Read text in image using pytesseract

from PIL import Image
import pytesseract

im = Image.open("sample1.jpg")

text = pytesseract.image_to_string(im, lang = 'eng')

print(text)

import pytesseract
import cv2

pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files (x86)\\Tesseract-OCR\\tesseract.exe'

image = cv2.imread("ocr.png")
image_grayscal = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

data = pytesseract.image_to_string(image_grayscal)

Read texts in white color

import pytesseract
import cv2

pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files (x86)\\Tesseract-OCR\\tesseract.exe'

image = cv2.imread("ocr.png")
image_grayscal = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
inverted_image = cv2.bitwise_not(image_grayscal) # color of text is white so we should invert colors

data = pytesseract.image_to_string(inverted_image)

References
https://stackoverflow.com/questions/50951955/pytesseract-tesseractnotfound-error-tesseract-is-not-installed-or-its-not-i
https://pupli.net/2020/05/inverting-colors-of-image-in-python-with-opencv/

Related