Show simple item record

dc.contributor.authorXue, Mingliang
dc.contributor.authorMian, A.
dc.contributor.authorLiu, Wan-Quan
dc.contributor.authorLi, Ling
dc.contributor.editorNOT FOUND
dc.date.accessioned2017-01-30T15:21:49Z
dc.date.available2017-01-30T15:21:49Z
dc.date.created2015-05-22T08:32:23Z
dc.date.issued2014
dc.date.submitted2015-05-22
dc.identifier.citationXue, M. and Mian, A. and Liu, W. and Li, L. 2014. Fully automatic 3D facial expression recognition using local depth features, in IEEE Winter Conference on Applications of Computer Vision, Mar 24-26 2014, pp. 1096-1103. Steamboat Springs, CO, USA: Institute of Electrical and Electronics Engineers.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/45568
dc.identifier.doi10.1109/WACV.2014.6835736
dc.description.abstract

Facial expressions form a significant part of our nonverbal communications and understanding them is essential for effective human computer interaction. Due to the diversity of facial geometry and expressions, automatic expression recognition is a challenging task. This paper deals with the problem of person-independent facial expression recognition from a single 3D scan. We consider only the 3D shape because facial expressions are mostly encoded in facial geometry deformations rather than textures. Unlike the majority of existing works, our method is fully automatic including the detection of landmarks. We detect the four eye corners and nose tip in real time on the depth image and its gradients using Haar-like features and AdaBoost classifier. From these five points, another 25 heuristic points are defined to extract local depth features for representing facial expressions. The depth features are projected to a lower dimensional linear subspace where feature selection is performed by maximizing their relevance and minimizing their redundancy. The selected features are then used to train a multi-class SVM for the final classification. Experiments on the benchmark BU-3DFE database show that the proposed method outperforms existing automatic techniques, and is comparable even to the approaches using manual landmarks.

dc.publisherInstitute of Electrical and Electronics Engineers
dc.subjectThree-dimensional displays
dc.subjectfeature selection
dc.subjectlearning (artificial intelligence)
dc.subjectfeature extraction
dc.subjectFace recognition
dc.subjectVectors
dc.subjecthuman computer interaction
dc.subjectFeature extraction
dc.subjectsupport vector machines
dc.subjectface recognition
dc.subjectNose
dc.subjectHaar transforms
dc.subjectMouth
dc.subjectimage classification
dc.titleFully automatic 3D facial expression recognition using local depth features
dc.typeConference Paper
dcterms.dateSubmitted2015-05-22
dcterms.source.startPage1096
dcterms.source.endPage1103
dcterms.source.title2014 IEEE Winter Conference on Applications of Computer Vision (WACV),
dcterms.source.series2014 IEEE Winter Conference on Applications of Computer Vision (WACV),
dcterms.source.conferenceWACV 2014: IEEE Winter Conference on Applications of Computer Vision
dcterms.source.conferencedatesMar 24 2014
dcterms.source.conferencelocationSteamboat Springs, CO, USA
dcterms.source.place445 Hoes Ln, Piscataway, NJ 08855 United States
curtin.digitool.pid226579
curtin.pubStatusPublished
curtin.refereedTRUE
curtin.departmentDepartment of Computing
curtin.identifier.scriptidPUB-SE-DOC-PH-87161
curtin.accessStatusFulltext not available


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record