Research and Application of a Graphical User Interface System for Peripheral Blood Cell Detection and Identification Based on Deep Learning Model YOLOv5

With the advancements in machine learning and deep learning technologies, significant breakthroughs have been achieved in the field of target recognition. This paper aims to research and apply a graphical user interface (GUI) system for blood cell detection and identification based on the deep learning model YOLOv5. The system enhances the accuracy of blood cell detection and identification by medical professionals, thereby improving diagnostic efficiency. This study mainly encompasses the collection and preprocessing of a blood cell image dataset, the training and optimization of the YOLOv5 model, and the design and development of the GUI system. Firstly, a substantial dataset of blood cell images is collected and subjected to preprocessing steps such as data cleaning and image augmentation to improve the robustness and accuracy of the training model. Secondly, the YOLOv5 model, based on deep learning target recognition, is applied for the detection and identification of blood cells. Then, the model is trained and optimized to enhance the accuracy of blood cell detection and identification. Lastly, a GUI system featuring a user-friendly interface and interaction is designed and developed. The trained model is then applied to real-world tasks of blood cell detection and identification, enabling medical professionals to conveniently use and operate the system, thereby improving work efficiency. Experimental results indicate that the GUI system for blood cell detection and identification, based on the deep learning model YOLOv5, can accurately detect and identify blood cells. This holds significant implications for blood analysis and related disease diagnosis in the medical field.