Converting image identified by PyTesseract to an array

Question

I have an image with a list of numbers which I have scanned using PyTesseract to construct a string. Concretely, here is the code:

from PIL import Image
import pytesseract
from scipy import stats
import numpy as np

pytesseract.pytesseract.tesseract_cmd = r'C:\\\Program Files\\\Tesseract-OCR\\\tesseract.exe'

str1=pytesseract.image_to_string(Image.open('D:/Image.png'))

Here's the image I am scanning:

The problem is that PyTesseract is scanning the image as individual characters instead of integers.

I would like to understand why this is happening and what can I do to get the desired result.

In short, PyTesseract is not scanning integers in a list of numbers, instead scanning them as individual characters. How do I tell it to scan for integers and put them in an array?

Did you mean that it will return you a string instead of a list of number? — jizhihaoSAMA, Mar 31 '20 at 08:31
What?So you want to convert it to `list`?`I need a string of numbers. `Could you edit your post and add your expectation output to your post? — jizhihaoSAMA, Mar 31 '20 at 08:36
A list of numbers would be fine. Okay, let me edit as to what I want. — Yuzuriha Inori, Mar 31 '20 at 08:37

score 2 · Accepted Answer · answered Mar 31 '20 at 08:53

Well,If you only want to get a list,Use re.split and strip can solve it.(Because tesseract's result has some errors).

You can try this:

import pytesseract
import re

data = pytesseract.image_to_string('OCR.png')
dataList = re.split(r',|\.| ',data) # split the string
resultList = [int(i.strip()) for i in dataList if i != ''] # remove the '' str and convert str to int.
print(resultList)

# result: [71, 194, 38, 1701, 89, 76, 11, 83, 1629, 48, 94, 63, 132, 16, 111, 95, 84, 341, 975, 14, 40, 64, .......

Beautiful, that worked perfectly ! That split command escaped me... — Yuzuriha Inori, Mar 31 '20 at 13:11

Converting image identified by PyTesseract to an array

1 Answers1