Plant Disease Detection Using Deep Convolutional Neural Network
Plant Disease Detection Using Deep Convolutional Neural Network
复制标题
DOI：
10.3390/app12146982
复制
发表时间：
2022-07-01
影响因子：
2.7
通讯作者：
Kanchanadevi, K.
中科院分区：
文献类型：
--
作者：
Pandian, J. Arun;Kumar, V. Dhilip;Kanchanadevi, K.
在这项研究中，我们提出了一种新型 14 层深度卷积神经网络 (14-DCNN)，利用叶子图像来检测植物叶子疾病。使用各种开放数据集创建了一个新数据集。使用数据增强技术来平衡数据集的各个类别的大小。使用了三种图像增强技术：基本图像处理（BIM）、深度卷积生成对抗网络（DCGAN）和神经风格迁移（NST）。该数据集包含 58 种不同的健康和患病植物叶类以及一种无叶植物的 147,500 张图像。所提出的 DCNN 模型在多图形处理单元 (MGPU) 环境中训练了 1000 个 epoch。使用从粗到精搜索技术的随机搜索来选择最合适的超参数值，以提高所提出的 DCNN 模型的训练性能。在 8850 张测试图像上，所提出的 DCNN 模型实现了 99.9655% 的总体分类精度、99.7999% 的加权平均精度、99.7966% 的加权平均召回率和 99.7968% 的加权平均 F1 分数。此外，所提出的 DCNN 模型的整体性能优于现有的迁移学习方法。
In this research, we proposed a novel 14-layered deep convolutional neural network (14-DCNN) to detect plant leaf diseases using leaf images. A new dataset was created using various open datasets. Data augmentation techniques were used to balance the individual class sizes of the dataset. Three image augmentation techniques were used: basic image manipulation (BIM), deep convolutional generative adversarial network (DCGAN) and neural style transfer (NST). The dataset consists of 147,500 images of 58 different healthy and diseased plant leaf classes and one no-leaf class. The proposed DCNN model was trained in the multi-graphics processing units (MGPUs) environment for 1000 epochs. The random search with the coarse-to-fine searching technique was used to select the most suitable hyperparameter values to improve the training performance of the proposed DCNN model. On the 8850 test images, the proposed DCNN model achieved 99.9655% overall classification accuracy, 99.7999% weighted average precision, 99.7966% weighted average recall, and 99.7968% weighted average F1 score. Additionally, the overall performance of the proposed DCNN model was better than the existing transfer learning approaches.