SMARTBLOOD: AUTOMATED BLOOD GROUP DETECTION USING HYBRID IMAGE AND FINGERPRINT ANALYSIS

Abstract

Blood group identification plays a vital role in medical diagnosis, transfusion compatibility, and emergency healthcare. Conventional blood testing methods are time-consuming, invasive, and require laboratory support. This study proposes SmartBlood, an innovative framework that integrates image processing and fingerprint analysis to automate blood group detection with high accuracy and minimal human intervention. The system captures a microscopic image of the blood sample and a fingerprint image to analyze inherent biometric patterns correlated with blood characteristics. Advanced machine learning and deep image processing algorithms are utilized to extract, preprocess, and classify the features for identifying ABO and Rh blood groups. The proposed model aims to achieve real-time results with reduced cost, enhanced reliability, and an efficient non-invasive approach for healthcare systems, blood donation centers, and emergency response units.