Unable to Extract Text from Image Using Tesseract OCR - How to Preprocess Instagram Reels Frames

Question

I am working on a project where I need to extract text from frames of an Instagram Reels video. I used the yt-dlp to download the video, extracted frames using ffmpeg, and attempted to read the text from the frames using Tesseract OCR.

However, I'm unable to extract text from the frames. Below is the code snippet I'm using:

from PIL import Image
import pytesseract
import os

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

image_path = r"Insta Reels\frame_0077.png"

try:
    if not os.path.exists(image_path):
        raise FileNotFoundError(f"The file {image_path} does not exist.")

    image = Image.open(image_path)

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

    if text.strip():
        print("Extracted text:")
        print(text)
    else:
        print("No text was extracted from the image.")

except FileNotFoundError as e:
    print(f"Error: {e}")
except Exception as e:
    print(f"An error occurred: {e}")

The problem is that the extracted text is either incomplete or not detected at all.

What preprocessing steps should I apply to these frames to improve the accuracy of Tesseract OCR?

Edit:

import cv2
import pytesseract

# Mention the installed location of Tesseract-OCR in your system
pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
image_path = r"Insta Reels\Video by mydarlingfood\frame_0077.png"

# Read image from which text needs to be extracted
img = cv2.imread(image_path)

# Preprocessing the image starts

# Convert the image to gray scale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# Performing OTSU threshold
ret, thresh1 = cv2.threshold(gray, 0, 255, cv2.THRESH_OTSU | cv2.THRESH_BINARY_INV)

# Specify structure shape and kernel size. 
rect_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (18, 18))

# Applying dilation on the threshold image
dilation = cv2.dilate(thresh1, rect_kernel, iterations=1)

# Finding contours
contours, hierarchy = cv2.findContours(dilation, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)

# Creating a copy of image
im2 = img.copy()

# Looping through the identified contours
for cnt in contours:
    x, y, w, h = cv2.boundingRect(cnt)
    
    # Drawing a rectangle on copied image
    rect = cv2.rectangle(im2, (x, y), (x + w, y + h), (0, 255, 0), 2)
    
    # Cropping the text block for giving input to OCR
    cropped = im2[y:y + h, x:x + w]
    
    # Display the cropped image
    cv2.imshow("Cropped Image", cropped)
    cv2.waitKey(0)  # Press any key to continue to the next cropped image

cv2.destroyAllWindows()

original image

after i tried to crop the image

It seems like it is not able to detect the different color.