Automatic Teller Machines from Siemens Nixdorf with automatic user
identification by means of physical characteristics instead of PIN number

PADERBORN. SIEMENS NIXDORF HAS DEVELOPED AN AUTOMATIC TELLER MACHINE THAT
IDENTIFIES USERS BY THEIR FACES. A PROCASH ATM HAS BEEN INTRODUCED THAT
AUTHENTICATES USERS BY THEIR PHYSICAL FEATURES AND CHECKS WHETHER THEY ARE
AUTHORIZED TO WITHDRAW CASH. THE NEW IDENTIFICATION SYSTEM IS BASED ON
NEURAL NETWORKS AND REPLACES CONVENTIONAL ENTRY OF A PIN NUMBER. IT IS
SIMPLER TO USE THAN EXISTING ACCESS CONTROL METHODS AND CONSIDERABLY MORE
SECURE, RELIABLY ELIMINATING CARD MISUSE. IT IS SUITABLE FOR INSTALLATION
IN EQUIPMENT OF THE CSC/430 AND CSC/450 SYSTEM FAMILIES.

January 22, 1996 -- Identification of ATM users by means of facial
recognition is based on the fact that human beings have unique
physiological features that remain unchanged throughout their lives. This
system is a joint development of Siemens Nixdorf, Maku Informationstechnik
GmbH, Essen, and the Zentrum fuer Neuroinformatik Gesellschaft fuer
intelligente Informationsverarbeitung (ZN) GmbH - the Center for
Neuroinformatics, Society for Intelligent Information Processing - in
Bocum.

When the user inserts his or her chipcard, a camera integrated in the ATM
automatically takes a photograph of the user's face and compares facial
features with the reference image stored on the card. The read device
automatically deletes the verification data when the card holder withdraws
cash. It stores the image of the user only if illegal access is attempted.
This enables the transaction to be reconstructed and the image may also
serve as legal evidence.

According to Dr. Wolfgang Kronen, head of neural personal identification
systems at ZN, real-world use is now possible as efforts to "compress the
biometric features required for identification purposes to a few hundred
bytes" have proved successful.

The rejection quota for authorized users is less than 0.5 % (5 per
thousand). The identification method underlying this system recently
emerged as winner of a competition sponsored by the US government. In
particular, the functional stability and reliability of the facial
recognition system were critically appraised.

Siemens Nixdorf Informationssysteme AG
Angelika B"ttcher, Siemens Nixdorf, Press Office
Tel.: (+49) 89 / 6 36 - 5 32 04

Uwe Krause, Siemens Nixdorf, LoB SB
Tel.: (+49) 52 52 / 82 80 10
 
 =========================================================
 From the 'New Product News' Electronic News Service on...
 AOL (Keyword = New Products) and Delphi (GO COMP PROD)
 =========================================================
 This information was processed from data provided by the
 company/author mentioned. For additional details, please
 contact them directly at the address/phone# indicated.
 Trademarks are the property of their respective owners!
 =========================================================
 All submissions for this service should be addressed to:
 BAKER ENTERPRISES,  20 Ferro Dr,  Sewell, NJ  08080  USA
 Email:   rbakerpc@delphi.com   --or--   rbakerpc@aol.com
 =========================================================
