How to read digits from an image with PyTesseract OCR?

Question

I'm trying to get PyTesseract OCR to read digits from this simple and well cropped Image, but for some reason it's just not able to do this.

from PIL import Image
import pytesseract as p

def obtain_balance(a):
    im = Image.open(a)
    width,height = im.size
    a = 300*5 - 120
    # print(width,height)
    left = 155+a
    top = 5
    right = 360+a 
    bottom = 120
    m1 = im.crop((left, top, right, bottom)) 
    text = p.image_to_string(m1,lang='eng',config='--psm 13 --oem 3 -c tessedit_char_whitelist=0123456789').split()
    print(text)
    m1.show()
    return text

obtain_balance('cur.jpg')

Output :

[]

Answer 1

When performing OCR, it is important to prepossess the image so that the desired foreground text is in black with the background in white . To do this, we can use OpenCV to Otsu's threshold the image and obtain a binary image. We then apply a slight Gaussian blur to smooth the image before throwing it into Pytesseract. We use --psm 6 config to treat the image as a single uniform block of text. See here for more configuration options.

---

Here's the preprocessed image and the result from Pytesseract

PRACTICE ACCOUNT
$9,047.26~ i

Code

import cv2
import pytesseract

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

image = cv2.imread('1.png', 0)
thresh = cv2.threshold(image, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
thresh = cv2.GaussianBlur(thresh, (3,3), 0)
data = pytesseract.image_to_string(thresh, lang='eng',config='--psm 6')
print(data)

cv2.imshow('thresh', thresh)
cv2.waitKey()