2.4. Face databases

Up to date, databases containing many faces have been created employing cameras and some of them contain colour images and even videos. Their main purpose has been to provide material to test and develop face recognition and detection algorithms. If the illumination changes are taken into consideration in these images, it is typically caused by variation in illumination direction, camera viewpoint or different white balancing light sources. Table 1 summarizes the properties of face databases some of which can be even downloaded from the WWW (see links at http://www.ee.oulu.fi/research/imag/color/). Also Yang and Ahuja (2001) and Gong et al. (2000) provide information on some of these databases. The physical basis of image formation data like camera responses are not considered with these databases and in some cases not even the type of the camera is mentioned. The illumination conditions are not reported and in some cases illumination changes are in fact caused by changes in illumination direction. Some databases do contain videos, for example from TV, but they are not taken in real, drastic conditions.

Table 1. Face databases.

Face database Number of personsImagesVariablesOther data related to face
MIT (Turk & Pentland 1991)16 men27 images per person grey images1. illumination direction 2. head tilt (orientation) 3. scalea video sequence of person moving behind a plant
Shimon Edelman"s 28 personsminimum: 60 images per person grey images1. horizontal illumination level 2. viewpoint 3. face expressions (3) 
CMU test images for face detection3 datasets; 2 test sets not mentionedgrey images1. frontal and profile views 2. different backgroundsground truths
University of Stirlingnot mentioned1591 colour and grey images1. illumination (not defined) 2. expression 3. different views and poses 
M2VTS (Pigeon & Vandendrope 1997)37 and 295185 and 295colour images1. rotation 2. expressions 3. glasses on / offfour video sequences per person (295, head rotation under controlled lighting) and speech data
Yale (Belhumeur et al. 1997, Georghiades et al. 2001)two databases, 15 and 10165 grey images and 5850 grey images1. facial expressions 2. glasses on / off 3. lighting direction and level 
UMIST (Graham & Allinson 1998)together 20 men and women564grey images1. different poses from profile to frontal view 
Purdue AR University (Martinez & Benavente 1998) 126, 70 men and 56 womenover 4000 colour images frontal view 1. facial expressions 2. occlusions 3. illumination: some images with different direction of yellowish light 
Goudail et al. (1996)11611600 frontal, grey images1. posetwo 30 s moving head videos
AT & T (Olivetti) (Samaria & Harter 1994)40400 grey images1. time 2. lighting level 3. facial expressions 4. glasses on / off 
University of Bern30450 grey images1. head position 2. size 3. contrast 
FERET (Phillips et al. 2000)not mentioned14051 grey images1. different poses from profiles to frontal view 2. different lighting level 3. facial expressionsground truths
Kodak data set (Loui et al. 1998)not mentionedcolour1. size 2. pose 3. illumination between images (near white balanced ones)videos (no big skin tone changes)
The Japanese Female Facial Expression (JAFFE) Database10 women213 grey images1. facial expressionsemotion ratings
PEIPA (Pilot European Image Processing Archive)two datasetsover 750 colour and grey1. pose 2. contrast 
Harvard (Hallinan 1995)10not mentioned grey1. illumination direction 
Usenix face datasetnot mentioned55921. variable viewing conditions 
NISTS Special Database 18 (Mugshot Identification Database)1573: 1495 men and 78 women3248 grey images1. poses: frontal and profile 2. size