A dynamic framework based on local Zernike moment and motion history image for facial expression recognition

详细信息    查看全文

• 作者：Xijian FanAuthor Vitae ; Tardi Tjahjadi ; ^{t.tjahjadi@warwick.ac.uk}Author Vitae
• 关键词：Zernike moment ; Facial expression ; Motion history image ; Entropy ; Feature extraction
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：April 2017
• 年：2017
• 卷：64
• 期：Complete
• 页码：399-406
• 全文大小：929 K
• 卷排序：64

文摘

Proposes a facial expression recognition framework that uses dynamic information. Introduces QLZM_MCF to capture dynamic information in temporal domain. Introduces enMHI_OF to utlise motion speed and spatial information. Proposes a weighting strategy on a grid for high recognition rate.