Biometric-based authentication system

The future work in wearable body sensor networks will be in several directions (1) provide an accurate and low-cost biometrics-based multiple model selection method to select best biometric features and modes for data authentication (2) develop a key agreement scheme that uses multiple collected dynamic biometric features as a key and share it among communication partners with low communication and computational cost (3) develop a biometric-based authentication system for textile-based body sensor networks under the low-cost key agreement scheme. 

However, all the above research studies have focused on secret key distribution issues, while the specific and unique challenge in biometric authentication, ie, how to merge the payload with the biometric information while preserving the statistical uniqueness of the biometric information, has not been addressed. Furthermore, all the above-mentioned biometric-based key-exchange schemes need critical time synchronization because they need to record biometric information simultaneously at different positions of the same human body, which incurs considerable extra communication overhead in extremely resource-constrained wearable body sensor networks. In addition, one of the biometric features may not be unique and accidental faulted measures (eg, due to hardware or software failures) may malfunction the traditional biometric-based security system. 

A palmprint-based biometric authentication system has been developed. Three feature types are experimented on the palmprints for the suitability and usefulness of the palmprint-based authentication. Of these the sigmoid features are found to be... 

---