This is the home page for the XM2VTSDB multi-modal face database project.  In this project a large multi-modal database was captured onto high quality digital video. The XM2VTSDB contains four recordings of 295 subjects taken over a period of four months. Each recording contains a speaking head shot and a rotating head shot. Sets of data taken from this database are available including high quality colour images, 32 KHz 16-bit sound files, video sequences and a 3d Model. For more information about the database and how to order it follow the links at the side of this page.

The database was aquired within the M2VTS project (Multi Modal Verification for Teleservices and Security applications), a part of the EU ACTS programme, which deals with access control by the use of multimodal identification of human faces. The goal of using a multimodal recognition scheme is to improve the recognition efficiency by combining single modalities, namely face and voice features.

The XM2VTSDB is being made available at cost price only - no benefits are expected from the distribution - we ask the end users to acknowledge the M2VTS project whenever this database is used (see the user agreement).


Any comments or general enquiries please contact: Dr Chi Ho Chan (Chiho.Chan@surrey.ac.uk)