Difference between revisions of "Publications:Person verification by lip-motion"
From ISLAB/CAISR
(Created page with "<div style='display: none'> == Do not edit this section == </div> {{PublicationSetupTemplate|Author=Maycel-Isaac Faraj, Josef Bigun |PID=239668 |Name=Faraj, Maycel-Isaac [mafa...") |
|||
| Line 4: | Line 4: | ||
{{PublicationSetupTemplate|Author=Maycel-Isaac Faraj, Josef Bigun | {{PublicationSetupTemplate|Author=Maycel-Isaac Faraj, Josef Bigun | ||
|PID=239668 | |PID=239668 | ||
| − | |Name=Faraj, Maycel-Isaac | + | |Name=Faraj, Maycel-Isaac (mafa) (Högskolan i Halmstad (2804), Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE) (3905), Halmstad Embedded and Intelligent Systems Research (EIS) (3938));Bigun, Josef (josef) (Högskolan i Halmstad (2804), Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE) (3905), Halmstad Embedded and Intelligent Systems Research (EIS) (3938)) |
|Title=Person verification by lip-motion | |Title=Person verification by lip-motion | ||
|PublicationType=Conference Paper | |PublicationType=Conference Paper | ||
Latest revision as of 21:40, 30 September 2016
| Title | Person verification by lip-motion |
|---|---|
| Author | Maycel-Isaac Faraj and Josef Bigun |
| Year | 2006 |
| PublicationType | Conference Paper |
| Journal | |
| HostPublication | Conference on Computer Vision and Pattern Recognition Workshop : New York City, New York, 17-22 June, 2006 |
| Conference | Conference on Computer Vision and Pattern Recognition Workshop, New York City, New York, 17-22 June, 2006 |
| DOI | http://dx.doi.org/10.1109/CVPRW.2006.158 |
| Diva url | http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:239668 |
| Abstract | This paper describes a new motion based feature extraction technique for speaker recognition using orientation estimation in 2D manifolds. The motion is estimated by computing the components of the structure tensor from which normal flows are extracted. By projecting the 3D spatiotemporal data to 2-D planes we obtain projection coefficients which we use to evaluate the 3-D orientations of brightness patterns in TV like 2D image sequences. This corresponds to the solutions of simple matrix eigenvalue problems in 2D, affording increased computational efficiency. An implementation based on joint lip movements and speech is presented along with experiments which confirm the theory, exhibiting a recognition rate of 98% on the publicly available XM2VTS database. |
