The goal of the Honda/UCSD Video Database is to provide a standard video database for evaluting face tracking/recognition algorithms. Since we believe that pose variation provides the greatest challenge to recognition, all the video sequences contain significant 2-D (in-plane) and 3-D (out-of-plane) head rotations. In each video, the person rotates and turns his/her head in his/her own preferred order and speed, and typically in about 15 seconds, the individual is able to provide a wide range of different poses. In addition, some of these sequences contain difficult events which a real-world tracker/recognizer would likely encounter, such as partial occlusion, face partly leaving the field of view, and large scale changes, etc.

Go to the Honda/UCSD Video Database.

The goal of this work was to derive an algorithm that could be used to reconstruct the 3D geometry of a rigid scene composed of a number of straight line features using the measurements obtained from a set of calibrated cameras at unknown positions. The algorithm we have implemented recovers the positions of the features and the positions of the cameras up to a scale factor.

This package contains two files, SFM.tar.Z and DATA.tar.Z.

SFM.tar.Z (90KB) is a compressed tar file containing the code that was used to implement the 3D structure from motion algorithm described in "Structure and Motion from Line Segments in Multiple Images" (500KB). by Camillo J. Taylor and David J. Kriegman, Center for Systems Science Technical Report No. 9402b, January 1994.

DATA.tar (7.1MB of compressed images) is a tar file containing three data sets of real images and input files that were used to test this program.

Examples of the results of this algorithm.

Homotopy continuation is a numerical method for solving systems of n polynomial equations in n variables. It finds both real and complex roots of the system, and we have successfully used it to solve systems with up to 2000 roots for a diverse set of applications including geometric modelling, aspect graph construction, stable pose computation, etc. This is a distributed implementation that runs across a network of UNIX machines. A program invokes clients on remote UNIX workstations to solve subproblems. We have run this using Sparc Stations running Solaris and Sun UNIX, and SGI's running IRIX.

Version 1.0 of this package is contained in array-1.0.tar.Z (50KB).

The Yale Face Database (size 6.4MB) contains 165 grayscale images in GIF format of 15 individuals. There are 11 images per subject, one per different facial expression or configuration: center-light, w/glasses, happy, left-light, w/no glasses, normal, right-light, sad, sleepy, surprised, and wink.

Go to the Yale Face Database.

The Yale Face Database B contains 5760 single light source images of 10 subjects each seen under 576 viewing conditions (9 poses x 64 illumination conditions). For every subject in a particular pose, an image with ambient (background) illumination was also captured. Hence, the total number of images is in fact 5760+90=5850. The total size of the compressed database is about 1GB.

Go to the Yale Face Database B.