Expression-invariant representations of faces

Addressed here is the problem of constructing and analyzing expression-invariant representations of human faces. We demonstrate and justify experimentally a simple geometric model that allows to describe facial expressions as isometric deformations of the facial surface. The main step in the constru...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 16(2007), 1 vom: 29. Jan., Seite 188-97
Auteur principal: Bronstein, Alexander M (Auteur)
Autres auteurs: Bronstein, Michael M, Kimmel, Ron
Format: Article
Langue:English
Publié: 2007
Accès à la collection:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Sujets:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM168258501
003 DE-627
005 20250208003346.0
007 tu
008 231223s2007 xx ||||| 00| ||eng c
028 5 2 |a pubmed25n0561.xml 
035 |a (DE-627)NLM168258501 
035 |a (NLM)17283777 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Bronstein, Alexander M  |e verfasserin  |4 aut 
245 1 0 |a Expression-invariant representations of faces 
264 1 |c 2007 
336 |a Text  |b txt  |2 rdacontent 
337 |a ohne Hilfsmittel zu benutzen  |b n  |2 rdamedia 
338 |a Band  |b nc  |2 rdacarrier 
500 |a Date Completed 28.02.2007 
500 |a Date Revised 26.10.2019 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a Addressed here is the problem of constructing and analyzing expression-invariant representations of human faces. We demonstrate and justify experimentally a simple geometric model that allows to describe facial expressions as isometric deformations of the facial surface. The main step in the construction of expression-invariant representation of a face involves embedding of the facial intrinsic geometric structure into some low-dimensional space. We study the influence of the embedding space geometry and dimensionality choice on the representation accuracy and argue that compared to its Euclidean counterpart, spherical embedding leads to notably smaller metric distortions. We experimentally support our claim showing that a smaller embedding error leads to better recognition 
650 4 |a Journal Article 
700 1 |a Bronstein, Michael M  |e verfasserin  |4 aut 
700 1 |a Kimmel, Ron  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 16(2007), 1 vom: 29. Jan., Seite 188-97  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnas 
773 1 8 |g volume:16  |g year:2007  |g number:1  |g day:29  |g month:01  |g pages:188-97 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 16  |j 2007  |e 1  |b 29  |c 01  |h 188-97