期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：1
出版社：S&S Publications
摘要：This paper is an important milestone towards automatic person authentication. In this work, from avideo source, video frames with pose free face is automatically sensed. Then mouth region is localized automatically.Then person identification is done using local binary pattern histogram of mouth region. Person identificationperformance while using neutral face, smile expression and visual speech are compared. A big custom dataset of 180videos of 30 persons are used. The result gives the conclusion that for person identification visual speech performs wellwith F1 score of 0.95, followed by neutral face, 0.93 and then smile expression, 0.87. It also concludes that the mouthcomponent of the face itself is efficient enough to identify persons.
关键词：Person identification; Local binary pattern histogram; Neutral; Smile expression; Visual speech;Accuracy; F1 score.
