Department of Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology, Chennai, India.
School of Computing and Information Technology, Reva University, Bengaluru, India.
Comput Intell Neurosci. 2022 Sep 14;2022:5102290. doi: 10.1155/2022/5102290. eCollection 2022.
In this research, we proposed a novel deep residual convolutional neural network with 197 layers (ResNet197) for the detection of various plant leaf diseases. Six blocks of layers were used to develop ResNet197. ResNet197 was trained and tested using a combined plant leaf disease image dataset. Scaling, cropping, flipping, padding, rotation, affine transformation, saturation, and hue transformation techniques were used to create the augmentation data of the plant leaf disease image dataset. The dataset consisted of 103 diseased and healthy image classes of 22 plants and 154,500 images of healthy and diseased plant leaves. The evolutionary search technique was used to optimise the layers and hyperparameter values of ResNet197. ResNet197 was trained on the combined plant leaf disease image dataset using a graphics processing unit (GPU) environment for 1000 epochs. It produced a 99.58 percentage average classification accuracy on the test dataset. The experimental results were superior to existing ResNet architectures and recent transfer learning techniques.
在这项研究中，我们提出了一种具有 197 层的新型深度残差卷积神经网络（ResNet197），用于检测各种植物叶片病害。使用六个层块来开发 ResNet197。使用组合的植物叶片病害图像数据集对 ResNet197 进行训练和测试。使用缩放、裁剪、翻转、填充、旋转、仿射变换、饱和度和色调变换技术来创建植物叶片病害图像数据集的扩充数据。该数据集由 22 种植物的 103 个患病和健康图像类以及 154,500 张健康和患病植物叶片图像组成。使用进化搜索技术来优化 ResNet197 的层和超参数值。使用图形处理单元（GPU）环境在组合的植物叶片病害图像数据集上对 ResNet197 进行了 1000 个时期的训练。它在测试数据集上产生了 99.58%的平均分类准确率。实验结果优于现有的 ResNet 架构和最近的迁移学习技术。
