Harness the power of AI-powered intelligence for enhanced recovery and recycling.
TOMRA’s deep learning technology is built on artificial neural networks that our in-house software engineers and recycling experts have trained.
Sophisticated algorithms utilize object recognition to compare millions of labeled images in the software to identify individual objects and materials as they speed along the sorting line. Our deep learning software is especially powerful in identifying hard-to-classify objects, leading to significantly higher purity results.
Our wide and ever-growing application ecosystem is thanks to our extensive experience in the recycling industry. The technology is designed to improve sorting accuracy and enables operators to create new material streams and access data for valuable decision-making.
At TOMRA, we’ve used Artificial Intelligence for decades, and we’re confident that deep learning will continue to add tremendous value for recyclers.
Main applications
Plastics
Paper
Wood
Packaging
AI-powered intelligence to boost sorting performance
Deep learning technology is based on artificial neural networks to solve a variety of complex tasks that conventional computer programs cannot. The “deep” in deep learning pays homage to the multiple layers of different functions that identify and classify objects.
The more complex the sorting task, the more layers of data, and hence, the deeper the learning. The technology then extracts a hierarchy of features from raw input data and groups it into different categories.
The use of deep learning technology not only automates manual sorting but also enables the industry to achieve high-quality recyclates through more granular sorting.
Deep Learning technology in action!
Related news
Artificial neural networks changing the game in wood recycling
Get ready for big data TOMRA introduces deep learning add-on for AUTOSORT™ machines at Ecomondo
