Blood group detection is an essential process in medical diagnostics, enabling safe blood transfusions, organ transplants, and pregnancy management. Traditional blood group testing methods involve drawing blood and perform laboratory-based serological tests, such as agglutination assays, to identify the presence of antigens on red blood cells. While these methods are reliable, they can be invasive, time-consuming, and require specialized equipment and trained personnel. These invasive methods also come with a huge cost associated with it.

With advancements in artificial intelligence and image processing, we are exploring non-invasive techniques to improve efficiency and accessibility in medical diagnostics. Fingerprint biometrics, widely used in security and identity verification, contain unique patterns that have been linked to genetic and physiological traits which has been proven in the some of the research done earlier. This has led to fingerprint patterns being correlated with blood group classification.

By leveraging deep learning techniques, particularly Convolutional Neural Networks (CNNs), this project aims to explore the feasibility of blood group detection through fingerprint analysis. This approach could revolutionize medical diagnostics by providing a rapid, non-invasive, and cost-effective alternative to traditional blood detection methods.