Edge AI Defect Inspector with Vision Shield
Edge AI Defect Inspector: Build a Real-Time Quality Inspection Line with Arduino Portenta H7 & Vision Shield
Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.
Assemble a miniature industrial defect inspection station that runs a MobileNetV2 neural network directly on the Portenta’s M7 core. The Vision Shield camera captures parts as they pass, classifies each as good or defective, and triggers a relay to reject faulty items — mirroring the intelligence of a smart factory QC line. From model training to hardware integration, you’ll build a complete edge AI system that makes decisions in milliseconds.
What You'll Build
A fully functional edge AI inspection station. You'll train a TensorFlow Lite model to recognize product defects using images from the Portenta Vision Shield, deploy it on the dual-core H7 processor, and program the 5V relay to physically separate good parts from rejects. A WS2812B LED ring provides real-time visual feedback — green for accepted, red for rejected — while the entire system is housed inside a DIN rail enclosure for a professional, factory-floor look.
What You'll Learn
- Train and quantize a MobileNetV2 model using TensorFlow Lite Micro for on-device inference
- Capture frames from the Vision Shield camera and preprocess them for the neural network
- Implement a state machine that controls a relay actuator based on classification results
- Design a stable power delivery system with a buck converter, resistors, and capacitors for noise-sensitive industrial-grade hardware
Kit Contents
| Component | Quantity |
|---|---|
| Arduino Portenta H7 | x1 |
| Portenta Vision Shield | x1 |
| 5V Relay Module | x1 |
| WS2812B 8-LED Ring | x1 |
| LM2596 Buck Converter | x1 |
| 470Ω Resistors | x5 |
| 100nF Caps | x10 |
| PCB Prototype Board | x2 |
| DIN Rail Enclosure | x1 |
| 5V 3A PSU | x1 |
| Soldering Iron | x1 |
| Solder Wire | x1 |
Why Buy This Kit Instead of Sourcing Parts Separately
| Factor | Sourcing Separately | Compoden Kit |
|---|---|---|
| Compatibility checks | You verify every part | Pre-tested as a system |
| Build support | Forums and scattered tutorials | AI companion trained on this exact project |
| Time to first working build | Days of debugging | Hours, with step-by-step guidance |
| Shipping coordination | Multiple sellers, multiple delays | One shipment from Bengaluru in 3-5 days |
Who This Kit Is For
Final-year B.Tech students in ECE or EEE developing a capstone project on industrial automation or embedded AI. Participants in Smart India Hackathon or Make-in-India prototyping challenges who need a reliable hardware foundation for defect detection demos. Engineering researchers at IITs, NITs, VIT, or BITS Pilani evaluating Portenta H7 and TensorFlow Lite for smart manufacturing use cases.
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.
What if I get stuck during the build?
Scan the QR code on the box to access the AI companion, which has been trained on every wiring connection, code snippet, and troubleshooting scenario for this kit. You can also reach our team via WhatsApp for direct assistance.
Can I modify the model to detect different types of defects?
Yes. The project is designed so you can swap in your own retrained MobileNetV2 model. You’ll learn how to collect image datasets, retrain, and deploy custom TFLite models for any defect classification task.
Does the kit include a conveyor belt or mechanical parts?
No. The kit concentrates on the electronics, camera, and AI inference. You can test the system with a manual slide or integrate it with your own conveyor mechanism; the relay output is ready to drive external actuators.
Is this suitable for a college project submission or hackathon?
Absolutely. The project covers advanced topics in edge computing, machine learning deployment, and industrial IoT—exactly the depth expected for final year or competition-grade prototypes.
Portenta Vision Shield camera feeds MobileNetV2 TFLite model on M7 core. Relay rejects defective parts.
What's in this kit
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.
Shipping Information
- Prepaid Orders: ₹75 for orders up to ₹999, FREE shipping above ₹999
- COD Orders: ₹125 shipping + ₹50 COD fee = ₹175 total
- Delivery Timeline: Dispatch in 1-2 days, delivery in 2-7 days depending on location
Returns & Warranty
- 7-Day Return: Manufacturing defects only (approval required)
- Warranty: 7 days from delivery
- Non-Returnable: Batteries, consumables, cut wires, clearance items