Published Paper Details:

Blood group identification plays a pivotal role in critical medical applications such as blood transfusions, organ transplantation, and trauma care. Conventional methods for determining blood type involve invasive procedures, specialized reagents, and trained personnel--factors that often hinder immediate response in emergencies and limit access in remote or under-resourced environments. This project introduces an innovative, non-invasive method for blood group detection using fingerprint image processing. By leveraging the uniqueness of fingerprint biometrics and the capabilities of modern machine learning techniques, particularly Convolutional Neural Networks (CNNs), the system aims to classify blood groups (A+, A-, B+, B-, AB+, AB-, O+, O-) solely based on fingerprint patterns. This project aims to develop an automated blood group detection system using image processing and fingerprint analysis to provide a non-invasive and rapid approach. The proposed system integrates computer vision techniques using algorithms and AI to interpret images encompassing tasks like image classification, often leveraging deep learning models like Convolutional Neural Networks (CNNs) and biometric analysis to determine an individual's blood group.