An efficient Minkowski distance-based matching with Merkle hash tree authentication for biometric recognition in cloud computing

Biometric recognition recognizes an identification of an individual which can be obtained with the biological characteristics such as fingerprint, iris, and voice. The challenge of biometric recognition is the matching of fingerprint database with some sort of similarity distance methods. In this paper, Minkowski distance-based matching with Merkle hash tree authentication approach is proposed to overcome the above-mentioned challenges. Merkle hash tree-based encryption algorithm is introduced to improve the privacy concerns, usability and memory durability of the proposed system. This strategy handles security concerns via feature extracted data hashing with the private key. Minutiae feature extraction procedure adequately removes edge-detected features from the sensed data. Notwithstanding the security improvement, the proposed methodology stores just the produced keys for lessening memory stockpiling of cloud framework. Thus, authentication enhancement improves the entire security considerations through the proposed Minkowski distance-based authentication methodology. Finally, to demonstrate the practicality of the scheme, we evaluate the proposed scheme using the MATLAB simulator. A fingerprint dataset named as NIST Special Database 4 (NIST-4) is used for experimental evaluation. The proposed recognition system has achieved superior accuracy of 100% compared to the existing approaches.