Body Composition Scale Kit: Build an AI Edge Device That Recognizes Food Items and Totals Your Cart Automatically

Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.

Imagine a scale on your kitchen counter that not only weighs ingredients but sees them. Place a packet of oats, a jar of peanut butter, or a bunch of bananas on the pad, and within a second the system knows exactly what they are—adding them to a live shopping cart and logging nutritional intake for the day. This Body Composition Scale Kit fuses a high-resolution OV2640 camera with a quantised YOLOv5 object detection model running entirely on an ESP32-S3, so no cloud is ever touched. The result is a privacy-first, offline-smart appliance that transforms how health‑conscious builders manage groceries, meal-prep, and personal wellness data.

What You'll Build

You’ll assemble a compact device that pairs a 5 kg load cell with a camera-driven AI processor. When an item is placed on the weighing pad, the camera captures an image, the on‑board YOLOv5 model identifies the SKU, and the ESP32‑S3 computes weight and quantity. The item, weight, and timestamp are then formatted into an MQTT message and pushed to a broker—instantly updating your shopping cart dashboard or a custom health‑tracking app. The TFT display shows the recognised item name and running total, while a DS3231 RTC stamps every event for accurate daily logs. All inference runs locally, giving you fast, reliable identification even without Wi‑Fi.

What You'll Learn

• Quantising and deploying a YOLOv5 vision model onto an ESP32‑S3 microcontroller with OV2640 camera input
• Interfacing an HX711 precision ADC with a 5 kg load cell for accurate weight readings and sensor calibration
• Implementing MQTT client logic on an embedded device to push cart totals and item logs over Wi‑Fi
• Integrating a real‑time clock (DS3231), microSD storage, and a TFT display into a single portable system

Kit Contents

Why Buy This Kit Instead of Sourcing Parts Separately

Who This Kit Is For

This kit is engineered for final‑year B.Tech ECE/CS students building a capstone project around edge AI or IoT‑enabled health tech. It’s also ideal for Smart India Hackathon teams tackling nutrition tracking or inventory automation themes, and for ATL Tinkering Lab mentors guiding advanced students through embedded vision. If you’re a hobbyist from VIT, NIT, or BITS with a solid grasp of Arduino or ESP-IDF and a desire to deploy a real quantised model at the edge, this kit will push your skills exactly where the industry is heading.

Built and Backed by Compoden

Every Compoden kit ships with an AI build companion trained on this exact project — accessible via a QR code on the box, with WhatsApp and email backup. We've spent 10 years building projects for makers, schools, and institutions across India. If a part fails because of a manufacturing defect, replace it free within 7 days.

Choose your assembly option:

• Soldering Kit — 25W soldering iron, 60/40 solder wire, flux, and small perfboard for permanent assembly.
• Breadboard Combo — 800-point full-size breadboard with 65-piece jumper wire pack for solderless prototyping.