Asymmetric Encryption Techniques for Data Embedding and Authentication in Fingerprints Using Eigen Space Based Modelling

Abstract

“This report introduces a novel fingerprint classification technique based on a multi-layered fuzzy logic classifier. We target the cause of missed detection by identifying the fingerprints at an early stage among dry, standard, and wet. Scanned images are classified based on clarity correlated with the proposed feature points. We also propose a novel adaptive algorithm based on eigenvector space for generating new samples to overcome the multiclass imbalance. Proposed methods improve the performance of ensemble learners. Early-stage improvements give a suitable dataset for fingerprint detection models. Leveraging the novel classifier, the best set of `standard' labeled fingerprints is used to generate a unique hybrid fingerprint orientation map (HFOM). We introduce a novel min-rotate max-flow optimization method inspired by the min-cut max-flow algorithm. Finally, HFOM is used along with a proposed asymmetric cryptographic method for secure data embedding. Focusing on the integrity aspect of confidentiality, integrity, and availability (CIA) tried in cybersecurity, the secured information is validated for authenticity before decryption using HFOM. We make the code publicly available for further research.”

During over 1 year of working period, I learnt many new things at the IVC Lab, DUK.