I am getting the error TesseractError: (2, 'Usage: pytesseract [-l lang] input_file'). Using ! sudo apt install but still getting the error in colab. Its a JPG I am trying to read.
-----------------------------code -------------------------------------
! apt install tesseract-ocr
! apt install libtesseract-dev
! sudo apt install tesseract-ocr
! pip install Pillow
! pip install pytesseract
import pytesseract
import shutil
import os
import cv2
import random
from google.colab import files
from io import BytesIO
from PIL import Image,ImageFilter
!pip install pdf2image
!apt-get install -y poppler-utils
from pdf2image import convert_from_path
#from google.colab import drive
!sudo apt install tesseract-ocr
!pip install pytesseract
!pip install tesseract
pytesseract.pytesseract.tesseract_cmd = r'/usr/local/bin/pytesseract'
image_path_in_colab = 'Pillow block drawing.jpg'
img = cv2.imread('Pillow block drawing.jpg')
custom_config = r'-l eng --psm 6'
pytesseract.image_to_string(img, config=custom_config)
extractedInformation = pytesseract.image_to_string(Image.open(image_path_in_colab))
print(extractedInformation)
pytesseract.image_to_string(img, config=custom_config)to pytesseract.image_to_string(img, lang='eng', config='--psm 6')