Instant Fingerprint Recognition Using Optimized Machine Learning Models by Corona Virus Optimization Algorithm

Fingerprint recognition has become an invaluable and rapidly advancing technology that plays a crucial role in various daily applications. From identity authentications to justice systems, mobile payment, and even access control and security measures. Despite the remarkable progress, fingerprint recognition is still a dynamic research field and confronts several challenges. One of the main challenges is the high variability in fingerprint images due to factors like fingerprint aging, central rotation, obliteration, z-cut, occlusion, orientation, and fingerprint device noises. Additionally, the computational complexity and the time concerns surrounding fingerprint recognition systems have raised considerations that need to be addressed. This study presents a brand-new, very quick, and extremely accurate fingerprint identification system built on a sophisticated, bio-inspired coronavirus optimization algorithm. Through hyperparameter tuning of machine learning algorithms and the use of Enhancement of the Coronavirus method, the principal objective of the suggested configuration is to choose and optimize the best characteristics of fingerprint photos and improve the accuracy of recognition. Six machine learning algorithms are utilized, and the proposed system has been evaluated on three datasets (i.e., NIST, CASIA Fingerprint 5.0, SOCOfing). The suggested system provides excellent recognition accuracy with little computing effort and complexity in uncontrolled contexts, with an average accuracy of 99% in 1.03 ms, as demonstrated by the comparison of experimental findings with current approaches, and time, respectively.