Advance Biometric System for Blood Group Detection Using Novel Based Finger Print Patterns

Blood group detection is a non-invasive technique for determining blood groups using fingerprint patterns represents a novel approach in biometric and medical research. Now a days all are using traditional using blood samples for blood group detection methods require blood samples and laboratory procedures, which can be time-consuming and invasive. This paper proposed by a novel based finger print patterns it approaches that explores the correlation between fingerprint patterns and blood group sample. By employing machine learning techniques this study aims to establish a reliable and accurate model for predicting blood groups from fingerprint images. The proposed system has the potential it will provide a rapid, noninvasive, and accessible alternative for blood group detection, which could be particularly useful in emergency medical situations and remote healthcare applications. The intelligent based K- Nearest Neighbour KNN algorithm efficiently groups similar fingerprint features, while Multi-Dimensional support Vector Machine- MDSVM is adept at separating distinct blood m group classes in high-dimensional spaces. By combining these methods, we model the subtle correlations between fingerprint characteristics and blood group markers, resulting in an approach that is both straightforward and highly effective processing large datasets. With the proposed KNN and MDSVM algorithm, the accuracy level reached is 95.53 % compared to other proposed methods.