Mouth covered detection for yawn

Masrullizam Mat Ibrahim, John Soraghan, Lykourgos Petropoulakis

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

6 Citations (Scopus)

Abstract

Yawn is one of the common fatigue sign phenomena. The common technique to detect yawn is based upon the measurement of mouth opening. However, the spontaneous human action to cover the mouth during yawn can prevent such measurements. This paper presents a new technique to detect the covered mouth by employing the Local Binary Pattern (LBP) features. Subsequently, the facial distortions during the yawn process are identified by measuring the changes of wrinkles using Sobel edges detector. In this research the Strathclyde Facial Fatigue (SFF) database that contains genuine fatigue signs is used for training, testing and evaluation of the developed algorithms. This database was created from sleep deprivation experiments that involved twenty participants.
Original languageEnglish
Title of host publication2013 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)
PublisherIEEE
Pages89-94
Number of pages4
ISBN (Print)9781479902675
DOIs
Publication statusPublished - 10 Oct 2013
Event2013 IEEE International Conference on Signal and Image Processing Applications (ICSIPA) - Meloka, Malaysia
Duration: 8 Oct 201310 Oct 2013

Conference

Conference2013 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)
Country/TerritoryMalaysia
CityMeloka
Period8/10/1310/10/13

Keywords

  • face recognition
  • sleep
  • edge detection
  • artificial neural networks
  • distortion measurement
  • LBP features
  • SFF database
  • sobel edge detector

Fingerprint

Dive into the research topics of 'Mouth covered detection for yawn'. Together they form a unique fingerprint.

Cite this