Data Science

Using Machine Learning for Green Screen Matting

A Danish startup has trained neural networks to recognize the pattern of a perfect cut-out. CloudCutout is applying machine learning techniques to the quotidian yet persnickety process of isolating an image from a background. Their initial target market is school photography, with the aim of undercutting the market by charging half the “standard knockout” bulk cost (50 cents) per image.

The Copenhagen-based team says its algorithm can automatically cut out studio images from consistent backgrounds, such as green- or blue-screens, but also from “standard backgrounds” used for school photographs, and also from the white backgrounds popular for product shots—saving time and money. Or that’s the pitch.

To ensure that they can scale to accommodate demand for the cutout service, they’re distributing their cutout engine on IBM SoftLayer and Amazon Web Services. “Computations related to neural networks are executed on bare metal SoftLayer nodes, that provide the most recent NVIDIA Tesla K80 GPUs, whereas remaining parts of our infrastructure are hosted on AWS,” they note.

Read more on TechCrunch >>

Discuss (0)