A High-Quality Rice Leaf Disease Image Data Augmentation Method Based on a Dual GAN

Deep learning models need sufficient training samples to support them in the training process; otherwise, overfitting occurs, resulting in model failure. However, in the field of smart agriculture, there are common problems, such as difficulty in obtaining high-quality disease samples and high cost. To solve this problem, this paper proposed a high-quality image augmentation (HQIA) method for generating high-quality rice leaf disease images based on a dual generative adversarial network (GAN). First, the original samples were used to train Improved Training of Wasserstein GANs (WGAN-GP) to generate pseudo-data samples. The pseudo-data samples were put into the Optimized-Real-ESRGAN (Opt-Real-ESRGAN) to generate high-quality pseudo-data samples. Finally, the high-quality pseudo-data samples were put into the disease classification convolutional neural network, and the effectiveness of the method was verified by indicators. Experimental results showed that this method can generate high-quality rice leaf disease images, and the recognition accuracy of high-quality rice disease image samples augmented by this method was 4.57% higher than that of using only the original training set on ResNet18 and 4.1% higher on VGG11. Compared with the data augmentation method only by WGAN-GP, the accuracy of ResNet18 increased by 3.08%, and the accuracy of VGG11 increased by 3.55%. The results demonstrate the effectiveness of the proposed method with limited training datasets.