Small sample image classification method based on support vector machine and convolutional neural network

The invention discloses a small sample image classification method based on a support vector machine and a convolutional neural network. The method comprises the following steps: training a support vector machine SVM by using a training set in a small number of labeled picture samples, and labeling a large number of unlabeled image samples by using the trained support vector machine SVM to form pseudo labels; and combining a training set in a small number of image samples with labels with the image samples with pseudo labels to form an enhanced training set ATS. According to the method, a convolutional neural network model is trained through an enhanced training set, knowledge migration from a support vector machine (SVM) to the convolutional neural network is realized, and finally, the image classification accuracy of the migrated convolutional neural network is verified by using a verification set in a small number of labeled samples. Due to the fact that the support vector machine can only process a small