In order to realize the identification of corn disease images in complex field background for small data samples, a corneal disease image recognition model based on transfer learning was proposed. Based on the VGG-16 model, a new fully connected layer module was designed. The VGG-16 model was migrated to the model in the trained convolution layer of the ImageNet image data set. The collected corn disease image data set was divided into a training set and a test set according to a ratio of 3∶1. In order to expand the data set of the image, the original set of the training set was rotated, flipped, and the like. Based on the training set before and after the expansion, the two layers of the training model, the full connection layer and the training model, all the layers (convolution layer + full connection layer) were tested. The results showed that all the layers of the data expansion and training model can improve the recognition ability of the model. Under the condition of all the layers of the training model and the expansion of the training set data, the average recognition accuracy of the image of corn healthy leaves, large spot disease leaves and rust leaves was 95.33%. Compared with the new learning, transfer learning can significantly improve the convergence speed and recognition ability of the model. Finally, the trained model was developed into a visual user interface, which can realize the intelligent recognition of corn leaf spot and rust images in the complex background of the field.