305\u62ec\uff1a<\/p>\n

    \n
  • \u5e76\u884c\u6027\uff1a<\/strong> \u7531\u4e8e\u51fd\u6570\u662f\u4e0d\u53ef\u53d8\u7684\uff0c\u56e0\u6b64\u5b83\u4eec\u53ef\u4ee5\u5728\u4e0d\u540c\u7684\u7ebf\u7a0b\u6216\u8fdb\u7a0b\u4e2d\u5b89\u5168\u5730\u540c\u65f6\u6267\u884c\u3002<\/li>\n
  • \u53ef\u7ec4\u5408\u6027\uff1a<\/strong> \u51fd\u6570\u53ef\u4ee5\u8f7b\u677e\u5730\u7ec4\u5408\u5728\u4e00\u8d77\u4ee5\u521b\u5efa\u65b0\u7684\u3001\u66f4\u590d\u6742\u7684\u51fd\u6570\uff0c\u8fd9\u7b80\u5316\u4e86\u590d\u6742\u64cd\u4f5c\u7684\u5f00\u53d1\u3002<\/li>\n
  • \u6d4b\u8bd5\u6027\uff1a<\/strong> \u7eaf\u51fd\u6570\u66f4\u5bb9\u6613\u6d4b\u8bd5\uff0c\u56e0\u4e3a\u5b83\u4eec\u7684\u8f93\u51fa\u4ec5\u53d6\u51b3\u4e8e\u5b83\u4eec\u7684\u8f93\u5165\u3002<\/li>\n<\/ul>\n

    \u57fa\u4e8e\u51fd\u6570\u5f0f\u7f16\u7a0b\u7684\u56fe\u50cf\u5904\u7406\u7b97\u6cd5\u4f18\u5316<\/strong><\/p>\n

    \u4ee5\u4e0b\u662f\u4e00\u4e9b\u4f7f\u7528\u51fd\u6570\u5f0f\u7f16\u7a0b\u4f18\u5316\u56fe\u50cf\u5904\u7406\u7b97\u6cd5\u7684\u5b9e\u9645\u793a\u4f8b\uff1a<\/p>\n

    \u56fe\u50cf\u8f6c\u6362<\/strong><\/p>\n

      \n
    • \n

      \u4f7f\u7528 map<\/code> \u51fd\u6570\u5c06\u50cf\u7d20\u503c\u8f6c\u6362\u4e3a\u7070\u5ea6\uff1a<\/p>\n

      grayscale_image = image.map(lambda pixel: (pixel[0] + pixel[1] + pixel[2]) \/ 3)<\/pre>\n<\/li>\n<\/ul>\n
      \u56fe\u50cf\u6ee4\u6ce2<\/strong><\/p>\n
        \n
      • \n
        \u4f7f\u7528 filter<\/code> \u51fd\u6570\u4ece\u56fe\u50cf\u4e2d\u5220\u9664\u566a\u70b9\uff1a<\/p>\n
        denoised_image = image.filter(lambda pixel: pixel < 128)<\/pre>\n<\/li>\n<\/ul>\n
        \u56fe\u50cf\u5206\u5272<\/strong><\/p>\n
          \n
        • \n
          \u4f7f\u7528 reduce<\/code> \u51fd\u6570\u8ba1\u7b97\u56fe\u50cf\u7684\u76f4\u65b9\u56fe\uff1a<\/p>\n
          histogram = image.reduce(lambda acc, pixel: acc[pixel] + 1, {})<\/pre>\n<\/li>\n<\/ul>\n
          \u5b9e\u6218\u6848\u4f8b\uff1a\u56fe\u50cf\u5206\u5272<\/strong><\/p>\n
          \u8003\u8651\u4ee5\u4e0b\u56fe\u50cf\u5206\u5272\u95ee\u9898\uff1a\u7ed9\u5b9a\u4e00\u5e45\u56fe\u50cf\uff0c\u6211\u4eec\u9700\u8981\u5c06\u56fe\u50cf\u5206\u5272\u6210\u4e0d\u540c\u7684\u533a\u57df\u6216\u5bf9\u8c61\u3002<\/p>\n
          \u4f7f\u7528\u51fd\u6570\u5f0f\u7f16\u7a0b\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u5730\u5b9e\u73b0\u8fd9\u4e00\u7b97\u6cd5\uff1a<\/p>\n
          import numpy as np\nfrom functools import reduce\n\ndef segment_image(image):\n    # \u521d\u59cb\u5316\u6807\u7b7e\u6570\u7ec4\n    labels = np.zeros_like(image)\n\n    # \u5faa\u73af\u904d\u5386\u56fe\u50cf\u4e2d\u7684\u6bcf\u4e2a\u50cf\u7d20\n    for y in range(image.shape[0]):\n        for x in range(image.shape[1]):\n            # \u5982\u679c\u50cf\u7d20\u5c1a\u672a\u6807\u8bb0\n            if labels[y, x] == 0:\n                # \u4f7f\u7528\u79cd\u5b50\u586b\u5145\u7b97\u6cd5\u4e3a\u76f8\u90bb\u533a\u57df\u5206\u914d\u4e00\u4e2a\u552f\u4e00\u7684\u6807\u7b7e\n                labels = fill_region(image, labels, y, x)\n\n    return labels\n\ndef fill_region(image, labels, y, x):\n    # \u5f53\u524d\u533a\u57df\u7684\u6807\u7b7e\n    label = np.max(labels) + 1\n\n    # \u4f7f\u7528\u6df1\u5ea6\u4f18\u5148\u641c\u7d22\u586b\u5145\u533a\u57df\n    stack = [(y, x)]\n    while stack:\n        y, x = stack.pop()\n        # \u5982\u679c\u50cf\u7d20\u6ee1\u8db3\u6761\u4ef6\n        if image[y, x] > 128 and labels[y, x] == 0:\n            # \u6807\u8bb0\u50cf\u7d20\n            labels[y, x] = label\n            # \u5c06\u76f8\u90bb\u50cf\u7d20\u6dfb\u52a0\u5230\u5806\u6808\u4e2d\n            stack.append((y+1, x))\n            stack.append((y-1, x))\n            stack.append((y, x+1))\n            stack.append((y, x-1))\n\n    return labels<\/pre>\n
          \u7ed3\u8bba<\/strong><\/p>\n
          \u51fd\u6570\u5f0f\u7f16\u7a0b\u4e3a\u56fe\u50cf\u5904\u7406\u7b97\u6cd5\u7684\u4f18\u5316\u63d0\u4f9b\u4e86\u8bb8\u591a\u597d\u5904\u3002\u901a\u8fc7\u5229\u7528\u4e0d\u53ef\u53d8\u6570\u636e\u548c\u7eaf\u51fd\u6570\uff0c\u6211\u4eec\u53ef\u4ee5\u521b\u5efa\u66f4\u6613\u4e8e\u5e76\u884c\u5316\u3001\u7ec4\u5408\u548c\u6d4b\u8bd5\u7684\u7b97\u6cd5\u3002<\/p>\n
          \u7ec8\u4e8e\u4ecb\u7ecd\u5b8c\u5566\uff01\u5c0f\u4f19\u4f34\u4eec\uff0c\u8fd9\u7bc7\u5173\u4e8e\u300a\u5982\u4f55\u4f7f\u7528\u51fd\u6570\u5f0f\u7f16\u7a0b\u4f18\u5316\u56fe\u50cf\u5904\u7406\u7b97\u6cd5\u300b\u7684\u4ecb\u7ecd\u5e94\u8be5\u8ba9\u4f60\u6536\u83b7\u591a\u591a\u4e86\u5427\uff01\u6b22\u8fce\u5927\u5bb6\u6536\u85cf\u6216\u5206\u4eab\u7ed9\u66f4\u591a\u9700\u8981\u5b66\u4e60\u7684\u670b\u53cb\u5427~\u7c73\u4e91\u516c\u4f17\u53f7\u4e5f\u4f1a\u53d1\u5e03\u6587\u7ae0\u76f8\u5173\u77e5\u8bc6\uff0c\u5feb\u6765\u5173\u6ce8\u5427\uff01<\/p>\n","protected":false},"excerpt":{"rendered":"
          \u5982\u4f55\u4f7f\u7528\u51fd\u6570\u5f0f\u7f16\u7a0b\u4f18\u5316\u56fe\u50cf\u5904\u7406\u7b97\u6cd5 \u4f60\u5728\u5b66\u4e60\u6587\u7ae0\u76f8\u5173\u7684\u77e5\u8bc6\u5417\uff1f\u672c\u6587\u300a\u5982\u4f55\u4f7f\u7528\u51fd\u6570\u5f0f\u7f16\u7a0b\u4f18\u5316\u56fe\u50cf\u5904\u7406\u7b97\u6cd5\u300b\uff0c\u4e3b\u8981\u4ecb\u7ecd\u7684\u5185\u5bb9\u5c31\u6d89\u53ca\u5230\uff0c\u5982\u679c\u4f60\u60f3\u63d0\u5347\u81ea\u5df1\u7684\u5f00\u53d1\u80fd\u529b\uff0c\u5c31\u4e0d\u8981\u9519\u8fc7\u8fd9\u7bc7\u6587\u7ae0\uff0c\u5927\u5bb6\u8981\u77e5\u9053\u7f16\u7a0b\u7406\u8bba\u57fa\u7840\u548c\u5b9e\u6218\u64cd\u4f5c\u90fd\u662f\u4e0d\u53ef\u6216\u7f3a\u7684\u54e6\uff01 \u5982\u4f55\u4f7f\u7528\u51fd\u6570\u5f0f\u7f16\u7a0b\u4f18\u5316\u56fe\u50cf\u5904\u7406\u7b97\u6cd5 \u5f15\u8a00 \u51fd\u6570\u5f0f\u7f16\u7a0b\u662f\u4e00\u79cd\u7f16\u7a0b\u8303\u4f8b\uff0c\u5b83\u5f3a\u8c03\u4f7f\u7528\u4e0d\u53ef\u53d8\u6570\u636e\u548c\u7eaf\u51fd\u6570\u3002\u4e0e\u4f20\u7edf\u7684\u9762\u5411\u5bf9\u8c61\u7f16\u7a0b\u76f8\u6bd4\uff0c\u51fd\u6570\u5f0f\u7f16\u7a0b\u5728\u56fe\u50cf\u5904\u7406\u4e2d\u5177\u6709\u8bb8\u591a\u6f5c\u5728\u7684\u597d\u5904\uff0c\u5305\u62ec\uff1a \u5e76\u884c\u6027\uff1a \u7531\u4e8e\u51fd\u6570\u662f\u4e0d\u53ef\u53d8\u7684\uff0c\u56e0\u6b64\u5b83\u4eec\u53ef\u4ee5\u5728\u4e0d\u540c\u7684\u7ebf\u7a0b\u6216\u8fdb\u7a0b\u4e2d\u5b89\u5168\u5730\u540c\u65f6\u6267\u884c\u3002 \u53ef\u7ec4\u5408\u6027\uff1a \u51fd\u6570\u53ef\u4ee5\u8f7b\u677e\u5730\u7ec4\u5408\u5728\u4e00\u8d77\u4ee5\u521b\u5efa\u65b0\u7684\u3001\u66f4\u590d\u6742\u7684\u51fd\u6570\uff0c\u8fd9\u7b80\u5316\u4e86\u590d\u6742\u64cd\u4f5c\u7684\u5f00\u53d1\u3002 \u6d4b\u8bd5\u6027\uff1a \u7eaf\u51fd\u6570\u66f4\u5bb9\u6613\u6d4b\u8bd5\uff0c\u56e0\u4e3a\u5b83\u4eec\u7684\u8f93\u51fa\u4ec5\u53d6\u51b3\u4e8e\u5b83\u4eec\u7684\u8f93\u5165\u3002 \u57fa\u4e8e\u51fd\u6570\u5f0f\u7f16\u7a0b\u7684\u56fe\u50cf\u5904\u7406\u7b97\u6cd5\u4f18\u5316 \u4ee5\u4e0b\u662f\u4e00\u4e9b\u4f7f\u7528\u51fd\u6570\u5f0f\u7f16\u7a0b\u4f18\u5316\u56fe\u50cf\u5904\u7406\u7b97\u6cd5\u7684\u5b9e\u9645\u793a\u4f8b\uff1a \u56fe\u50cf\u8f6c\u6362 \u4f7f\u7528 map \u51fd\u6570\u5c06\u50cf\u7d20\u503c\u8f6c\u6362\u4e3a\u7070\u5ea6\uff1a grayscale_image = image.map(lambda pixel: (pixel[0] + pixel[1] + pixel[2]) \/ 3) \u56fe\u50cf\u6ee4\u6ce2 \u4f7f\u7528 filter \u51fd\u6570\u4ece\u56fe\u50cf\u4e2d\u5220\u9664\u566a\u70b9\uff1a denoised_image = image.filter(lambda pixel: pixel < 128) \u56fe\u50cf\u5206\u5272 \u4f7f\u7528 reduce \u51fd\u6570\u8ba1\u7b97\u56fe\u50cf\u7684\u76f4\u65b9\u56fe\uff1a histogram = image.reduce(lambda acc, pixel: acc[pixel] + 1, {}) \u5b9e\u6218\u6848\u4f8b\uff1a\u56fe\u50cf\u5206\u5272 \u8003\u8651\u4ee5\u4e0b\u56fe\u50cf\u5206\u5272\u95ee\u9898\uff1a\u7ed9\u5b9a\u4e00\u5e45\u56fe\u50cf\uff0c\u6211\u4eec\u9700\u8981\u5c06\u56fe\u50cf\u5206\u5272\u6210\u4e0d\u540c\u7684\u533a\u57df\u6216\u5bf9\u8c61\u3002 \u4f7f\u7528\u51fd\u6570\u5f0f\u7f16\u7a0b\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u5730\u5b9e\u73b0\u8fd9\u4e00\u7b97\u6cd5\uff1a […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[16],"tags":[],"class_list":["post-46595","post","type-post","status-publish","format-standard","hentry","category-16"],"_links":{"self":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/46595","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/comments?post=46595"}],"version-history":[{"count":0,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/46595\/revisions"}],"wp:attachment":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/media?parent=46595"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/categories?post=46595"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/tags?post=46595"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}