import cv2
import pytesseract
import matplotlib.pyplot as plt

from difflib import SequenceMatcher

def similar(a, b):
return SequenceMatcher(None, a, b).ratio()

img = cv2.imread('resources/ammy.png')
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
text = pytesseract.image_to_string(img)
spl_text = text.split("\n")
spl_text_two = ''
for sentence in spl_text:
spl_text_two.join(sentence.split())

print('spltwo' + spl_text_two)
for i in range(len(spl_text)+1):
for word in spl_text_two:
print(word)
print(str(i) + " " + spl_text[i])

import cv2
import pytesseract

from difflib import SequenceMatcher

def similar(a, b):
return SequenceMatcher(None, a, b).ratio()

# Set the Tesseract OCR executable path
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'

# Read the image using OpenCV
img = cv2.imread('LINKTOIMAGE')

# Convert the image to grayscale
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# Use pytesseract to extract text from the image
text = pytesseract.image_to_string(gray_img)

# Split the text into lines
spl_text = text.split("\n")

# Initialize an empty string to store the modified text
spl_text_two = ''

# Concatenate words without spaces to remove line breaks
for sentence in spl_text:
spl_text_two += ''.join(sentence.split())

# Convert the text to title case
spl_text_two = spl_text_two.title()

# Print the modified text
print('spl_text_two: ' + spl_text_two)

# Print each word and its corresponding line number
for i, word in enumerate(spl_text):
print(f'{i + 1}: {word.title()}')