完整後設資料紀錄
DC 欄位語言
dc.contributor.authorWu, Yu-Kuen
dc.contributor.authorLai, Shang-Hong
dc.date.accessioned2009-08-23T04:43:21Z
dc.date.accessioned2020-05-25T06:52:19Z-
dc.date.available2009-08-23T04:43:21Z
dc.date.available2020-05-25T06:52:19Z-
dc.date.issued2007-01-31T05:43:22Z
dc.date.submitted2006-12-04
dc.identifier.urihttp://dspace.lib.fcu.edu.tw/handle/2377/3637-
dc.description.abstractIn this paper, we propose a new facial expression recognition algorithm based on supervised locally linear embedding (SLLE) analysis on the optical flow and ratio image. In this algorithm, we first extract the face region from the face image to remove factors due to global head motion. Secondly, we compute the optical flow and ratio image between the neutral face and expression images and then apply the SLLE to extract the low-dimensional discriminating features from the expression motion and brightness variation. Finally, we compute the distance between the low-dimensional feature vectors to recognize the facial expression. Experimental results on the JAFFE face database and Yale database show that the proposed algorithm outperforms previous methods for facial expression recognition.
dc.description.sponsorship元智大學,中壢市
dc.format.extent6p.
dc.format.extent2270351 bytes
dc.format.mimetypeapplication/pdf
dc.language.isozh_TW
dc.relation.ispartofseries2006 ICS會議
dc.subject.otherFace Detection and Recognition
dc.titleFacial Expression Recognition Based on Supervised LLE Analysis of Optical Flow and Ratio Image
分類:2006年 ICS 國際計算機會議

文件中的檔案:
檔案 描述 大小格式 
ce07ics002006000181.pdf2.22 MBAdobe PDF檢視/開啟


在 DSpace 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。