🖼️ Image Text Summarizer (OCR + NLP)

This project extracts text from an image using Tesseract OCR and summarizes the extracted text using Hugging Face Transformers.

It combines:

• Optical Character Recognition (OCR)
• Natural Language Processing (NLP)
• Transformer-based summarization models

---

⚙ Installation Guide

1️⃣ Install Python

Make sure Python 3.8 or higher is installed.

Check version:

python --version

If not installed, download from: https://www.python.org/downloads/

---

2️⃣ Clone the Repository

git clone https://github.com/your-username/image-text-summarizer.git
cd image-text-summarizer

---

3️⃣ Install Required Dependencies

pip install pytesseract pillow transformers torch

(Optional) Create a virtual environment:

python -m venv venv
venv\Scripts\activate     # Windows
source venv/bin/activate  # Linux/macOS

---

4️⃣ Install Tesseract OCR (Important)

This project requires Tesseract OCR installed separately.

🔹 Windows

1. Download from: https://github.com/tesseract-ocr/tesseract
2. Install it.
3. If needed, set path in your script:

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

---

🔹 Linux (Ubuntu/Debian)

sudo apt update
sudo apt install tesseract-ocr

---

🔹 macOS

brew install tesseract

---

▶ How to Use

Step 1: Add Your Image

Place your image file inside the project folder.

Example:

project-folder/
│
├── image_summary.py
├── sample.png

---

Step 2: Update Image Path

Open image_summary.py and update:

image = Image.open("sample.png")

Make sure the filename matches your image.

---

Step 3: Run the Script

python image_summary.py

---

✅ Output

The script will:

1. Extract text from the image.
2. Print extracted text.
3. Generate summarized text.
4. Print the final summary.

---

🧠 How It Works

1. Image is loaded using Pillow.
2. Text is extracted using Tesseract OCR.
3. Extracted text is passed to Hugging Face summarization pipeline.
4. Transformer model generates a concise summary.

---

🚨 Common Errors & Fixes

❌ TesseractNotFoundError

Make sure:

• Tesseract is installed
• Path is correctly set (Windows users)

---

❌ Model Download Takes Time

The first run may take longer because the transformer model downloads automatically.

---

📦 requirements.txt (Optional)

You can create a requirements.txt file with:

pytesseract
pillow
transformers
torch

Install using:

pip install -r requirements.txt

---

👨‍💻 Author

Your Name
Computer Science Student
Interested in AI, NLP, and Automation

---

⭐ If you like this project, give it a star on GitHub!