Robust facial expression recognition in the presence of rotation and partial occlusion

Simple item page
dc.contributor.advisorGhaziasgar, Mehrdad
dc.contributor.advisorConnan, James
dc.contributor.authorMushfieldt, Diego
dc.date.accessioned2014-06-18T14:09:09Z
dc.date.accessioned2024-10-30T14:00:51Z
dc.date.available2014-06-18T14:09:09Z
dc.date.available2024-10-30T14:00:51Z
dc.date.issued2014
dc.description>Magister Scientiae - MScen_US
dc.description.abstractThis research proposes an approach to recognizing facial expressions in the presence of rotations and partial occlusions of the face. The research is in the context of automatic machine translation of South African Sign Language (SASL) to English. The proposed method is able to accurately recognize frontal facial images at an average accuracy of 75%. It also achieves a high recognition accuracy of 70% for faces rotated to 60◦. It was also shown that the method is able to continue to recognize facial expressions even in the presence of full occlusions of the eyes, mouth and left/right sides of the face. The accuracy was as high as 70% for occlusion of some areas. An additional finding was that both the left and the right sides of the face are required for recognition. As an addition, the foundation was laid for a fully automatic facial expression recognition system that can accurately segment frontal or rotated faces in a video sequence.en_US
dc.identifier.urihttps://hdl.handle.net/10566/16968
dc.language.isoenen_US
dc.publisherUniversity of Western Capeen_US
dc.rights.holderUniversity of Western Capeen_US
dc.subjectBlenderen_US
dc.subjectFace detectionen_US
dc.subjectFacial expression recognitionen_US
dc.subjectHaar featuresen_US
dc.subjectLocal binary patternsen_US
dc.subjectMorphological operationsen_US
dc.subjectOcclusionen_US
dc.subjectRotationen_US
dc.subjectSkin detectionen_US
dc.subjectSupport vector machineen_US
dc.titleRobust facial expression recognition in the presence of rotation and partial occlusionen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Mushfieldt_MSC_2014.pdf
Size:
13.43 MB
Format:
Adobe Portable Document Format
Description:
Thesis
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.62 KB
Format:
Plain Text
Description:
Download

Collections

Magister Scientiae - MSc (Computer Science)