TV

Software Can Recognize Eye Contact and Gaze in Everyday Situations

Eye contact is an important non-verbal cue in social signal processing and promising as a measure of attention in human-object interactions and attentive user interfaces. Researchers from Saarland University have developed software for eye contact detection that can spot a person's gaze independent of environment, imaging position, and object target size. They evaluated the method in real-world scenarios: detecting eye contact at the workplace from cameras mounted to target objects, as well as during everyday social interactions with the wearer of a head-mounted egocentric camera. To learn more, read a Tech Briefs Q&A with the technology's inventor.