Red Blood Cells Classification Using Image Processing

The timely and accurate diagnosis of red blood cell (RBC) diseases is critical for effective treatment and management. Traditional diagnostic methods often involve costly procedures and prolonged report generation times, leading to delays in patient care. This study presents an automated RBC disease classification system leveraging image processing and machine learning techniques. The proposed system efficiently detects and classifies RBC abnormalities, such as Leukemia and Myeloma, using a structured approach involving preprocessing, segmentation, feature extraction, and classification. The methodology integrates MATLAB for image analysis and employs the K-Nearest Neighbors (KNN) algorithm for classification. The system is designed to reduce diagnostic time, improve accuracy, and make disease detection more accessible. Experimental results indicate that the automated approach enhances efficiency while minimizing costs, thereby offering a promising solution for rapid blood disease identification.