Fingerprint-Based Pattern Recognition for Accurate ABO Blood Group Prediction

Abstract

Blood group identification plays a vital role in medical diagnosis, emergency care, and forensic applications. Traditional laboratory methods, while accurate, are often time-consuming and require biological samples. To address these challenges, this study proposes a novel approach for predicting ABO blood groups using fingerprint-based pattern recognition. Fingerprints are chosen due to their unique ridge structures and proven correlation with genetic traits, making them a reliable biometric source. A convolutional neural network (CNN) model is employed to automatically extract discriminative features from fingerprint images and classify them into the respective ABO blood groups. The proposed framework eliminates the need for invasive testing by leveraging a non-intrusive, cost-effective, and efficient biometric modality. Experimental evaluations demonstrate that the CNN model achieves high prediction accuracy, highlighting its potential in healthcare and forensic science as a complementary tool to conventional methods. This work contributes to the advancement of biometric-driven medical diagnostics by integrating deep learning with physiological pattern recognition.