Output 从 tesseract ocr 中提取的文本

Question

I am using google tesseract to extract text from images. I have a folder where I have some images and I wanted to store the extracted text in form of a text file. The results are okay but there is some red boxes shown in the output.txt file.

Here is my code for text extraction from a folder

import cv2
import pytesseract as pt
import os

custom_config = "--oem 3 --psm 6"

path ="/home/rakshit/Documents/textextraction/croped/82092117"

textBox = []
for filename in os.listdir(path):
    head = os.path.split(filename)
    file_name = head[1].split('_',1)[0]

    imagePath = os.path.join(path, filename)
    img = cv2.imread(imagePath)
    text = pt.image_to_string(image, config = custom_config)
    textBox.append(text)

finalPath = f"/home/rakshit/Documents/textextraction/outputText/detected/{file_name}.txt"

with open(finalPath, 'w') as f:
    for t in textBox:
        f.write(t)
        f.write("\n")

The output text is something like this: Output text file image

Can someone tell me what are these boxes have appeared in the output text file? Thanks in advance for any time you have devoted to this problem.

Answer 1

Sharing a screen image of text file is not a good manner. But I guess it is the page break .