|
INSTRUCTIONS FOR DOWNLOADING
SCfaceDB Landmarks
-
Download license agreement,
sign one copy, and send by email to atvs uam.es according to the instructions given in point 2.
-
Send an email to atvsuam.es, as follows:
Subject:
[DATABASE download: SCfaceDB Landmarks]
Body: Your name, e-mail, telephone
number, organization, postal mail, purpose for which you will use
the database, time and date at which you sent the email with the
signed license agreement.
-
Once the email copy of the license
agreement has been received at ATVS, you will receive an email with a
username, a password, and a time slot to download the database.
-
Download the database, for which you will need to provide the
authentication information given in step 3. After you finish the
download, please notify by email to atvsuam.es that you have
successfully completed the transaction.
-
For more information, please contact: atvsuam.es
DESCRIPTION OF SCfaceDB Landmarks
The database is comprised of 21 facial landmarks (from 4,160 face images) from 130 users annotated manually by a human operator, as described in [FSI2013].
The 21 facial landmarks are stored in .pos file. After loading each file, a matrix of dimensions 21 by 2 has the (x, y) coordinates of each facial landmark. See the figure on the right to check the given facial landmarks.
The nomenclature followed to identify the 21 facial landmarks is as follows:
ROW 1 = Top of the head ROW 2 = Right eyebrow right corner ROW 3 = Right eyebrow left corner ROW 4 = Left eyebrow right corner ROW 5 = Left eyebrow left corner ROW 6 = Right eye right corner ROW 7 = Right eye center of pupil ROW 8 = Right eye left corner ROW 9 = Left eye right corner ROW 10 = Left eye center of pupil ROW 11 = Left eye left corner ROW 12 = Nose right corner ROW 13 = Nose center bottom ROW 14 = Nose left corner ROW 15 = Mouth right corner ROW 16 = Mouth left corner ROW 17 = Chin corner ROW 18 = Right ear top corner ROW 19 = Right ear bottom corner ROW 20 = Left ear top corner ROW 21 = Left ear bottom corner
REFERENCES
For further information regarding the database, the different features approaches extracted from the data and the experimental work we refer the reader to:
Please remember to reference article [FSI2013] on any work made public, whatever the form, based directly or indirectly on any part of the SCfaceDB Landmarks.
|
