Extracting coordinates of text using tesseract python without using pytesseract

Question

i did not found any pytesseract alternative wrapper not for windows system. I want to extract the text with its coordinates without using pytesseract in pandas dataframe.

Answer 1

tesseract_path is the path where your tesseract is installed in windows system.

img_path is the path of the image from which we want to extract text.

tsv_path is the output path of file in which the extracted info is stored eg ../path/sample_output

import os

tesseract_cmd = '"%s" %s %s -l eng --psm 6 tsv'%(tesseract_path, img_path, tsv_path)

os.system('cmd /c %s'%(tesseract_cmd))

import pandas as pd

df = pd.read_csv('%s.tsv'%(tsv_path), sep='\t', header=0)

references: https://github.com/tesseract-ocr/tesseract/wiki/Command-Line-Usage