DOI: 10.36347/sjet.2023.v11i03.003

Pages: 34-38

There are various types of leukocytes in blood cells, and various types of leukocytes play an important role in fighting fungal, bacterial, viral and other infections in the human body, so studying and classifying leukocyte types is an important task for medical researchers. Based on the low efficiency and accuracy of traditional methods for detecting leukocytes, an efficient processing of leukocyte images using convolutional neural networks is proposed, which can perform tasks such as classification and localization of leukocytes. The proposed method and previous detection networks were also compared in experiments, and the experimental results proved that the proposed Yolov5 convolutional neural network has the highest detection speed and accuracy, with mAP reaching 86.47%.