Waldo Finder! 🌟

Waldo Solver is a fast, privacy-first, AI-powered desktop app that helps you find Waldo in images using advanced computer vision models. Built for speed, simplicity, and local intelligence.

Runtime update: the app now uses a TypeScript inference pipeline instead of the old Python server, so users no longer need to bundle Python or manage extra runtime dependencies.

---

Tech Used 🧑‍💻

---

Core Features ⚡

• 🖼️ AI-Powered Waldo Detection:
  Uses local computer vision models to find Waldo in your images.

• 🔍 Offline Processing:
  All detection runs locally. No internet required, no data leaves your device.

• 📂 SUPER FREAKING FAST:
  Select and process your images at the speed of light, with live progress tracking.

• 📂 Multi Objects classification:
  Can differentiate between Waldo and all of his friends and family! ( I assume they are, is there a lore to this?)

• 🎨 Modern UI:
  Responsive, clean interface built with SolidJS and TailwindCSS.

• 💻 Cross-platform Desktop App:
  Powered by Tauri for lightweight, native performance on Windows, macOS, and Linux.

• ⚙️ Configurable Settings:
  Adjust detection sensitivity, timeout, and save location.

---

Screenshots 📸

Project showcase: Snappy, Modern, Relible, and VERY Accurate! 🌟

Hello Screen: Welcome screen with animated logo and quick access to start detection.

File Picker: Select images for Waldo detection with a modern, easy-to-use dialog.

Loading Screen: Real-time progress bar and status while processing images.

Main Detection Screen: View and interact with the image being analyzed for Waldo.

Solved Screen: See the detected Waldo location highlighted on your image.

Blur Solution: Privacy-focused preview with sensitive regions blurred until revealed.

Settings Screen: Configure detection parameters, timeout, and save location.

About Screen: Learn more about the app, its features, and its privacy-first approach.

---

Models Used 🧠

All models run locally and are optimized for performance.

Model	Purpose	Notes
YOLOv12	Object detection (Waldo)	Fast, accurate, runs locally
Custom Waldo Dataset	Trained for Waldos detection	Improves accuracy on challenge images

• The training wasn't straightforward, as you can see you can't just train a model on these beefy huge images, so I had to be ... creative :^)

---

Dataset 📂

I BUILT MY OWN DATASAET BY SPENDING DAYS OF MY LIFE SOLVING A KIDS BOOK SERIES

• I shouldn't say it that way but who cares
• link if you're interested : Dataset

Dataset: uses a 68 Super high resolution hand solved Waldo spreads.

---

Project Structure

/ (root)
├── README.md              # This file.
├── package.json           # Node dependencies and scripts.
├── tsconfig.json          # Typescript configuration.
├── vite.config.ts         # Vite configuration.
├── public/                # Public assets (logo, etc.).
├── screenshots/           # Application screenshots.
├── src/                   # SolidJS source code.
│   ├── App.css            # App level styles.
│   ├── App.tsx            # Main App component.
│   ├── components/        # Reusable UI components.
│   ├── hooks/             # Custom hooks.
│   ├── routes/            # Application pages.
│   ├── utils/             # Utility functions.
│   └── main.tsx           # Application entry point.
└── src-tauri/             # Tauri integration (Rust backend).

---

Setup and Development 🛠️

1. Prerequisites:

   • Node.js (v18+), pnpm, Rust, and Tauri CLI.

2. Install Dependencies:

   pnpm install

3. Run in development:

   pnpm start

4. Build production assets:

   pnpm build

5. Use the installer:

   • From the releases section on windows, for other installers you can build on your machine.

---

Recommended IDE Setup 💻

• VS Code
• Tauri for VS Code
• rust-analyzer

---

Contributing 👥

Contributions are welcome!
If you find a bug, have a feature request, or want to improve the codebase, feel free to:

1. Open an issue to discuss the change.
2. Fork the repository.
3. Create your feature branch (git checkout -b feature/AmazingFeature).
4. Commit your changes (git commit -m 'Add some AmazingFeature').
5. Push to the branch (git push origin feature/AmazingFeature).
6. Open a Pull Request.

---

Roadmap 🗺️

Phase 1: Core Functionality

• Offline Waldo detection.
• High accuracy model.
• Configurable detection settings.

Phase 2: Enhanced Features

• Annotated output images.
• Performance and UI improvements.
• Error handling and logging.

License ⚖️

This project is licensed under a custom License - see the LICENSE file for details.

---

Contact 📬

• GitHub: mohaneddz
• Email: mohaned.manaa.dev@gmail.com

---