Blood Group Prediction Using Fingerprint Through Deep Learning

Abstract

Accurate blood group identification is extremely important in healthcare. It is needed for blood transfusions, emergency treatments, organ transplants and many routine medical procedures. However, the traditional method of testing blood is still invasive, slow and dependent on laboratory facilities, and it can sometimes lead to errors. BloodPrint offers a non-invasive alternative by using deep learning to predict a person’s blood group from their fingerprint. The system uses Convolutional Neural Networks to study fingerprint ridge patterns and match them to ABO and Rh blood groups. With its carefully designed process that includes image preprocessing, ridge enhancement and data augmentation, BloodPrint provides a fast, accessible and affordable way to identify blood groups. This makes it especially helpful in emergencies, rural areas and places with limited medical resources. The experimental results show strong accuracy across all eight blood groups, proving that fingerprints can be a reliable indicator. By combining biometric information with modern artificial intelligence, BloodPrint introduces a practical, contactless and scalable method that can improve how healthcare diagnostics are delivered in the future.