A HYBRID APPROACH FOR DEEP LEARNING BASED FINGER VEIN BIOMETRICS TEMPLATE SECURITY
Shendre Shivam, Shubhangi Sapkal · Известия Южного федерального университета. Технические науки · 2020
We are living in the today’s society, where we have fairly-enough storage capacity and processingpower, the only issue is with security. As, the technologies are evolving with faster rate, weare tend to grow the use of electronic devices rapidly in todays’ society, it started to flow or leakageof personal information around/across, which then leads to breach of this information. Now,personal or identical verification is key problem is being crucial. So whatever traditional methodswe have for providing authentication or security those have proven inadequate to be unreliableand do not provide strong security. Biometric template protection is one of the most importantissues in securing today’s biometric system. We have many algorithms which don’t give adequatesolution for the same. So we tried to give a method which will reach to the expectations more satisfactorilyand certainly to the extent required. In this paper we have discussed a hybrid method forfinger vein biometric recognition based on deep learning approach using BDD and fuzzy commitmentschemes. The proposed hybrid method consists of four parts, namely Finger vein featureextraction, BDD-based secure template generation, Fuzzy commitment scheme and ML basedfinger vein recognition and decision making. Thus it has four module and each module works efficientlyand gives accurate results on all databases.