Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/184852
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.coverage.spatial | ||
dc.date.accessioned | 2017-12-27T10:11:19Z | - |
dc.date.available | 2017-12-27T10:11:19Z | - |
dc.identifier.uri | http://hdl.handle.net/10603/184852 | - |
dc.description.abstract | Facial expressions are the most effective way of non-verbal communication. Facial expressions newlinegive clues about the emotional state, pain, alertness, personality, social interaction newlineand physiological signals. Automatic facial expression analysis confronts a series newlineof challenges because the expressions are generally mixed and highly dependent on the newlinesubject. newlineThe major steps of facial expression analysis include face detection, facial feature extraction, newlinenormalization of features (so that they are invariant to pose, illumination and newlinesubject), discriminative mapping of the features and efficient classification. The requirement newlineof real time applications further adds stringent constraints on the efficiency of these newlinetasks. The researchers from the field of computer vision and machine learning are working newlineon automatic facial expression analysis for intelligent environments and multimodal newlinehuman-computer interaction. Facial expression analysis has much research to do because newlineof its potential uses and inherent challenges. The challenges addressed in the proposed newlinework include extraction of facial features, their mapping to high discriminative space, newlineemotion synthesis, handling multiple facial feature descriptors and Action Unit intensity newlinedetection. newlineThe lip features are investigated for prototypic facial expressions analysis to contribute newlineto the argument that facial components instead of holistic facial features can be used for newlinefacial expression analysis. newlineThe feature extraction methods need extraction of facial feature deformation from newlineneutral state caused due to different states of mind. Thin Plate Spline (TPS), which was newlinepreviously adopted for image registration, provides an effective solution for measuring newlinerigid and non-rigid transformation between the source and target image. This property of newlineTPS is explored in the presented work for computing deformation of facial features due newlineto different expressions. The deformations so computed are used for emotion recognition newlineand emotion synthesis. The computation of deformation ... | |
dc.format.extent | ||
dc.language | English | |
dc.relation | ||
dc.rights | university | |
dc.title | Video Analysis of Human Facial Expressions for Human Computer Interaction using Artificial Intelligence | |
dc.title.alternative | ||
dc.creator.researcher | Neeru Rathee | |
dc.description.note | ||
dc.contributor.guide | Dinesh Ganotra | |
dc.publisher.place | Delhi | |
dc.publisher.university | Guru Gobind Singh Indraprastha University | |
dc.publisher.institution | University School of Information and Communication Technology | |
dc.date.registered | 2010 | |
dc.date.completed | 2016 | |
dc.date.awarded | 10/03/2017 | |
dc.format.dimensions | ||
dc.format.accompanyingmaterial | CD | |
dc.source.university | University | |
dc.type.degree | Ph.D. | |
Appears in Departments: | University School of Information and Communication Technology |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
neeru ratheeusict2010.pdf | Attached File | 5.83 MB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: