VisionParse AI

AI-powered OCR web application for extracting, processing, and analyzing text from images and PDF documents.

---

🚀 Overview

VisionParse AI is a full-stack OCR (Optical Character Recognition) application built using React + FastAPI that extracts text from images and PDFs using Tesseract OCR.

The application includes smart text processing, background OCR tasks, PDF support, export functionality, and a modern responsive UI.

---

✨ Features

• 📤 Drag & Drop File Upload
• 🖼️ Image OCR Processing
• 📄 PDF Text Extraction
• ⚡ Background OCR Processing
• 📊 OCR Confidence Scores
• 🔍 Search Within Extracted Text
• 🧠 Smart Text Cleanup & Processing
• 📑 TXT / PDF / DOCX / JSON Export
• 🌙 Dark Mode UI
• 📱 Responsive Design
• 🔐 JWT Authentication
• 📋 History Dashboard

---

🛠️ Tech Stack

Frontend

• React 18
• Vite
• Tailwind CSS

Backend

• FastAPI
• Python
• SQLAlchemy

OCR & Processing

• Tesseract OCR
• OpenCV
• pdf2image
• Poppler

Authentication

• JWT Authentication
• Passlib / bcrypt

---

📂 Project Structure

OCR/
├── frontend/
├── backend/
├── README.md
└── .gitignore

---

⚙️ Installation & Setup

1. Clone Repository

git clone https://github.com/YOUR_USERNAME/VisionParseAI.git
cd VisionParseAI

---

🔧 Backend Setup

cd backend

python -m venv venv

# Windows
venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Run backend server
uvicorn main:app --reload

Backend runs on:

http://localhost:8000

API Docs:

http://localhost:8000/docs

---

🎨 Frontend Setup

cd frontend

npm install

npm run dev

Frontend runs on:

http://localhost:5173

---

🔑 Environment Variables

Example .env configuration:

TESSERACT_PATH=C:/Program Files/Tesseract-OCR/tesseract.exe
POPPLER_PATH=C:/poppler/Library/bin

---

📸 Screenshots

Dashboard

(Add Screenshot Here)

Upload & OCR Processing

(Add Screenshot Here)

OCR Result View

(Add Screenshot Here)

---

🔌 Main API Endpoints

Method	Endpoint	Description
POST	/api/upload	Upload document
GET	/api/ocr/result/{id}	Get OCR result
GET	/api/history	Document history
GET	/api/export/{id}	Export extracted text
POST	/api/auth/login	User login

---

🔒 Security Features

• File validation
• JWT authentication
• UUID-based file naming
• Secure environment variables
• Restricted CORS configuration

---

📌 Project Status

✅ Core OCR pipeline completed ✅ Frontend and backend integration completed ✅ Local OCR processing functional

Future improvements:

• Advanced AI text analysis
• Cloud deployment
• OCR optimization
• Enhanced UI/UX

---

👨‍💻 Author

Gokul Nath

---

📄 License

MIT License