基于YOLOV5的外周血白细胞检测

Detection of Peripheral Blood Leukocytes Based on YOLOV5

针对显微镜拍摄的血涂片白细胞图像中存在大量细小的细胞,计数工作中存在漏检及速度慢的问题,本文从深度学习的角度研究相关技术难点,结合卫星遥感目标检测方法,提出一种基于YOLOV5的外周血白细胞检测的高效快速检测方法。相较于传统算法和通用的目标检测算法,本算法具有更好的检测能力。实验证明,该方法可以较好地解决血涂片图像计数中的一系列问题,检测效果良好。

In view of the large number of small cells in the leukocyte image of blood smear taken by micro-scope, there are problems of missed detection and slow speed in counting. This paper studies the related technical difficulties from the perspective of deep learning. Combined with the satellite remote sensing target detection method, we propose an efficient and fast detection method based on deep learning. Compared with traditional algorithms and general target detection algorithms, it has better detection ability. Practice shows that this method can better solve a series of problems in blood smear image counting, and achieve a good detection effect.