📄️ Introduction
navio VISION is a visual anomaly detection solution for automated quality inspection, built as an extension on top of the navio platform. It lets you train a model that distinguishes normal from anomalous images of your parts or production states — without any machine learning expertise — and use it to inspect images manually or directly from your production line.
📄️ Creating a Use Case
A use case refers to a specific scenario where you want to detect anomalies — for example, a certain part or production state you want to inspect. The Use cases overview shows all your use cases along with the provided demo use cases, which you can explore to get a better understanding of how navio VISION works in practice.
📄️ Inspecting Images
Once your model is ready, you can inspect images directly on the use case's Details tab — no integration required.
📄️ Live Data Connections
Link your inspection devices to navio VISION and start receiving live visual data for real-time analysis and anomaly detection. A typical setup is a camera on your production line that writes images to a cloud storage folder — navio VISION pulls new images in a configurable interval and automatically analyzes them using your trained model.
📄️ Labeling & Retraining
The predictions of your model become more accurate the more real, labeled production data it is trained on. navio VISION closes this loop: label the images collected via your live data connection and retrain the model with a single click.
📄️ Monitoring
The Monitoring tab of a use case gives you an overview of all inspection results over time — whether they come from your live data connection or from manual inspections.