# Solder Defect Detection

In this example, we showcase a real-world use case: detecting soldering defects on SMD components using an OAK4-CS edge AI camera
mounted on a microscope. The OAK4-S features a 48MP IMX586 rolling shutter sensor, making it ideal for high-resolution, real-time
PCB inspection.

The goal is to demonstrate how easy it is to go from an idea to an initial working prototype for edge-based defect detection,
using tools like Roboflow, LuxonisTrain, and the DepthAI platform—with minimal setup and no machine learning expertise required.

### Materials used

 * AMScope (SM-7 series)
 * [OAK4-CS](https://shop.luxonis.com/products/oak-4-cs)
 * [3D printed camera mount](https://www.thingiverse.com/thing:4792408)

### The Process in a Nutshell

 1. Find a baseline dataset We started with a public Roboflow dataset on PCB defects. First evaluation of its performance was done
    on Roboflow’s web UI.
 2. Capture and annotate our own data to add to baseline dataset Took ~50 microscope photos with the OAK4-S and labeled defects.
 3. Retrain the model Combined public + custom data and trained using [`LuxonisTrain`](https://github.com/luxonis/luxonis-train).
 4. Deploy to the OAK4-S Loaded the model onto the camera for real-time solder inspection.

### Solder Defect Detection Blogpost

Read the full write-up on the OAK4-S microscope setup and defect detection workflow.

[Read the blogpost](https://discuss.luxonis.com/blog/6221-ai-powered-soldering-defect-detection-with-oak4-s-and-a-microscope)