Publication

Abstract : Feature transformation is the most primary step in biometric template protection whose effectiveness is directly dependent upon the test and trained samples. The minutiae points are segregated to retrieve the attributes with the singular point data to enlarge the secure user template. The user fingerprint information could be revealed to produce the secured template with the help of the fingerprint image. An attempt of feature transformation is experimented in this paper by DNA based encoding methodology. The general formation of the proposed technique is constructed from the Biometric data to generate the feature extraction; the Z pattern generation is used for implementing the transformation and produced the DNA codec. The evaluation of each step in the proposed scheme is theoretically evaluated and experimented with. The revocability, diversity and the security parameters are analyzed and compared with the relevant methods using the images from FVC2004 dataset that the accuracy for biometric template is achieved through the enhanced recognition rate. The complexity and the performance of the proposed method proved challenging to the state of art techniques.