Facial expression recognition based on local binary patterns

X. Feng, M. Pietikäinen, A. Hadid

科研成果: 期刊稿件文章同行评审

82 引用 (Scopus)

摘要

In this paper, a novel approach to automatic facial expression recognition from static images is proposed. The face area is first divided automatically into small regions, from which the local binary pattern (LBP) histograms are extracted and concatenated into a single feature histogram, efficiently representing facial expressions-anger, disgust, fear, happiness, sadness, surprise, and neutral. Then, a linear programming (LP) technique is used to classify the seven facial expressions. Experimental results demonstrate an average expression recognition accuracy of 93.8% on the JAFFE database, which outperforms the rate of all other reported methods on the same database.

源语言英语
页(从-至)592-598
页数7
期刊Pattern Recognition and Image Analysis
17
4
DOI
出版状态已出版 - 12月 2007

指纹

探究 'Facial expression recognition based on local binary patterns' 的科研主题。它们共同构成独一无二的指纹。

引用此