Computer vision requires labelled datasets which are often filled with errors and “anomalies” that can destroy the performance of the models trained using them. The image labelling industry is booming, but how can we ensure quality of labelled images without having to check each and every one?
Here comes Viz-EDA, the automatic anomaly and data visualisation tool for industry. The tool exists as a simple Flask app, with the ability to build it further or start entirely from scratch.
The project involves understanding different types of CV datasets and building a modular visualisation tool that runs with both local and cloud-hosted data. Moreover, it uses an automated “anomaly” detector using a trained computer vision model to check the data.
To find out more about how computer vision is changing the economics of the recycling industry, view our WasteNet page.

To see more, view GitHub