On Tuesday, 15 October 2019, Fujitsu in collaboration with Carnegie Mellon University School of Computer Science, announced it is developing AI facial expression recognition technology that detects subtle changes in facial expression with a high degree of accuracy.
According to the company, one of the obstacles for facial expression recognition technology is the difficulty in providing large amounts of data required to train detection models for each facial pose because faces are usually captured with various angles, sizes, and positions in the real-world.
To address the problem, Fujitsu is said to have adopted a different normalisation process for each facial image. For example, when the angle of the subject’s face is oblique, the technology can adjust the image to more closely resemble the frontal image of the face, allowing the detection model to be trained with a relatively small amount of data.
Fujitsu anticipates that the new technology will find use in a variety of real-world applications, including communication facilitation for employee engagement, to improve workplace safety for drivers and factory workers and enhancing robots’ reactions.
This technology has achieved a high detection accuracy rate of 81% even with limited training data – it is also more accurate than other existing technologies according to certain facial expression recognition technology benchmarks.
Fujitsu aims to introduce technology to practical applications for various use cases, including teleconferencing support, employee engagement measurement, and driver monitoring.
Edited by Jenna Cook
Follow Jenna Cook on Twitter
Follow IT News Africa on Twitter