A new method of image recognition based on deep learning generates adversarial networks and integrates traditional algorithms

This paper discusses an innovative image recognition method, which combines the advanced feature learning ability of generative adversarial networks (Gan) with the robustness of traditional image recognition algorithms. Based on small-sample training, Gan can generate high-quality image samples to expand the training set. Therefore, by designing and training a generative adversarial network, the real image data and its labels can be integrated into the training set. The GAN-generated images, together with corresponding labels, are input into SVM for training, and appropriate kernel functions and parameters are selected to optimize the SVM model to maximize classification performance. GAN is good at data generation and feature learning, while SVM is good at problems with clear classification boundaries, and this model combining the two methods is used in image recognition.