TY - CONF T1 - Smiling faces are better for face recognition T2 - Fifth IEEE International Conference on Automatic Face and Gesture Recognition, 2002. Proceedings Y1 - 2002 A1 - Yacoob,Yaser A1 - Davis, Larry S. KW - between-class scatter matrices KW - Databases KW - discrimination power measure KW - dynamic scenarios KW - expressive faces KW - face recognition KW - facial expressions KW - performance KW - performance differences KW - smiling faces KW - software performance evaluation KW - Training KW - visual databases KW - within-class scatter matrices AB - This paper investigates face recognition during facial expressions. While face expressions have been treated as an adverse factor in standard face recognition approaches, our research suggests that, if a system has a choice in the selection of faces to use in training and recognition, its best performance would be obtained on faces displaying expressions. Naturally, smiling faces are the most prevalent (among expressive faces) for both training and recognition in dynamic scenarios. We employ a measure of discrimination power that is computed from between-class and within-class scatter matrices. Two databases are used to show the performance differences on different sets of faces JA - Fifth IEEE International Conference on Automatic Face and Gesture Recognition, 2002. Proceedings PB - IEEE SN - 0-7695-1602-5 M3 - 10.1109/AFGR.2002.1004132 ER -