{"id":7123,"date":"2019-05-30T09:26:53","date_gmt":"2019-05-30T00:26:53","guid":{"rendered":"http:\/\/www.gisdeveloper.co.kr\/?p=7123"},"modified":"2020-05-28T10:26:12","modified_gmt":"2020-05-28T01:26:12","slug":"python%ea%b3%bc-opencv-52-opencv%ec%97%90%ec%84%9c-k-means-%ea%b5%b0%ec%a7%91%ed%99%94clustering","status":"publish","type":"post","link":"http:\/\/www.gisdeveloper.co.kr\/?p=7123","title":{"rendered":"Python\uacfc OpenCV \u2013 52 : OpenCV\uc5d0\uc11c K-Means \uad70\uc9d1\ud654(Clustering)"},"content":{"rendered":"

\uc774 \uae00\uc758 \uc6d0\ubb38\uc740 https:\/\/opencv-python-tutroals.readthedocs.io\/en\/latest\/py_tutorials\/py_ml\/py_kmeans\/py_kmeans_opencv\/py_kmeans_opencv.html \uc785\ub2c8\ub2e4.<\/p>\n

OpenCV\uc5d0\uc11c K-Means \uc54c\uace0\ub9ac\uc998\uc744 \uc774\uc6a9\ud55c \ub370\uc774\ud130 \uad70\uc9d1\ud654\ub294 cv2.kmeans() \ud568\uc218\ub97c \ud1b5\ud574 \uc774\uc6a9 \ub429\ub2c8\ub2e4. \uc774 \ud568\uc218\uc5d0 \ub300\ud55c \uc778\uc790\ub294 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4.<\/p>\n

    \n
  1. samples : <\/bold>np.float32 \ub370\uc774\ud0c0 \ud0c0\uc785\uc774\uba70, \uac01 \ud53c\uccd0(Feature)\ub294 \ub2e8\uc77c \uc5f4(Column)\uc73c\ub85c \uc800\uc7a5\ub418\uc5b4\uc838 \uc788\uc5b4\uc57c \ud569\ub2c8\ub2e4.<\/li>\n
  2. nclusters(K) : <\/bold>\uad70\uc9d1\ud654\ud560 \uac1c\uc218<\/li>\n
  3. criteria : <\/bold>\ubc18\ubcf5\uc744 \uc885\ub8cc\ud560 \uc870\uac74\uc785\ub2c8\ub2e4. \uc870\uac74\uc774 \ub9cc\uc871\ub418\uba74 \uc54c\uace0\ub9ac\uc998\uc758 \ubc18\ubcf5\uc740 \uc911\uc9c0\ub429\ub2c8\ub2e4. 3\uac1c\uc758 \uc778\uc790\ub97c \uac16\ub294 \ud29c\ud50c(Tuple)\uc774\uba70, (type, max_iter, epsilon)\uc785\ub2c8\ub2e4. \uac01\uac01\uc758 \ub300\ud55c \uc778\uc790\ub294 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4.\n
      \n
    • type : <\/bold>\uc885\ub8cc \uc870\uac74\uc758 \ud0c0\uc785\uc73c\ub85c cv2.TERM_CRITERIA_EPS\ub294 \uc8fc\uc5b4\uc9c4 \uc815\ud655\ub3c4(epsilon \uc778\uc790)\uc5d0 \ub3c4\ub2ec\ud558\uba74 \ubc18\ubcf5\uc744 \uc911\ub2e8\ud558\uace0, cv2.TERM_CRITERIA_MAX_ITER\ub294 max_iter \uc778\uc790\uc5d0 \uc9c0\uc815\ub41c \ud69f\uc218\ub9cc\ud07c \ubc18\ubcf5\ud558\uace0 \uc911\ub2e8\ud569\ub2c8\ub2e4. cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER\ub97c \uc870\ud569\ud574 \uc0ac\uc6a9\ud558\uba74 \ub450\uac00\uc9c0 \uc870\uac74 \uc911 \ud558\ub098\uac00 \ub9cc\uc871\ub418\uba74 \ubc18\ubcf5\uc774 \uc911\ub2e8\ub429\ub2c8\ub2e4.<\/li>\n<\/li>\n
    • max_iter : \ucd5c\ub300 \ubc18\ubcf5\ud560 \ud69f\uc218(\uc815\uc218\ud615 \ud0c0\uc785)<\/bold><\/li>\n
    • epsilon : <\/bold>\uc815\ud655\ub3c4<\/li>\n<\/ul>\n<\/li>\n
    • attempts : <\/bold>\ub2e4\ub978 \ucd08\uae30 \ub77c\ubca8\ub9c1\uc744 \uc0ac\uc6a9\ud558\uba74\uc11c \uc2e4\ud589\ub418\ub294 \uc54c\uace0\ub9ac\uc998\uc758 \uc2e4\ud589 \ud69f\uc218\ub97c \uc9c0\uc815\ud558\ub294 \ud50c\ub798\uadf8. \uc54c\uace0\ub9ac\uc998\uc740 \ucd5c\uc801\uc758 \ucef4\ud329\ud2b8\ud568(Compactness)\uc744 \ub9cc\ub4dc\ub294 \ub77c\ubca8\uc744 \ubc18\ud658\ud569\ub2c8\ub2e4. \uc774 \ucef4\ud329\ud2b8\ud568\uc740 \ucd9c\ub825\uc73c\ub85c \ubc18\ud658\ub429\ub2c8\ub2e4.<\/li>\n
    • flags : <\/bold>\ucd08\uae30\uac12\uc744 \uc7a1\uc744 \uc911\uc2ec\uc5d0 \ub300\ud55c \ud50c\ub798\uadf8\ub85c\uc368 cv2.KMEANS_PP_CENTERS\uc640 cv2.KMEANS_RANDOM_CENTERS \uc911 \ud558\ub098\uac00 \uc0ac\uc6a9\ub429\ub2c8\ub2e4.<\/li>\n<\/ol>\n

      \uc774 \ud568\uc218\uc758 \ubc18\ud658\uac12\uc740 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4.<\/p>\n

        \n
      1. compactness : <\/bold>\uac01 \ud3ec\uc778\ud2b8\uc640 \uad70\uc9d1\ud654\ub97c \uc704\ud55c \uc911\uc2ec \uac04\uc758 \uac70\ub9ac\uc758 \uc81c\uacf1\uc758 \ud569<\/li>\n
      2. labes : <\/bold>\ub77c\ubca8\uc5d0 \ub300\ud55c \ubc30\uc5f4\uc774\uba70, ‘0’, ‘1’ \uac19\uc774 \uc774\uc804 \uae00\uc5d0\uc11c \uc5b8\uae09\ud55c \ub0b4\uc6a9\uacfc \uac19\uc74c.<\/li>\n
      3. centers : <\/bold>\ud074\ub7ec\uc2a4\ud130\uc758 \uc911\uc2ec\uc774 \uc800\uc7a5\ub41c \ubc30\uc5f4<\/li>\n<\/ol>\n

        \uc774\uc81c 3\uac00\uc9c0 \uc608\ub97c \ud1b5\ud574 K-Means \uc54c\uace0\ub9ac\uc998\uc774 \uc5b4\ub5bb\uac8c OpenCV\uc5d0\uc11c \uc0ac\uc6a9\ub418\ub294\uc9c0 \uc0b4\ud3b4\ubd05\uc2dc\ub2e4.<\/p>\n

        1. \ud558\ub098\uc758 \ud2b9\uc9d5(Feature)\uc744 \uac00\uc9c0\ub294 \ub370\uc774\ud130<\/h4>\n

        \uc624\uc9c1 \ud558\ub098\uc758 \ud2b9\uc9d5\uc744 \uac00\uc9c0\ub294 \ub370\uc774\ud130, \uc608\ub97c \ub4e4\uc5b4 1\ucc28\uc6d0 \ub370\uc774\ud130 \uc14b\uc744 \ubd05\uc2dc\ub2e4. \uadf8\ub7ec\ub2c8\uae4c T\uc154\uce20\uc758 \ud06c\uae30\ub97c \uacb0\uc815\ud558\uae30 \uc704\ud574 \uc0ac\ub78c\uc758 \ud0a4\uc5d0 \ub300\ud55c \ud2b9\uc9d5\ub9cc\uc744 \uace0\ub824\ud558\ub294 \uac83\uc785\ub2c8\ub2e4.<\/p>\n

        \ub370\uc774\ud130\ub97c \uc0dd\uc131\ud558\uace0 Matplotlib\uc73c\ub85c \ud45c\uc2dc\ud574 \ubcf4\uba74..<\/p>\n

        \r\nimport numpy as np\r\nimport cv2\r\nfrom matplotlib import pyplot as plt\r\n\r\nx = np.random.randint(25,100,25) \r\ny = np.random.randint(175,255,25)\r\nz = np.hstack((x,y))\r\nz = z.reshape((50,1))\r\nz = np.float32(z)\r\nplt.hist(z,256,[0,256]),plt.show()\r\n<\/pre>\n
        \ud06c\uae30 50\uac1c\uc758 \ubc30\uc5f4 z\uac00 \uc788\uc73c\uba70, \uad6c\uc131 \uc694\uc18c\uc758 \uac12\uc740 0~255 \uc0ac\uc774\uc785\ub2c8\ub2e4. z\ub97c \ub2e8\uc77c \uc5f4(column)\ub85c \uad6c\uc131\ud569\ub2c8\ub2e4. \ub9c8\uc9c0\ub9c9\uc73c\ub85c \ub370\uc774\ud130\uc758 \ud0c0\uc785\uc744 np.float32\ub85c \ubcc0\ud658\ud569\ub2c8\ub2e4. \uacb0\uacfc\ub294 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4.<\/p>\n
        \"\"<\/p>\n
        \uc774\uc81c, K-Means \ud568\uc218\ub97c \uc801\uc6a9\ud574 \ubd05\uc2dc\ub2e4. \uc54c\uace0\ub9ac\uc998 \uc885\ub8cc\uc5d0 \ub300\ud55c \uae30\uc900 \uc870\uac74\uc744 \uc815\ud574\uc57c \ud569\ub2c8\ub2e4. \uc5ec\uae30\uc11c \uae30\uc900\uc740 10\ubc18 \ubc18\ubcf5\uacfc \uc815\ud655\ub3c4(epsilon)\uc740 1.0\uc73c\ub85c \uc815\ud569\ub2c8\ub2e4.<\/p>\n
        \r\n# Define criteria = ( type, max_iter = 10 , epsilon = 1.0 )\r\ncriteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10, 1.0)\r\n\r\n# Set flags (Just to avoid line break in the code)\r\nflags = cv2.KMEANS_RANDOM_CENTERS\r\n\r\n# Apply KMeans\r\ncompactness,labels,centers = cv2.kmeans(z,2,None,criteria,10,flags)\r\n<\/pre>\n
        \uc704 \uc608\uc81c\uc758 cv2.kmeans \ud568\uc218\ub294 compactness\uc640 labels, centers \ubcc0\uc218\uc5d0 \ubc18\ud658\uac12\uc744 \ub118\uaca8\uc90d\ub2c8\ub2e4. \uc774 \uacbd\uc6b0 centers\ub294 57.92\uacfc 114.5\uc774\uba70, labels\uc5d0\ub294 \uac01 \uc694\uc18c\uc5d0 \ub300\ud574 ‘0’, ‘1’ \uc911\uc5d0 \ud558\ub098\uc758 \uac12\uc73c\ub85c \ubd84\ub958\ub41c \ub77c\ubca8\uac12\uc785\ub2c8\ub2e4. \uc5ec\uae30\uc11c \uc774 \ub77c\ubca8\uac12\uc744 \uae30\ubc18\uc73c\ub85c \ub370\uc774\ud130\ub97c A\uc640 B \ubcc0\uc218\ub85c \ub098\ub220\ubd05\uc2dc\ub2e4.<\/p>\n
        \r\nA = z[labels==0]\r\nB = z[labels==1]\r\n<\/pre>\n
        \uadf8\ub9ac\uace0 A\uc640 B\ub97c \uac01\uac01 \ud30c\ub780\uc0c9\uacfc \ube68\uac04\uc0c9\uc73c\ub85c \ud45c\uc2dc\ud558\uace0, \uad70\uc9d1\ud654\ub41c \uc911\uc2ec\uc744 \ub178\ub780\uc0c9\uc73c\ub85c \ud45c\uc2dc\ud574 \ubd05\uc2dc\ub2e4.<\/p>\n
        \r\n# Now plot 'A' in red, 'B' in blue, 'centers' in yellow\r\nplt.hist(A,256,[0,256],color = 'r')\r\nplt.hist(B,256,[0,256],color = 'b')\r\nplt.hist(centers,32,[0,256],color = 'y')\r\nplt.show()\r\n<\/pre>\n
        \uacb0\uacfc\ub294 \uc544\ub798\uc640 \uac19\uc2b5\ub2c8\ub2e4.<\/p>\n
        \"\"<\/p>\n
        2. \uc5ec\ub7ec \uac1c\uc758 \ud2b9\uc9d5(Feature)\uc744 \uac00\uc9c0\ub294 \ub370\uc774\ud130<\/h4>\n
        \uc774\uc804 \uc608\uc5d0\uc11c, T\uc154\uce20\uc5d0 \ub300\ud574 \uc624\uc9c1 \ud0a4\uc5d0 \ub300\ud55c \ud2b9\uc9d5\uc810\ub9cc\uc744 \uace0\ub824\ud588\uc2b5\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 \ud0a4\uc640 \ubab8\ubb34\uac8c\ucc98\ub7fc 2\uac1c\uc758 \ud2b9\uc9d5\uc810\uc744 \uace0\ub824\ud574 \ubd05\uc2dc\ub2e4.<\/p>\n
        \uc774\uc804 \uacbd\uc6b0\uc5d0\uc11c, \uc785\ub825 \ub370\uc774\ud130\ub97c \ub2e8\uc77c \uc5f4(column) \ubca1\ud130\ub85c \uad6c\uc131\ud588\ub2e4\ub294 \uac83\uc744 \uae30\uc5b5\ud574\uc57c \ud569\ub2c8\ub2e4. \uac01 \ud2b9\uc9d5\uc740 \uc5f4\ub85c \uc815\ub82c\ub418\uc5b4 \uc787\uc5b4\uc57c \ud569\ub2c8\ub2e4. \uc608\ub97c \ub4e4\uc5b4\uc11c, \uc774 \uacbd\uc6b0 50\uba85\uc758 \uc0ac\ub78c\uc5d0 \ub300\ud574 \ud0a4\uc640 \ubab8\ubb34\uac8c \uac12\uc73c\ub85c \uad6c\uc131\ub41c 50×2 \ud06c\uae30\uc758 \ud14c\uc2a4\ud2b8 \ub370\uc774\ud130\ub97c \uad6c\uc131\ud569\ub2c8\ub2e4. \uccab\ubc88\uc9f8 \uc5f4(Column)\uc740 50\uba85\uc5d0 \ub300\ud55c \ud0a4 \uac12\uc774\uace0 \ub450\ubc88\uc9f8 \uc5f4\uc740 \uc774\ub4e4\uc758 \ud0a4\uac12\uc785\ub2c8\ub2e4. \uccab\ubc88\uc9f8 \ud589(Row)\ub294 \uccab\ubc88\uc9f8 \uc0ac\ub78c\uc758 \ud0a4\uc640 \ubab8\ubb34\uac8c \uac12\uc785\ub2c8\ub2e4. \uc989, \uc544\ub798 \uadf8\ub9bc\uacfc \uac19\uc740 \uad6c\uc131\uc785\ub2c8\ub2e4.<\/p>\n
        \"\"<\/p>\n
        \ubc14\ub85c \ucf54\ub4dc\ub97c \ubcf4\uba74..<\/p>\n
        \r\nimport numpy as np\r\nimport cv2\r\nfrom matplotlib import pyplot as plt\r\n\r\nX = np.random.randint(25,50,(25,2))\r\nY = np.random.randint(60,85,(25,2))\r\nZ = np.vstack((X,Y))\r\n\r\n# convert to np.float32\r\nZ = np.float32(Z)\r\n\r\n# define criteria and apply kmeans()\r\ncriteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10, 1.0)\r\nret,label,center=cv2.kmeans(Z,2,None,criteria,10,cv2.KMEANS_RANDOM_CENTERS)\r\n\r\n# Now separate the data, Note the flatten()\r\nA = Z[label.ravel()==0]\r\nB = Z[label.ravel()==1]\r\n\r\n# Plot the data\r\nplt.scatter(A[:,0],A[:,1])\r\nplt.scatter(B[:,0],B[:,1],c = 'r')\r\nplt.scatter(center[:,0],center[:,1],s = 80,c = 'y', marker = 's')\r\nplt.xlabel('Height'),plt.ylabel('Weight')\r\nplt.show()\r\n<\/pre>\n
        \uacb0\uacfc\ub294 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4.<\/p>\n
        \"\"<\/p>\n
        3. \uc0c9\uc0c1 \uc591\uc790\ud654(Color Quantization)<\/h4>\n
        \uc0c9\uc0c1 \uc591\uc790\ud654\ub294 \uc774\ubbf8\uc9c0\uc5d0\uc11c \uc0ac\uc6a9\ud558\ub294 \uc0c9\uc0c1\uc758 \uc218\ub97c \uc904\uc774\ub294 \ucc98\ub9ac\uc785\ub2c8\ub2e4. \uc774\ub7ec\ud55c \ucc98\ub9ac\ub97c \ud558\ub294 \ubaa9\uc801 \uc911 \ud558\ub098\ub294 \uc0ac\uc6a9\ud558\ub294 \uba54\ubaa8\ub9ac\ub97c \uc904\uc774\uae30 \uc704\ud574\uc11c\uc785\ub2c8\ub2e4. \uc0c9\uc0c1 \uc591\uc790\ud654\ub97c \uc704\ud574 K-Means \ud074\ub7ec\uc2a4\ud130\ub9c1\uc744 \ud65c\uc6a9\ud574 \ubcf4\uaca0\uc2b5\ub2c8\ub2e4.<\/p>\n
        \uc0c8\ub86d\uac8c \ucd94\uac00\ub418\ub294 \uc0c8\ub85c\uc6b4 \ub0b4\uc6a9\uc740 \uc5c6\uc2b5\ub2c8\ub2e4. \ud2b9\uc9d5\uc810\uc740 3\uac1c\uc778\ub370, \ubc14\ub85c R, G, B\uc785\ub2c8\ub2e4. \uc774\ubbf8\uc9c0\uc758 \ud654\uc18c \ub370\uc774\ud130\ub97c Mx3 \ubc30\uc5f4\ub85c \ub9cc\ub2e4\ub294\ub370, M\uc740 \uc774\ubbf8\uc9c0\uc758 \ud654\uc18c \uac1c\uc218\uc785\ub2c8\ub2e4. \ud074\ub7ec\uc2a4\ud130\ub9c1 \uc774\ud6c4\uc5d0, \uc911\uc2ec\uc810(\uc774 \uac12 \uc5ed\uc2dc\ub3c4 R, G, B \uc784)\uac12\uc73c\ub85c \ud574\ub2f9 \uc18c\uc18d\ub418\ub294 \ud654\uc18c\uc758 \uac12\uc744 \ubcc0\uacbd\ud569\ub2c8\ub2e4. \uadf8\ub9ac\uace0 \ub2e4\uc2dc Mx3 \ubc30\uc5f4\uc744 \uc6d0\ub798 \uc774\ubbf8\uc9c0\uc758 \ud06c\uae30\ub85c \uc7ac\uad6c\uc131\ud558\uba74 \ub429\ub2c8\ub2e4. \ucf54\ub4dc\ub294 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4.<\/p>\n
        \r\nimport numpy as np\r\nimport cv2\r\n\r\nimg = cv2.imread('.\/data\/harleyQuinnA.jpg')\r\nZ = img.reshape((-1,3))\r\n\r\n# convert to np.float32\r\nZ = np.float32(Z)\r\n\r\n# define criteria, number of clusters(K) and apply kmeans()\r\ncriteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10, 1.0)\r\nK = 7\r\nret,label,center=cv2.kmeans(Z,K,None,criteria,10,cv2.KMEANS_RANDOM_CENTERS)\r\n\r\n# Now convert back into uint8, and make original image\r\ncenter = np.uint8(center)\r\nres = center[label.flatten()]\r\nres2 = res.reshape((img.shape))\r\n\r\ncv2.imshow('res2',res2)\r\ncv2.waitKey(0)\r\ncv2.destroyAllWindows()\r\n<\/pre>\n
        \uc774\ubbf8\uc9c0\ub97c 7\uac1c\uc758 \uc0c9\uc0c1\ub9cc\uc73c\ub85c \uad6c\uc131\ub418\ub3c4\ub85d \uc591\uc790\ud654\ud558\ub294 \uac83\uc73c\ub85c \uacb0\uacfc\ub294 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4.<\/p>\n
        \"\"<\/p>\n","protected":false},"excerpt":{"rendered":"
        \uc774 \uae00\uc758 \uc6d0\ubb38\uc740 https:\/\/opencv-python-tutroals.readthedocs.io\/en\/latest\/py_tutorials\/py_ml\/py_kmeans\/py_kmeans_opencv\/py_kmeans_opencv.html \uc785\ub2c8\ub2e4. OpenCV\uc5d0\uc11c K-Means \uc54c\uace0\ub9ac\uc998\uc744 \uc774\uc6a9\ud55c \ub370\uc774\ud130 \uad70\uc9d1\ud654\ub294 cv2.kmeans() \ud568\uc218\ub97c \ud1b5\ud574 \uc774\uc6a9 \ub429\ub2c8\ub2e4. \uc774 \ud568\uc218\uc5d0 \ub300\ud55c \uc778\uc790\ub294 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4. samples : np.float32 \ub370\uc774\ud0c0 \ud0c0\uc785\uc774\uba70, \uac01 \ud53c\uccd0(Feature)\ub294 \ub2e8\uc77c \uc5f4(Column)\uc73c\ub85c \uc800\uc7a5\ub418\uc5b4\uc838 \uc788\uc5b4\uc57c \ud569\ub2c8\ub2e4. nclusters(K) : \uad70\uc9d1\ud654\ud560 \uac1c\uc218 criteria : \ubc18\ubcf5\uc744 \uc885\ub8cc\ud560 \uc870\uac74\uc785\ub2c8\ub2e4. \uc870\uac74\uc774 \ub9cc\uc871\ub418\uba74 \uc54c\uace0\ub9ac\uc998\uc758 \ubc18\ubcf5\uc740 \uc911\uc9c0\ub429\ub2c8\ub2e4. 3\uac1c\uc758 \uc778\uc790\ub97c \uac16\ub294 \ud29c\ud50c(Tuple)\uc774\uba70, (type, max_iter, epsilon)\uc785\ub2c8\ub2e4. … <\/p>\n
        \ub354 \ubcf4\uae30 “Python\uacfc OpenCV \u2013 52 : OpenCV\uc5d0\uc11c K-Means \uad70\uc9d1\ud654(Clustering)”<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[130,131],"tags":[],"class_list":["post-7123","post","type-post","status-publish","format-standard","hentry","category-opencv","category-python"],"_links":{"self":[{"href":"http:\/\/www.gisdeveloper.co.kr\/index.php?rest_route=\/wp\/v2\/posts\/7123","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.gisdeveloper.co.kr\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.gisdeveloper.co.kr\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.gisdeveloper.co.kr\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.gisdeveloper.co.kr\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=7123"}],"version-history":[{"count":13,"href":"http:\/\/www.gisdeveloper.co.kr\/index.php?rest_route=\/wp\/v2\/posts\/7123\/revisions"}],"predecessor-version":[{"id":9404,"href":"http:\/\/www.gisdeveloper.co.kr\/index.php?rest_route=\/wp\/v2\/posts\/7123\/revisions\/9404"}],"wp:attachment":[{"href":"http:\/\/www.gisdeveloper.co.kr\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7123"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.gisdeveloper.co.kr\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7123"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.gisdeveloper.co.kr\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7123"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}