Fusing face and ECG for personal identification

Abstract

Single modality biometric identification systems exhibit performance that may not be adequate for many security applications. Face and fingerprint modalities dominate the biometric verification/identification field. However, both face and fingerprint can be compromised using counterfeit credentials. Previous research has demonstrated the use of the electrocardiogram (ECG) as a novel biometric. This paper explores the fusion of a traditional face recognition technique with ECG. System performance with multimodality fusion can be superior to reliance on a single biometric, but performance depends heavily on the fusion technique. In addition, a fusion-based system is more difficult to defeat, since an imposter must provide counterfeit credentials for both face and cardiovascular function.