如何在python中使用tesseract仅从图像中获取数字？

Question

这是原图

def extract_number(video_name):
  global read
  img = cv2.imread(video_name)
  HSV_image = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
  h, s, v = cv2.split(HSV_image)
  s = cv2.GaussianBlur(s, (1, 1), 0)
  thresh = cv2.threshold(
      s, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
  cv2.imwrite('{}.png'.format(video_name), thresh)
  kernel = cv2.getStructuringElement(cv2.MORPH_RECT, ksize=(1, 2))
  thresh = cv2.dilate(thresh, kernel)
  txt = image_to_string(thresh, config='--oem 1 --psm 13')
  return txt

这是我用上面的代码实现的最好的

Answer 1

我会让它比那简单得多：

def extract_number(your_image):
  # open the image
  img = cv2.imread(your_image)

  # turn it to a binary image, no need to save it.
  [ret, binary_image] = cv2.threshold(img, 200, 255, cv2.THRESH_BINARY) 

  # turn it into text (you are probably going to have issues depending on the image)
  txt = image_to_string(binary_image, config='--oem 1 --psm 13')
  return txt

将其转换为二值图像的结果：