Aiming at the low accuracy and efficiency of manual microscopic examination of white blood cell classification, based on deep learning and machine learning algorithms, a white blood cell classification method based on transfer learning and support vector machine is proposed. First, perform fine-tuning training on the transfer model, then use the fine-tuned training transfer model for feature extraction, then input the features into the neural network and support vector machine for training, and finally classify the white blood cells through the combined classifier of neural network and support vector machine. The experimental results show that the accuracy of white blood cell classification has increased from 83.26% of the initial fine-tuning training to 90.43% with the optimization of the transfer model, and finally increased to 93.52% through the combined classifier, which can help doctors improve the accuracy of diagnosis in clinical practice and efficiency.