Facial Image Processing for Sleepiness Estimation

Natalia I Vargas-Cuentas (1) , Avid Roman-Gonzalez (2)

1 Universidad de Ciencias y Humanidades, Perú.
2 UNSAAC - Universidad Nacional de San Antonio Abad del Cusco

—Sleepiness could cause different accidents at work and in our daily lives. Activities such as driving a car, handling heavy machinery, being in charge of controlling a satellite or monitoring a nuclear plant, are activities that require short visual and motor reaction times. These reactions could be affected by sleepiness. The highest number of these accidents is related to vehicular accidents. WHO statistics show that 1.2 million people worldwide die every year due to road crashes, 50 million people are injured, and more than 3,000 people die daily from road traffic injuries. The primary objective of the present work is to develop a tool based on techniques of artificial intelligence and image processing that can detect states of sleepiness in people whose work needs the greatest attention-to avoid accidents. The idea is to develop an algorithm that can be executed on a computer and through a webcam can record the face of the person or worker to analyze the video and through facial recognition techniques can identify the eyes of the person, and thus identify eyelashes that would be an indicator of sleepiness. It is expected to have an algorithm developed in MATLAB to detect drowsiness and provide some notification.

Mots clés: face detection; eye detection; vehicular accident; yes-no questions; Sleepiness

Domaines: Traitement du signal et de l'image [eess.SP]

Natalia I Vargas-Cuentas, Avid Roman-Gonzalez. Facial Image Processing for Sleepiness Estimation. 2nd International Conference on Bio-engineering for Smart Technologies, Aug 2017, Paris, France. ⟨hal-01637809⟩