Knowledge Base

Home  Search   Show all  Top

Details of the record

titleGavabDB: a 3D Face Database
authorsA. B. Moreno, A. Sanchez
keywordsGavabDB, Gavab, FERET, Yale, database, AR, MIT, ORL, CVL, PF01, XM2VTS, 3D_RMA,
abstractA 3D face image database (GavabDB) has been built for
automatic face recognition experiments and other possible
image applications such as pose correction and 3D face model
registration. This paper presents the database features and also
explains the process of building the database in detail.
Additionally, our motivation for creating this database, the
image acquisition process, the image properties and a
discussion about them, as well as some conclusions extracted
from the database creation are presented. GavabDB contains
427 three-dimensional facial surface images corresponding to
61 individuals (45 male and 16 female), and there are 7
different images per each person. The whole set of individuals
are Caucasian and most of them are aged between 18 y 40.
Each image consists in a three-dimensional mesh representing
a face surface. There are systematic variations over the pose
and facial expression of each person. In particular, there are 2
frontal and 4 rotated images without any facial expressions,
and 3 frontal images in which the subject presents different
and accentuated facial expressions. The purpose of this
publication is to present this database such that other
researchers in this field can use it for related facial
published year
(Total records:1429)
Home  Search   Show all  Top

Powered by: DaDaBIK