👕🎨 Clothing Color Classifier

A TinyML Object Detection model that identifies clothing colors in real time — trained and deployed entirely through Edge Impulse Studio.

Overview

Can a small edge AI model learn to recognize colors on clothing items just from a webcam feed — with no cloud, no heavy hardware, and a small custom dataset? Clothing Color Classifier answers that question with a resounding yes.

This project uses Edge Impulse Studio to train an Object Detection model that locates a clothing item's colored area and classifies its color into one of four categories: Red, Magenta, Pink, and Sky Blue. The final model reached a 94.7% F1 score, with real-time detection tested live through a browser webcam — no software installation required.

Hardware & Tools

• USB Webcam connected to a laptop
• Edge Impulse Studio (data labeling, training, live classification)
• No microcontroller deployment required — runs entirely in-browser

Dataset

• 146 images total (120 training / 26 test)
• 4 balanced classes: Magenta (30), Pink (37), Red (30), Sky Blue (37)
• Images captured with varied angles, distances, and contrasting dark backgrounds

Model

Training configuration: 100 cycles, learning rate 0.001, data augmentation enabled, CPU processor.

Results

F1 Score: 94.7%

Live Demo

Tested directly in-browser via Edge Impulse's Live Classification — no downloads, no firmware flashing.

🔗 Try the live model

Key Takeaways

• Bounding box precision has a sweet spot — too loose or too tight both hurt accuracy
• FOMO is a strong choice for small, custom Object Detection datasets
• A full Edge AI pipeline is achievable entirely through the browser

Future Work

• Deploy to an edge device for offline detection
• Expand to real fabric/clothing items
• Explore outfit-matching recommendations
• Use printable paper templates (hand-colored) to expand color variety in the dataset