IEEE/ACM Trans Comput Biol Bioinform. 2022 May-Jun;19(3):1817-1826. doi: 10.1109/TCBB.2021.3056683. Epub 2022 Jun 3.
Plant leaves can be used to effectively detect plant diseases. However, the number of images of unhealthy leaves collected from various plants is usually unbalanced. It is difficult to detect diseases using such an unbalanced dataset. We used DoubleGAN (a double generative adversarial network) to generate images of unhealthy plant leaves to balance such datasets. We proposed using DoubleGAN to generate high-resolution images of unhealthy leaves using fewer samples. DoubleGAN is divided into two stages. In stage 1, we used healthy leaves and unhealthy leaves as inputs. First, the healthy leaf images were used as inputs for the WGAN (Wasserstein generative adversarial network) to obtain the pretrained model. Then, unhealthy leaves were used for the pretrained model to generate 6464 pixel images of unhealthy leaves. In stage 2, a superresolution generative adversarial network (SRGAN) was used to obtain corresponding 256256 pixel images to expand the unbalanced dataset. Finally, compared with images generated by DCGAN (Deep convolution generative adversarial network). The dataset expanded with DoubleGAN, the generated images are clearer than DCGAN, and the accuracy of plant species and disease recognition reached 99.80 and 99.53 percent, respectively. The recognition results are better than those from the original dataset.
植物叶片可用于有效检测植物病害。然而，从各种植物采集的不健康叶片图像数量通常是不平衡的。使用这样一个不平衡的数据集很难检测疾病。我们使用 DoubleGAN（双生成对抗网络）生成不健康植物叶片的图像来平衡此类数据集。我们提出使用 DoubleGAN 利用较少的样本生成高分辨率的不健康叶片图像。DoubleGAN 分为两个阶段。在第一阶段，我们使用健康叶片和不健康叶片作为输入。首先，将健康叶片图像用作 WGAN（Wasserstein 生成对抗网络）的输入，以获得预训练模型。然后，将不健康的叶片用于预训练模型以生成 6464 像素的不健康叶片图像。在第二阶段，使用超分辨率生成对抗网络 (SRGAN) 获得相应的 256256 像素图像，以扩展不平衡数据集。最后，与由 DCGAN（深度卷积生成对抗网络）生成的图像相比。使用 DoubleGAN 扩展的数据集，生成的图像比 DCGAN 更清晰，植物种类和疾病识别的准确率分别达到 99.80%和 99.53%。识别结果优于原始数据集。
