Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/98794
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGeng, Congen
dc.contributor.authorJiang, Xudongen
dc.date.accessioned2013-09-09T07:31:39Zen
dc.date.accessioned2019-12-06T19:59:44Z-
dc.date.available2013-09-09T07:31:39Zen
dc.date.available2019-12-06T19:59:44Z-
dc.date.copyright2012en
dc.date.issued2012en
dc.identifier.citationGeng, C., & Jiang, X. (2012). Face alignment based on the multi-scale local features . 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1517-1520.en
dc.identifier.urihttps://hdl.handle.net/10356/98794-
dc.identifier.urihttp://hdl.handle.net/10220/13413en
dc.description.abstractMany face recognition algorithms depend on careful positioning of face images into the same canonical pose. Currently, this positioning is usually done by detecting the locations of eyes. And the face images are transformed to the same positions according to the eye coordinates detected. In this paper, we describe a method based on multi-scale local features to achieve face alignment automatically not just dependent on the localizations of two eyes. Given an unaligned face image resulting from a face detector and a set of aligned face images in the data set, we build an automatic transformation mechanism, under which the unaligned face image can be precisely aligned for the following recognition process. Our alignment method improves performance on face recognition tasks, over images aligned by many other algorithms.en
dc.language.isoenen
dc.rights© 2012 IEEE.en
dc.subjectDRNTU::Engineering::Electrical and electronic engineeringen
dc.titleFace alignment based on the multi-scale local featuresen
dc.typeConference Paperen
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen
dc.contributor.conferenceIEEE International Conference on Acoustics, Speech and Signal Processing (2012 : Kyoto, Japan)en
dc.identifier.doihttp://dx.doi.org/10.1109/ICASSP.2012.6288179en
item.grantfulltextnone-
item.fulltextNo Fulltext-
Appears in Collections:EEE Conference Papers

Google ScholarTM

Check

Altmetric

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.