Blood cell identification and counting are essential nowadays for healthcare professionals and therapists treating a variety of diseases. Platelet detection and counting are commonly performed for various disorders such as COVID-19 and others. However, it is the most costly and time-consuming. Furthermore, it is not available everywhere. From that standpoint, it is necessary to develop an effective technological model for detecting and counting three fundamental kinds of blood cells: Platelets, Red Blood Cells (RBCs), and White Blood Cells (WBCs). So, a deep learning-based model is proposed in this study comparing two versions of YOLOv5 model such as YOLOv5s and YOLOv5m. It is found that the YOLOv5m model outperforms with 0.799 precision, where YOLOv5s produces 0.797 precision. The study suggests that the YOLOv5m model is highly capable of detecting and counting the blood cells individually. Doctors, physicians, and other clinicians will be capable to identify and quantify blood cells from real-time photos. It will save money and time by identifying and counting blood cells using real-time blood photos.