Identification of Human Blood Group Detection using Support Vector Machine and Image Processing

Abstract

Human survival depends on blood, particularly in situations where transfusions are required. It is vital to know one's blood group under these circumstances. In the past, blood samples were mixed with chemicals, and the agglutination process was observed under a microscope to manually determine blood types. Although this method works well, it can take a lot of time and is prone to human mistakes. In the current digital era, image-processing techniques have made blood group determination more effective thanks to technological improvements. Modern solutions such as image processing now provide fast, accurate, and dependable outcomes. Image processing systems can accurately classify blood types by examining photographs of blood samples.  In comparison to conventional methods, this approach allows for the precise identification of blood types in a shorter amount of time by processing datasets of blood samples and numerical data. A major change in medical diagnostics has occurred with the shift from manual to digital approaches, which increase accuracy and decrease mistake rates. Image processing is becoming the tool of choice for determining blood groups in medical settings as it advances. Automated systems are a useful tool in emergencies since they guarantee more accuracy and expedite processes. The support vector machine approach is employed in this study to identify and identify the various blood group kinds. The employed technique demonstrates a very high degree of blood group detection accuracy.