删除验证码文本中不需要的行 - opencv - python

Question

我试图使用opencv从captcha图像中获取文本。问题是文本被噪声掩盖，用这些水平线/噪声处理是很复杂的。

原始图像

我处理的图片：

不知道如何删除这些水平线并获取文本

代码：

import numpy as np
import cv2

# Load an color image in grayscale
img = cv2.imread('captcha.jpg',0)

#display image in window
#cv2.imshow('image',img) #@param - windowname, image to be displayed

horizontal_inv = cv2.bitwise_not(img)
#perform bitwise_and to mask the lines with provided mask
masked_img = cv2.bitwise_and(img, img, mask=horizontal_inv)
#reverse the image back to normal
masked_img_inv = cv2.bitwise_not(masked_img)
cv2.imshow("masked img", masked_img_inv)
cv2.imwrite("result2.jpg", masked_img_inv)

cv2.waitKey(0) # time for window to show image in milliseconds - 0 is infinite wait
cv2.destroyAllWindows()

编辑：如果文本为浅色，如何处理

Answer 1

import numpy as np
import cv2

# Load an color image in grayscale
img = cv2.imread('captcha.jpg',0)

#display image in window
#cv2.imshow('image',img) #@param - windowname, image to be displayed

horizontal_inv = cv2.bitwise_not(img)
#perform bitwise_and to mask the lines with provided mask
masked_img = cv2.bitwise_and(img, img, mask=horizontal_inv)
#reverse the image back to normal
masked_img_inv = cv2.bitwise_not(masked_img)

kernel = np.ones((5,5),np.uint8)
dilation = cv2.dilate(masked_img_inv,kernel,iterations = 3) # to remove blackline noise
cv2.imwrite("result1.jpg", dilation)

ret,thresh2 = cv2.threshold(dilation,254,255,cv2.THRESH_BINARY_INV) 
thresh2=cv2.bitwise_not(thresh2)
# cv2.imshow("masked img", masked_img_inv)
cv2.imwrite("result2.jpg", thresh2)

cv2.waitKey(0) # time for window to show image in milliseconds - 0 is infinite wait
cv2.destroyAllWindows()

如果您将来有疑问，请告诉我。