Telling attention from distraction, with emotion recognition

Detects whether a person at a screen is attentive or distracted, at 87% accuracy; checks across frames cut false alarms by 40%.

Computer vision
Samsung R&D Institute India
Sep 2023 – Nov 2023
Shipped
short entry

87%

attention-monitoring accuracy

○ reported, from my resume

40%

fewer false positives from multi-frame validation

○ reported, from my LinkedIn

Illustration drawn by code: landmarks and head pose; attention drops as the head turns away.

Reads facial expression, eye movement, yawns and head pose, and confirms a signal across several frames before raising an alert. Emotion recognition is a feature of the same app. Used in the exam-proctoring platform.

More in computer vision