Enhanced Blood Group Prediction with Fingerprint Images using Deep Learning

Blood group identification plays an essential role in medical diagnosis and emergency treatment. Traditionally, it is performed through serological testing, which requires drawing blood samples and relying on laboratory equipment and trained personnel. Although these methods provide high accuracy, they are invasive, take time, and may not be feasible in urgent situations or locations with limited medical resources. This study investigates an alternative technique for determining blood groups using fingerprint images by leveraging deep learning models, particularly Convolutional Neural Networks (CNNs) with efficient architectures. By examining the distinct ridge patterns present in a fingerprint, these models have the potential to deliver a non-invasive, quicker, and more accessible solution compared to conventional procedures. The research focuses on evaluating the practicality of this method and highlights how deep learning can be applied to predict blood groups using biometric data.