{"id":1959,"date":"2022-01-13T17:00:31","date_gmt":"2022-01-13T09:00:31","guid":{"rendered":"http:\/\/139.9.1.231\/?p=1959"},"modified":"2022-01-13T17:20:09","modified_gmt":"2022-01-13T09:20:09","slug":"n111","status":"publish","type":"post","link":"http:\/\/139.9.1.231\/index.php\/2022\/01\/13\/n111\/","title":{"rendered":"\u56fe\u50cf\u53bb\u566a"},"content":{"rendered":"\n

\u901a\u5e38\u8ba4\u4e3a\u566a\u58f0\u662f\u96f6\u5747\u503c\u7684\u968f\u673a\u53d8\u91cf\u3002\u8003\u8651\u4e00\u4e2a\u6709\u566a\u58f0\u7684\u50cf\u7d20\uff0cp=p0+n\uff0c\u5176\u4e2dp0\u662f\u50cf\u7d20\u7684\u771f\u5b9e\u503c\uff0cn\u662f\u8be5\u50cf\u7d20\u4e2d\u7684\u566a\u58f0\u3002\u4f60\u53ef\u4ee5\u4ece\u4e0d\u540c\u7684\u56fe\u50cf\u4e2d\u83b7\u53d6\u5927\u91cf\u76f8\u540c\u7684\u50cf\u7d20\uff08\u4f8b\u5982N\uff09\u5e76\u8ba1\u7b97\u5176\u5e73\u5747\u503c\u3002\u7406\u60f3\u60c5\u51b5\u4e0b\uff0c\u7531\u4e8e\u566a\u58f0\u7684\u5e73\u5747\u503c\u4e3a\u96f6\uff0c\u56e0\u6b64\u5e94\u8be5\u5f97\u5230p=p0\u3002<\/p>\n\n\n\n

\u4f60\u53ef\u4ee5\u901a\u8fc7\u7b80\u5355\u7684\u8bbe\u7f6e\u81ea\u5df1\u8fdb\u884c\u9a8c\u8bc1\u3002\u5c06\u9759\u6001\u76f8\u673a\u56fa\u5b9a\u5728\u67d0\u4e2a\u4f4d\u7f6e\u51e0\u79d2\u949f\u3002\u8fd9\u5c06\u4e3a\u4f60\u63d0\u4f9b\u5f88\u591a\u5e27\u6216\u540c\u4e00\u573a\u666f\u7684\u5f88\u591a\u56fe\u50cf\u3002\u7136\u540e\u7f16\u5199\u4e00\u6bb5\u4ee3\u7801\uff0c\u627e\u5230\u89c6\u9891\u4e2d\u6240\u6709\u5e27\u7684\u5e73\u5747\u503c\uff08\u8fd9\u5bf9\u4f60\u73b0\u5728\u5e94\u8be5\u592a\u7b80\u5355\u4e86\uff09\u3002 \u6bd4\u8f83\u6700\u7ec8\u7ed3\u679c\u548c\u7b2c\u4e00\u5e27\u3002\u4f60\u4f1a\u770b\u5230\u566a\u58f0\u51cf\u5c11\u3002\u4e0d\u5e78\u7684\u662f\uff0c\u8fd9\u79cd\u7b80\u5355\u7684\u65b9\u6cd5\u5bf9\u6444\u50cf\u673a\u548c\u573a\u666f\u7684\u8fd0\u52a8\u5e76\u4e0d\u7a33\u5065\u3002\u901a\u5e38\uff0c\u53ea\u6709\u4e00\u5f20\u5608\u6742\u7684\u56fe\u50cf\u53ef\u7528\u3002<\/p>\n\n\n\n

\u56e0\u6b64\u60f3\u6cd5\u5f88\u7b80\u5355\uff0c\u6211\u4eec\u9700\u8981\u4e00\u7ec4\u76f8\u4f3c\u7684\u56fe\u50cf\u6765\u5e73\u5747\u566a\u58f0\u3002\u8003\u8651\u56fe\u50cf\u4e2d\u7684\u4e00\u4e2a\u5c0f\u7a97\u53e3\uff08\u4f8b\u59825×5\u7a97\u53e3\uff09\u3002 \u5f88\u6709\u53ef\u80fd\u540c\u4e00\u4fee\u8865\u7a0b\u5e8f\u53ef\u80fd\u4f4d\u4e8e\u56fe\u50cf\u4e2d\u7684\u5176\u4ed6\u4f4d\u7f6e\u3002\u6709\u65f6\u5728\u5b83\u5468\u56f4\u7684\u4e00\u4e2a\u5c0f\u793e\u533a\u4e2d\u3002\u4e00\u8d77\u4f7f\u7528\u8fd9\u4e9b\u76f8\u4f3c\u7684\u8865\u4e01\u5e76\u627e\u5230\u5b83\u4eec\u7684\u5e73\u5747\u503c\u600e\u4e48\u529e\uff1f\u5bf9\u4e8e\u90a3\u4e2a\u7279\u5b9a\u7684\u7a97\u53e3\uff0c\u8fd9\u5f88\u597d\u3002\u8bf7\u53c2\u9605\u4e0b\u9762\u7684\u793a\u4f8b\u56fe\u7247\uff1a<\/p>\n\n\n\n

\"\"\/<\/figure>\n\n\n\n

\u56fe\u50cf\u4e2d\u7684\u84dd\u8272\u8865\u4e01\u770b\u8d77\u6765\u5f88\u76f8\u4f3c\u3002\u7eff\u8272\u8865\u4e01\u770b\u8d77\u6765\u5f88\u76f8\u4f3c\u3002\u56e0\u6b64\uff0c\u6211\u4eec\u83b7\u53d6\u4e00\u4e2a\u50cf\u7d20\uff0c\u5728\u5176\u5468\u56f4\u83b7\u53d6\u4e00\u4e2a\u5c0f\u7a97\u53e3\uff0c\u5728\u56fe\u50cf\u4e2d\u641c\u7d22\u76f8\u4f3c\u7684\u7a97\u53e3\uff0c\u5bf9\u6240\u6709\u7a97\u53e3\u6c42\u5e73\u5747\uff0c\u7136\u540e\u7528\u5f97\u5230\u7684\u7ed3\u679c\u66ff\u6362\u8be5\u50cf\u7d20\u3002\u6b64\u65b9\u6cd5\u662f\u201c\u975e\u672c\u5730\u5747\u503c\u6d88\u566a\u201d\u3002\u4e0e\u6211\u4eec\u4e4b\u524d\u770b\u5230\u7684\u6a21\u7cca\u6280\u672f\u76f8\u6bd4\uff0c\u5b83\u82b1\u8d39\u4e86\u66f4\u591a\u65f6\u95f4\uff0c\u4f46\u662f\u6548\u679c\u975e\u5e38\u597d\u3002\u66f4\u591a\u4fe1\u606f\u548c\u5728\u7ebf\u6f14\u793a\u53ef\u5728\u5176\u4ed6\u8d44\u6e90\u7684\u7b2c\u4e00\u4e2a\u94fe\u63a5\u4e2d\u627e\u5230\u3002<\/p>\n\n\n\n

\u5bf9\u4e8e\u5f69\u8272\u56fe\u50cf\uff0c\u56fe\u50cf\u5c06\u8f6c\u6362\u4e3aCIELAB\u8272\u5f69\u7a7a\u95f4\uff0c\u7136\u540e\u5206\u522b\u5bf9L\u548cAB\u5206\u91cf\u8fdb\u884c\u964d\u566a\u3002<\/p>\n\n\n\n

OpenCV\u4e2d\u7684\u56fe\u50cf\u53bb\u566a<\/a><\/h3>\n\n\n\n

OpenCV\u63d0\u4f9b\u4e86\u6b64\u65b9\u6cd5\u7684\u56db\u4e2a\u53d8\u4f53\u3002<\/p>\n\n\n\n

  1. cv.fastNlMeansDenoising<\/strong>()-\u5904\u7406\u5355\u4e2a\u7070\u5ea6\u56fe\u50cf<\/li>
  2. cv.fastNlMeansDenoisingColored<\/strong>()-\u5904\u7406\u5f69\u8272\u56fe\u50cf\u3002<\/li>
  3. cv.fastNlMeansDenoisingMulti<\/strong>()-\u5904\u7406\u5728\u77ed\u65f6\u95f4\u5185\u6355\u83b7\u7684\u56fe\u50cf\u5e8f\u5217\uff08\u7070\u5ea6\u56fe\u50cf\uff09<\/li>
  4. cv.fastNlMeansDenoisingColoredMulti<\/strong>()-\u4e0e\u4e0a\u9762\u76f8\u540c\uff0c\u4f46\u7528\u4e8e\u5f69\u8272\u56fe\u50cf\u3002<\/li><\/ol>\n\n\n\n

    \u5e38\u7528\u53c2\u6570\u4e3a\uff1a – h\uff1a\u51b3\u5b9a\u6ee4\u6ce2\u5668\u5f3a\u5ea6\u7684\u53c2\u6570\u3002\u8f83\u9ad8\u7684h\u503c\u53ef\u4ee5\u66f4\u597d\u5730\u6d88\u9664\u566a\u70b9\uff0c\u4f46\u540c\u65f6\u4e5f\u53ef\u4ee5\u6d88\u9664\u56fe\u50cf\u7ec6\u8282\u3002\uff08\u53ef\u4ee5\u8bbe\u4e3a10\uff09 – hForColorComponents\uff1a\u4e0eh\u76f8\u540c\uff0c\u4f46\u4ec5\u7528\u4e8e\u5f69\u8272\u56fe\u50cf\u3002\uff08\u901a\u5e38\u4e0eh\u76f8\u540c\uff09 – templateWindowSize\uff1a\u5e94\u4e3a\u5947\u6570\u3002\uff08\u5efa\u8bae\u8bbe\u4e3a7\uff09 – searchWindowSize\uff1a\u5e94\u4e3a\u5947\u6570\u3002\uff08\u5efa\u8bae\u8bbe\u4e3a21\uff09<\/p>\n\n\n\n

    import numpy as np\nimport cv2 as cv\nfrom matplotlib import pyplot as plt\nimg = cv.imread('die.png')\ndst = cv.fastNlMeansDenoisingColored(img,None,10,10,7,21)\nplt.subplot(121),plt.imshow(img)\nplt.subplot(122),plt.imshow(dst)\nplt.show()<\/code><\/pre>\n\n\n\n
    1. cv.fastNlMeansDenoisingMulti<\/strong>() \u73b0\u5728\uff0c\u6211\u4eec\u5c06\u5bf9\u89c6\u9891\u5e94\u7528\u76f8\u540c\u7684\u65b9\u6cd5\u3002\u7b2c\u4e00\u4e2a\u53c2\u6570\u662f\u566a\u58f0\u5e27\u5217\u8868\u3002\u7b2c\u4e8c\u4e2a\u53c2\u6570imgToDenoiseIndex<\/code>\u6307\u5b9a\u6211\u4eec\u9700\u8981\u53bb\u566a\u7684\u5e27\uff0c\u4e3a\u6b64\uff0c\u6211\u4eec\u5728\u8f93\u5165\u5217\u8868\u4e2d\u4f20\u9012\u5e27\u7684\u7d22\u5f15\u3002\u7b2c\u4e09\u662ftemporalWindowSize<\/code>\uff0c\u5b83\u6307\u5b9a\u8981\u7528\u4e8e\u964d\u566a\u7684\u9644\u8fd1\u5e27\u7684\u6570\u91cf\u3002\u5e94\u8be5\u5f88\u5947\u602a\u3002\u5728\u90a3\u79cd\u60c5\u51b5\u4e0b\uff0c\u603b\u5171\u4f7f\u7528temporalWindowSize<\/code>\u5e27\uff0c\u5176\u4e2d\u4e2d\u5fc3\u5e27\u662f\u8981\u88ab\u53bb\u566a\u7684\u5e27\u3002\u4f8b\u5982\uff0c\u4f60\u4f20\u9012\u4e86\u4e00\u4e2a5\u5e27\u7684\u5217\u8868\u4f5c\u4e3a\u8f93\u5165\u3002\u4ee4imgToDenoiseIndex = 2,temporalWindowSize =3<\/code>\u3002\u7136\u540e\u4f7f\u7528frame-1<\/code>\uff0cframe-2<\/code>\u548cframe-3<\/code>\u53bb\u566aframe-2<\/code>\u3002\u8ba9\u6211\u4eec\u6765\u770b\u4e00\u4e2a\u4f8b\u5b50\u3002<\/li><\/ol>\n\n\n\n
      import numpy as np\nimport cv2 as cv\nfrom matplotlib import pyplot as plt\ncap = cv.VideoCapture('vtest.avi')\n# \u521b\u5efa5\u4e2a\u5e27\u7684\u5217\u8868\nimg = [cap.read()[1] for i in xrange(5)]\n# \u5c06\u6240\u6709\u8f6c\u5316\u4e3a\u7070\u5ea6\ngray = [cv.cvtColor(i, cv.COLOR_BGR2GRAY) for i in img]\n# \u5c06\u6240\u6709\u8f6c\u5316\u4e3afloat64\ngray = [np.float64(i) for i in gray]\n# \u521b\u5efa\u65b9\u5dee\u4e3a25\u7684\u566a\u58f0\nnoise = np.random.randn(*gray[1].shape)*10\n# \u5728\u56fe\u50cf\u4e0a\u6dfb\u52a0\u566a\u58f0\nnoisy = [i+noise for i in gray]\n# \u8f6c\u5316\u4e3aunit8\nnoisy = [np.uint8(np.clip(i,0,255)) for i in noisy]\n# \u5bf9\u7b2c\u4e09\u5e27\u8fdb\u884c\u964d\u566a\ndst = cv.fastNlMeansDenoisingMulti(noisy, 2, 5, None, 4, 7, 35)\nplt.subplot(131),plt.imshow(gray[2],'gray')\nplt.subplot(132),plt.imshow(noisy[2],'gray')\nplt.subplot(133),plt.imshow(dst,'gray')\nplt.show()<\/code><\/pre>\n\n\n\n
      \"\"\/<\/figure>\n\n\n\n
      \u8ba1\u7b97\u9700\u8981\u82b1\u8d39\u5927\u91cf\u65f6\u95f4\u3002\u7ed3\u679c\uff0c\u7b2c\u4e00\u4e2a\u56fe\u50cf\u662f\u539f\u59cb\u5e27\uff0c\u7b2c\u4e8c\u4e2a\u662f\u566a\u58f0\u5e27\uff0c\u7b2c\u4e09\u4e2a\u662f\u53bb\u566a\u56fe\u50cf\u3002<\/p>\n\n\n\n
      \u9644\u52a0\u8d44\u6e90<\/a><\/h3>\n\n\n\n
      1. http:\/\/www.ipol.im\/pub\/art\/2011\/bcm_nlm\/<\/a> (\u5b83\u5305\u542b\u8be6\u7ec6\u4fe1\u606f\uff0c\u5728\u7ebf\u6f14\u793a\u7b49\u3002\u5f3a\u70c8\u5efa\u8bae\u8bbf\u95ee\u3002\u6211\u4eec\u7684\u6d4b\u8bd5\u56fe\u50cf\u662f\u4ece\u6b64\u94fe\u63a5\u751f\u6210\u7684)<\/li>
      2. Online course at coursera (\u8fd9\u91cc\u62cd\u6444\u7684\u7b2c\u4e00\u5f20\u56fe\u7247)<\/li><\/ol>\n","protected":false},"excerpt":{"rendered":"
        \u901a\u5e38\u8ba4\u4e3a\u566a\u58f0\u662f\u96f6\u5747\u503c\u7684\u968f\u673a\u53d8\u91cf\u3002\u8003\u8651\u4e00\u4e2a\u6709\u566a\u58f0\u7684\u50cf\u7d20\uff0cp=p0+n\uff0c\u5176\u4e2dp0\u662f\u50cf\u7d20\u7684\u771f\u5b9e\u503c\uff0cn\u662f\u8be5\u50cf\u7d20\u4e2d\u7684\u566a\u58f0 … \u7ee7\u7eed\u9605\u8bfb\u56fe\u50cf\u53bb\u566a<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[15],"tags":[],"_links":{"self":[{"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/posts\/1959"}],"collection":[{"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/comments?post=1959"}],"version-history":[{"count":4,"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/posts\/1959\/revisions"}],"predecessor-version":[{"id":1963,"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/posts\/1959\/revisions\/1963"}],"wp:attachment":[{"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/media?parent=1959"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/categories?post=1959"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/tags?post=1959"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}