作者: Yu-li Xue , Xia Mao , Fan Zhang
DOI: 10.1109/ICMLC.2006.258460
关键词:
摘要: Over the last decade, significant effort has been made in developing methods of facial expression analysis. Because limited data sets expressions, comprehensive emotional recognition that is essential areas such as affective computing and human-machine interaction not well studied. This paper provides Beihang University Facial Expression Database, which includes 25 expressions (18 pure 3 mixed 4 complex expressions) many unique appeared other face databases. The questionnaire investigation videos 18 shows effectiveness data. experiment on 9 demonstrates feasibility multiple recognition.