Overview

The head pose database is a benchmark of 2790 monocular face images of 15 persons with variations of pan and tilt angles from -90 to +90 degrees. For every person, 2 series of 93 images (93 different poses) are available. The purpose of having 2 series per person is to be able to train and test algorithms on known and unknown faces (cf. sections 2 and 3). People in the database wear glasses or not and have various skin color. Background is willingly neutral and uncluttered in order to focus on face operations.

Data Collection

All images have been taken using the FAME Platform of the PRIMA Team in INRIA Rhone-Alpes. To obtain different poses, we have put markers in the whole room. Each marker corresponds to a 2D pose (pan, tilt). Post-it are used as markers. The whole set of post-it covers a half-sphere in front of the person.

In order to obtain the face centered on image, the person is asked to adjust the chair to see the device in front of him. The person stands at a distance of 2 meters from the camera. After this initialization phase, the person stares successively at 93 post-its, without moving his eyes. All images are obtained by using this method.

TopView

Top sight

SideView

Side sight

Fame

The FAME Platform

Data Annotation

The corresponding face labels are stored as rectangle coordinates in an individual text file of the corresponding name:

**person[Id][serie][Number][tilt][Pan].txt**

The text file contains the following elements: [*Corresponding Image File]*

Face [Face Center X] [Face Center Y] [Face Width] [*Face Height]*

Data Format

Filenames are constructed according the following grammar :

**person[Id][serie][Number][tilt][Pan].jpg**

Id = {01, ..., 15} Number of the person,
Serie = {1, 2} Number of the serie,
Number = {00, 01, ..., 92} Number of the file in the directory,
Tilt = {-90, -60, -30, -15, 0, +15, +30, +60, +90} Vertical angle,
Pan = {-90, -75, -60, -45, -30, -15, 0, +15, +30, +45, +60, +75, +90} Horizontal angle.

Each filename is unique. For example, take the file person08123-30+45.jpg :

Id = 08
Serie = 1
Number = 23
Tilt = -30
Pan = +45

	Negative values	Positive values
Pan Angle	Bottom	Top
Tilt Angle	Left	Right

In case the vertical angle is -90 or +90, the person is looking at the bottom or the top, and then the horizontal angle is 0. Each serie contains therefore 7 x 13 + 2 x 1 = 93 images.

Citation

This database can be used for any purpose, provided that the following article is cited:

@article{article,
author = {Gourier, Nicolas and Crowley, James},
year = {2004},
month = {01},
pages = {},
title = {Estimating Face orientation from Robust Detection of Salient Facial Structures},
journal = {FG Net Workshop on Visual Observation of Deictic Gestures}
}