Highly secure palmprint based biometric template using fuzzy vault

摘要

Biometric cryptosystem is an integrated system of cryptographywith biometric featureswhich is considered to be a promising component of template security. This paper presents a novel method for biometric cryptosystem based on fuzzy vault using palmprint features. Initially, pre-processing is performed to remove noise in palmprint enrolled image and to pre-align image automatically. Bottom-hat filtering is employed for the feature extraction from the palmprint images. A polynomial is evaluated from the secret key and this polynomial is used to generate projections from palmprint features.Fuzzy vault is createdby combiningprojectedpointswith randomly generated dummyor chaff points.During decoding process, matching scores are calculatedby comparing the query feature and stored vault. The vault is successfully decodedwhen the matched scores should be greater than a predefined threshold value. Experiments were conducted on CASIA database. Simulation result demonstrates that the proposed method gives better performance than other methods and improves the robustness against some security attacks.