Biometric Authendication Using Brain Signatures

This paper proposes an algorithm to recognize EEG brain signatures of individuals for biometric authentication. Research on brain signals show that each individual has unique brain wave patterns. Electroencephalography signals of biometric tasks are acquired to extract the distinctive brain signature of an individual. Electroencephalography signals recorded during four biometric tasks, such as relax, read, spell and math activity were acquired from twenty five healthy subjects. The proposed algorithm for recognition of individuals uses power spectral density and neural networks. The performance of the existing algorithm was found to be 95% for spell task using single channel data. The performances of the proposed algorithm are appreciable with an accuracy of 98% for the spell task and 95% for the read task. Comparisons are also made using single channel and two channel data. Experimental results show that two channel acquisition process yields better recognition rates.