ocr - Extract underlined text from image (OpenCV)

Question

I need to display all underlined texts from this type of image. Or process with OpenCV so that only underlined texts remain on the photo

The volume of text in the photo is dynamic, this is just an example.

I tried this code example from Extract text with strikethrough from image

import cv2
img = cv2.imread('juFpe.png', cv2.IMREAD_GRAYSCALE)
thresh = cv2.threshold(img, 0, 255, cv2.THRESH_BINARY_INV )[1]
kernel = cv2.getStructuringElement(cv2.MORPH_RECT,(1,5))
kernel2=cv2.getStructuringElement(cv2.MORPH_RECT,(8,8))
detect_thin = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
detect_thin = cv2.morphologyEx(detect_thin, cv2.MORPH_DILATE, kernel2)
marker=cv2.compare(detect_thin, thresh,cv2.CMP_LT) # thin lines
while True: #morphological reconstruction
    tmp=marker.copy()
    marker=cv2.dilate(marker, kernel2)
    marker=cv2.min(thresh, marker)
    difference = cv2.subtract(marker, tmp)
    if cv2.countNonZero(difference) == 0:
        break

cv2.imwrite('lines.png', marker)

But it doesn't work in my example. You can adapt this code to my example or write your own

I do not have experience with OpenCV

Answer 1

等待大神答复