Scopus Indexed Publications

Paper Details

DCBC_DeepL: Detection and Counting of Blood Cells Employing Deep Learning and YOLOv5 Model
Md. Abdur Rahaman, Md. Mamun Ali,

Blood cell identification and counting is critical for doctors and physicians nowadays in order to diagnose and treat a variety of disorders. Platelet identification and counting are frequently performed in the context of many types of sickness such as COVID-19 and others. However, it is frequently costly and time intensive. Additionally, it is not widely available. From this vantage point, it is necessary to develop an efficient technical model capable of detecting and counting three fundamental types of blood cells: platelets, red blood cells, and white blood cells. Thus, this study proposes a deep learning-based model based on the YOLOv5 model with a precision of 0.799. The model consists of thre different layers such as backbone, neck and output layer The model is extremely capable of detecting and counting individual blood cells. Doctors, physicians, and other professionals will be able to detect and count blood cells using real-time images. It will significantly minimise the cost and time associated with detecting and counting blood cells by utilizing real-time blood images.

Deep learning Platelets Red blood cell White blood cell YOLOv5
Journal or Conference Name
Communications in Computer and Information Science
Publication Year