Inspired by the hilarious scene in the comedy movie "Sillycon Valley", where an AI app could detect whether something is a hot dog or not a hot dog, this project brings that concept to life using TensorFlow.js!
This is a web-based AI application that uses object detection to classify whether the object in your webcam feed is a hot dog or not a hot dog. It’s a fun and practical way to explore computer vision and web technologies!
In "Sillycon Valley," an Asian developer showcased his app, which used AI to hilariously detect only hot dogs with great precision. This project pays homage to that comedic genius while showcasing the power of modern machine learning libraries.
- Real-Time Object Detection: Uses your webcam to detect objects in real-time.
- Hot Dog Classification: Specifically identifies hot dogs and displays "Hot Dog."
- Not a Hot Dog: If the detected object isn’t a hot dog, it displays "Not a Hot Dog."
- Interactive UI: A fun and intuitive interface with bounding boxes and labels.
- TensorFlow.js: For running machine learning models directly in the browser.
- COCO-SSD: A pre-trained object detection model capable of recognizing 80 object classes, including hot dogs.
- HTML/CSS/JavaScript: For building the web interface.
hot-dog-or-not/ ├── index.html # Main HTML file ├── styles.css # CSS file for styling ├── script.js # JavaScript logic for object detection └── README.md # This file!
- The app loads the COCO-SSD model.
- Your webcam feed is processed in real-time.
- If a hot dog is detected:
- A green bounding box is drawn, and it displays "🌭 Hot Dog!"
- If no hot dog is detected:
- A red bounding box is drawn around the object, and it displays "Not a Hot Dog."
