使用python从“票证”中提取文本

Question

我使用了许多python库从这些票证中提取文本，但它们没有给我正确的结果。

我什至在这些图像上应用了过滤器和预处理，但是我无法从其中提取所有文本，尤其是要提取的元素是日期和时间以及TTC量和中间的序列号像31950 A 34一样。

您在这里找到该代码的图像和执行结果

# USAGE
# python ocr.py --image example.png  --preprocess blur

# import the necessary packages
from PIL import Image
import pytesseract
import argparse
import cv2
import os

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
    help="path to input image to be OCR'd")
ap.add_argument("-p", "--preprocess", type=str, default="thresh",
    help="type of preprocessing to be done")
args = vars(ap.parse_args())

# load the example image and convert it to grayscale
image = cv2.imread(args["image"])
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

# cv2.imshow("Image", gray)

# check to see if we should apply thresholding to preprocess the
# image
if args["preprocess"] == "thresh":
    gray = cv2.threshold(gray, 0, 255,
        cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]

# make a check to see if median blurring should be done to remove
# noise
elif args["preprocess"] == "blur":
    gray = cv2.medianBlur(gray, 3)

# write the grayscale image to disk as a temporary file so we can
# apply OCR to it
filename = "{}.png".format(os.getpid())
cv2.imwrite(filename, gray)

# load the image as a PIL/Pillow image, apply OCR, and then delete
# the temporary file
text = pytesseract.image_to_string(Image.open(filename))
os.remove(filename)
print(text)

# show the output images
# cv2.imshow("Image", image)
# cv2.imshow("Output", gray)
cv2.waitKey(0)