At the recent SPS show, the three companies demonstrated the first product to emerge from the joint project – a deep-learning-based optical character recognition (OCR) function called Deep OCR. It is claimed to achieve remarkably fast read rates even on fonts that would otherwise be difficult to recognise.
Machine vision algorithms based on deep learning are opening up new ways to improve quality, boost productivity and prevent waste, while making manufacturing more flexible. “Our collaboration with MVTec gives machine-builders access to the best selection of the best performing vision functions around,” says B&R’s machine vision expert, Andreas Waldl. “They are an industry leader in both deep learning and classic rule-based algorithms – two complementary approaches that each play an essential role in machine automation."
High-performance deep-learning algorithms need powerful processors. But implementing them on edge devices makes power consumption a critical issue. This is where Hailo comes in. Despite being capable of 26 tera-operations per second, its inference accelerators have a low power consumption. “Hailo is helping us put truly groundbreaking speed and intelligence where our customers need it for their fastest and most adaptive manufacturing solutions,” explains Waldl.
“This kind of collaboration is exactly what we had in mind when we started Hailo,” says the company’s CEO, Orr Danon. “The new B&R camera harnesses Hailo's top-performing AI accelerator, and in combination with their state-of-the-art edge devices and MVTec's advanced machine learning algorithms, we are setting new performance standards that will improve productivity and enhance quality in industrial applications.”
B&R’s partnership with MVTec and Hailo will turn it machine vision cameras into powerful edge devices
Hailo: Twitter LinkedIn Facebook
MVTec: LinkedIn
