ocr_utils.py

import cv2
import pytesseract
import os
from PIL import Image

def preprocess_image_for_ocr(image_path):
    image = cv2.imread(image_path)
    if image is None:
        raise ValueError("Image not found or unable to load.")
    return image

def extract_text_from_object(image_path):
    
    preprocessed_image = preprocess_image_for_ocr(image_path)
    text = pytesseract.image_to_string(preprocessed_image)
    return text
def extract_image_as_whole(image_path):
    
    image = cv2.imread(image_path)
    txt= pytesseract.image_to_string(image)
    return txt