Zebra unveils deep learning OCR for warehousing

Zebra Technologies Corporation has unveiled Deep Learning Optical Character Recognition (DL-OCR). The solution supports manufacturers and warehousing operators who increasingly need fast, accurate, and reliable ready-to-use deep learning solutions for compliance, quality, and presence checks.

Getting an OCR inspection right can be challenging. A variety of factors including stylized fonts, blurred, distorted or obscured characters, reflective surfaces and complex, non-uniform backgrounds can make it impossible to achieve stable results using traditional OCR techniques.

The new industrial-quality DL-OCR tool is an add-on to Zebra Aurora software that makes reading text quick and easy. DL-OCR comes with a ready-to-use neural network that is pre-trained using thousands of different image samples. It can deliver high accuracy straight out of the box, even when dealing with very difficult cases.

Users can create robust OCR applications in just a few simple steps—all without the need for machine vision expertise.

“Our advanced OCR technology has been enhanced and optimized by machine vision experts to offer state-of-the-art, industrial reliability,” said Donato Montanari, Vice President and General Manager, Machine Vision, Zebra Technologies.

“Users simply highlight the read area, and the software does the rest. Zebra Aurora works on most fonts out of the box - even stylized characters so there is no need to train fonts or maintain libraries.”

Zebra’s DL-OCR addresses the need for faster, more accurate forms of automation by warehousing operators and manufacturers. The tool is helping today’s industrial imaging professionals think and act more like data scientists.

“Our vision is to enable engineers to harness the latest innovations in the field by making them more accessible to implement and leverage. It means engineers can think and act more like data scientists in the face of increasing volumes and varieties of data, and better understand the workings and business benefits of deep learning solutions,” said Montanari.

“Being able to sense, analyse and act in realtime can be achieved with ready-to-use deep learning tools that capture and analyse data at the edge.”