# Overview and Architecture

AI and machine vision enable real-time detection of welding defects, ensuring immediate corrective action before issues escalate. By leveraging the right camera and computing hardware, a trained AI model continuously monitors the weld, halting the process the moment a defect is detected. Deep learning AI processes video data at frame rates far beyond human capability, delivering unmatched precision and reliability.

## Architecture Overview

### High-Level Architecture Diagram
![Architecture Diagram](./images/defect-detection-arch-diagram.png)
*Figure 1: Architecture Diagram for Weld Porosity Detection Implementation.*

## Supporting Resources
* [Get Started Guide](get-started.md)
* [API Reference](api-reference.md)
* [System Requirements](system-requirements.md)