Published Paper Details:

The analysis of a patient's blood sample is a significant responsibility in the medical industry. Blood cell abnormalities create a variety of health issues. White blood cells are one of the most important components of blood. White blood cells are immune cells that fight infections caused by bacteria and viruses in the body. White blood cells can be classified to assist us in identifying various illnesses. Due to a variety of medical conditions, normal white blood cells might change in size, shape, and texture. The objective of this research is to enhance the number of detectable aberrant white blood cells via image processing. For categorization, this study employed various machine learning methods such as Random Forest, XgBoost, and Decision Tree. As a consequence, the algorithm recognised and classified four images of white blood cells. These photos were derived by the system from prior hospital patients. Furthermore, the slides are photographed. The image was then placed into the programme. The system processed and classified the image. In effect, the results indicate the identity of the aberrant white blood cells discovered in the system's image, as well as a soft copy of the checklist.