Concurrent self-organizing maps -a powerfuu artificial neural tool for biometric technology

We investigate the new artificial neural classification model called Concurrent Self-Organizing Maps (CSOM), representing a winner-takes-all collection or small SOM units. We evaluate two significant areas of CSOM applications in Biometric Technology face recognition and speaker recognition. For thc ORL face database of 40 subjects, we obtain a recognition score of 91% using CSOM, while with a single big SOM one yields a score of 71% only! For a speaker database provided by 25 talkers, we obtain 3 recognition score of 92.17% using CSOM, by comparison to SOM that lcads to thc recognition ratc of 79.63%!