how to get character position in pytesseract

Question

I am trying to get character position of image files using pytesseract library .

import pytesseract
from PIL import Image
print pytesseract.image_to_string(I         


        

Answer 1

The position of the character can be found as follows.

import csv
import cv2
from pytesseract import pytesseract as pt

pt.run_tesseract('bw.png', 'output', lang=None, boxes=True, config="hocr")

# To read the coordinates
boxes = []
with open('output.box', 'rb') as f:
    reader = csv.reader(f, delimiter = ' ')
    for row in reader:
        if(len(row)==6):
            boxes.append(row)

# Draw the bounding box
img = cv2.imread('bw.png')
h, w, _ = img.shape
for b in boxes:
    img = cv2.rectangle(img,(int(b[1]),h-int(b[2])),(int(b[3]),h-int(b[4])),(255,0,0),2)

cv2.imshow('output',img)

While using this method, one may miss some texts. It would require some preprocessing (viz. background subtraction) of the image to get better results.

Answer 2

Did you try use pytesseract.image_to_data()?

data = pytesseract.image_to_data(img, output_type=Output.DICT)
boxes = len(data['level'])
for i in range(boxes ):
    (x, y, w, h) = (data['left'][i], data['top'][i], data['width'][i], data['height'][i])
    #Draw box        
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)

Answer 3

Using pytesseract doesn't seem the best idea to have the position but you can do this :

from pytesseract import pytesseract
pytesseract.run_tesseract('image.png', 'output', lang=None, boxes=False, config="hocr")