BrainChip looks to improve facial classification accuracy

1 min read

BrainChip, a neuromorphic computing company, has announced the BrainChip Studio 2018.3 update for its BrainChip Studio AI-powered video analysis software.

The update includes a powerful new mode that improves the software’s face classification accuracy by between 10-30 percent.

To date, BrainChip Studio has been using spiking neural networks to enable facial classification on partial faces. This partial-face mode is useful in situations where the probe image or the extracted faces may be obscured due to hats, masks, scarves or camera angle.

BrainChip Studio 2018.3 uses a full-face mode to perform facial classifications. In situations where the entire face is visible in the probe image or in the extracted faces, this new mode provides a significant increase in facial classification accuracy. Depending on the dataset used, testing indicates this mode provides a significant improvement in accuracy, but without impacting on throughput.

According to MarketsandMarkets, the facial recognition market is expected to be worth over $7billion by 2022.

BrainChip Studio’s facial classification technology works in environments where traditional biometric-based face recognition systems have tended to fail, including low-light, low-resolution, and visually-noisy environments.

BrainChip Studio is primarily used by law enforcement, intelligence, and counter-terrorism agencies that use existing CCTV infrastructure.

“We are always looking for ways to continually improve our products by listening to our customer requests,” said Bob Beachler, BrainChip’s Senior Vice President of Marketing and Business Development. “Not surprisingly, improving accuracy is typically at the top of list for video analytic software. With BrainChip Studio 2018.3 we have been able to provide a dramatic increase in accuracy.”