How to Do OCR in Python: Simple Steps with pytesseract

To do OCR in Python, use the pytesseract library which acts as a wrapper for Google's Tesseract OCR engine. Install Tesseract on your system, then use pytesseract.image_to_string() to extract text from images.

Syntax

The basic syntax to perform OCR with pytesseract is:

• pytesseract.image_to_string(image): Extracts text from the given image.
• image: An image object loaded using libraries like PIL or OpenCV.

You must have Tesseract OCR installed on your computer and accessible in your system path.

python

import pytesseract
from PIL import Image

# Load image
image = Image.open('sample.png')

# Extract text
text = pytesseract.image_to_string(image)
print(text)

Example

This example shows how to load an image and extract text using pytesseract. It demonstrates the full process from reading the image file to printing the recognized text.

python

import pytesseract
from PIL import Image

# Make sure Tesseract is installed and in your PATH
# Load an example image
image = Image.open('ocr_sample.png')

# Perform OCR to extract text
extracted_text = pytesseract.image_to_string(image)

print('Extracted Text:')
print(extracted_text)

Output

Extracted Text:
Hello, this is a sample text extracted from the image.

Common Pitfalls

Common mistakes when doing OCR in Python include:

• Not installing the Tesseract OCR engine separately (pytesseract is only a wrapper).
• Incorrect image path or unsupported image format.
• Low image quality or noisy images causing poor text extraction.
• Not specifying the correct language if text is not English.

Always check that Tesseract is installed and accessible, and preprocess images for better results.

python

import pytesseract
from PIL import Image

# Wrong: Using pytesseract without Tesseract installed
# This will raise an error

# Right: Ensure Tesseract is installed and in PATH
# Example preprocessing for better OCR
image = Image.open('ocr_sample.png').convert('L')  # Convert to grayscale

text = pytesseract.image_to_string(image)
print(text)

Quick Reference

Tips for effective OCR in Python:

• Install Tesseract OCR from official repo.
• Use pytesseract as a Python wrapper.
• Preprocess images (grayscale, thresholding) to improve accuracy.
• Specify language with lang parameter if needed, e.g., pytesseract.image_to_string(image, lang='eng').
• Use high-quality images with clear text.

Key Takeaways

Install Tesseract OCR engine separately before using pytesseract in Python.

Use pytesseract.image_to_string() to extract text from images easily.

Preprocess images to grayscale or clean noise for better OCR accuracy.

Specify the language parameter if your text is not in English.

Ensure image paths and formats are correct to avoid errors.