python - 在python中使用opencv从图像中去除高密度噪声

Question

我正在尝试检测数字仪表的数字。我现在面临的问题是图像有很多噪音，即使在添加了许多过滤器之后，我也无法在不扭曲数字的情况下消除噪音。这是我到目前为止所取得的成就:

img = cv2.imread(image_path)
img = cv2.resize(img  , (280 , 70))

gamma = 2.5

# apply gamma correction and show the images
gamma = gamma if gamma > 0 else 0.1
img = adjust_gamma(img, gamma=gamma)

img = applyClahe(img)
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img = cv2.GaussianBlur(img, (3, 3), 0)
dst = cv2.fastNlMeansDenoising(img,None,3,10,21)
thresh = cv2.adaptiveThreshold(dst,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,\
            cv2.THRESH_BINARY,11,2)
kernel = np.ones((1,2), np.uint8)
thresh = cv2.erode(thresh, kernel, iterations=1)
thresh = cv2.fastNlMeansDenoising(thresh,None,30,15,30)
connectivity = 4 
thresh = cv2.medianBlur(thresh, 3)

是否有更积极的算法可以过滤掉这些噪音？

Answer 1

尝试使用 niBlackThreshold。我在跑this example结果:

还不错吧？