遍历文件夹读取JPG文件，并处理 短横线，书横线

import os
import imutils
import cv2
import pytesseract
import re

def get_text(gray): # get page number information from the head, then fill it by 255
image_text = gray[:180, :400]
text_iamge = pytesseract.image_to_string(image_text)
print(text_iamge)
text_head = re.findall(r’[0-9]{1,3}’, text_iamge)
#print(text_head[0])
gray[:180, :400]=255
return text_head[0]

def find_lines(gray,head=1): # find lines issue on horizontal and vertical
# count for lines counts
# edged = cv2.Canny(gray, 30, 150)
thresh = cv2.threshold(gray, 220, 255, cv2.THRESH_BINARY_INV)[1]
count =0
thresh = imutils.resize(thresh, 500)
cv2.imshow(‘thresh’, thresh)
cv2.waitKey(0)
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)

cnts = imutils.grab_contours(cnts)
output = image.copy()
outp