| 基于迁移学习和改进CNN的葡萄叶部病害检测系统 |
| |
| 引用本文： | 樊湘鹏,许燕,周建平,李志磊,彭炫,王小荣.基于迁移学习和改进CNN的葡萄叶部病害检测系统[J].农业工程学报,2021,37(6):151-159. |
| |
| 作者姓名： | 樊湘鹏 许燕 周建平 李志磊 彭炫 王小荣 |
| |
| 作者单位： | 1.新疆大学机械工程学院，乌鲁木齐 830047；2.新疆维吾尔自治区农牧机器人及智能装备工程研究中心，乌鲁木齐 830047；3.新疆大学机械制造系统工程国家重点实验分室，乌鲁木齐 830047;1.新疆大学机械工程学院，乌鲁木齐 830047；2.新疆维吾尔自治区农牧机器人及智能装备工程研究中心，乌鲁木齐 830047；4. 新疆大学工程训练中心，乌鲁木齐 830047 |
| |
| 基金项目： | 国家自然科学基金资助项目（51765063）；新疆维吾尔自治区天山雪松科技创新领军人才计划项目（2018xs01）；新疆维吾尔自治区研究生科研创新项目（XJ2019G033） |
| |
| 摘 要： | 为建立高效、准确的葡萄叶部病害检测系统,引入迁移学习机制,利用大型公开数据集对VGG16模型预训练,保持模型前端13个层的参数和权重不变,对全连接层和分类层改进后利用新数据集微调训练模型,包括对训练优化器、学习率和中心损失函数平衡参数的优选试验,最后将模型部署在Android手机端。试验表明,在微调训练阶段选择Adam优化器、初始学习率设为0.001、中心损失函数平衡参数设为0.12时,改进的VGG16模型性能最优,对葡萄6类叶部图像的分类平均准确率为98.02%,单幅图像平均检测耗时为0.327s。与未改进的VGG16模型相比,平均准确率提高了2.82%,平均检测耗时下降了66.8%,权重参数数量减少了83.4%。改进后的模型综合性能优于AlexNet、ResNet50和Inceptionv3等模型。将模型跨平台部署在Android手机端,自然环境下验证的平均准确率为95.67%,平均检测耗时为0.357 s。该研究建立的基于迁移学习和改进卷积神经网络的病害检测系统可实现对葡萄叶部病害的快速、智能诊断,为葡萄病害的及时防控提供依据。
|
| 关 键 词： | 图像识别 病害 葡萄叶 迁移学习 卷积神经网络 全局平均池化 手机识别系统 智能诊断 |
| 收稿时间： | 2020/10/16 0:00:00 |
| 修稿时间： | 2021/3/2 0:00:00 |
Detection system for grape leaf diseases based on transfer learning and updated CNN |
| |
| Fan Xiangpeng,Xu Yan,Zhou Jianping,Li Zhilei,Peng Xuan,Wang Xiaorong.Detection system for grape leaf diseases based on transfer learning and updated CNN[J].Transactions of the Chinese Society of Agricultural Engineering,2021,37(6):151-159. |
| |
| Authors: | Fan Xiangpeng Xu Yan Zhou Jianping Li Zhilei Peng Xuan Wang Xiaorong |
| |
| Institution: | 1.College of Mechanical Engineering, Xinjiang University, Urumqi 830047, China; 2. Agriculture and Animal Husbandry Robot and Intelligent Equipment Engineering Research Center of Xinjiang Uygur Autonomous Region,Urumqi 830047, China; 3. National key laboratory of mechanical manufacturing system engineering branch of Xinjiang University, Urumqi 830047, China;;1.College of Mechanical Engineering, Xinjiang University, Urumqi 830047, China; 2. Agriculture and Animal Husbandry Robot and Intelligent Equipment Engineering Research Center of Xinjiang Uygur Autonomous Region,Urumqi 830047, China;4.Engineering Training Center, Xinjiang University, Urumqi 830047, China;2.Agriculture and Animal Husbandry Robot and Intelligent Equipment Engineering Research Center of Xinjiang Uygur Autonomous Region,Urumqi 830047, China;4.Engineering Training Center, Xinjiang University, Urumqi 830047, China |
| |
| Abstract: | Abstract: Leaf diseases have a severe threat to the quality and yield of grapes. However, there is often difficulty in the disease detection and low application rate of convolutional neural network (CNN) in a complicated field environment. In this study, an accurate and intelligent detection system was established to realize the strong robustness and real-time performance for grape leaf diseases using transfer learning and an updated CNN model. Firstly, 1990 images were captured for the healthy leaves and five types of infected leaves from field conditions. The combined datasets of PlantVillage and AI Challenger were used to pre-train the VGG16 network for the fully trained parameters. Secondly, the batch normalization, global average pooling layer, and Center Loss function were utilized to modify the structure of the pre-trained VGG16 network, where there was no change in the parameters of the thirteen front convolutional layers and pooling layers. The updated CNN was fine-tuned with the augmented images of grape leaves from field conditions. Stochastic gradient descent (SGD) and adaptive moment estimation (Adam) optimizers were adopted at the initial learning rates of 0.01 and 0.001 in the phase of fine-tuning for experimental comparison. Thirdly, different equilibrium parameters of Center Loss function were utilized in Softmax classification layer for optimal performance. The updated CNN model was also compared with the state-of-the-art models. Finally, the optimal CNN model was deployed in mobile phones to carry out in field condition. The experimental results showed that the updated model using Adam optimizer behaved with a higher accuracy and more stable performance than those using the SGD in the fine-tuning training phase. There were a higher accuracy, a lower loss value, and smaller vibration in the trained model with a small initial learning rate of 0.001 than those with a larger initial learning rate of 0.01, indicating that a smaller learning rate was more reasonable for fine-tuning training. In addition, the accuracy of the model was improved by the equilibrium parameter with a certain range in a Center Loss function. When the equilibrium parameter was set as 0.12, optimal performance of the updated CNN model was achieved at the initial learning rate of 0.001, where the average classification precision was 0.980 0, the recall was 0.980 1, the F1 score was 0.980 1, the average accuracy was 98.02%, and the testing time per image was 0.327 s. The accuracy of updated CNN increased by 2.82%, while the detection time was reduced by 66.8%, and the number of parameters decreased by 83.4%, compared with the original VGG16 network. The comprehensive performance of the updated VGG16 model was also better than that of AlexNet, ResNet50, and Inception v3 models, indicating obvious advantages in the accuracy, weight space occupation, and testing time for the detection of grape leaf diseases. It infers that the Batch normalization layer can speed up the learning process, whereas, the Global average pooling layer without fully connected layers can greatly reduce the number of weight parameters of the model. Center Loss function improved the ability of fine classification. After deployed into smart phone platform, the detection system maintained an accuracy of 95.67% and detection time of 0.357 s per image for the portable and intelligent diagnostics of grape leaf diseases. The transfer learning provided the possibility of quickly acquiring high-performance model under the condition of small datasets. The finding can provide precise guide for the prevention and control of grape diseases in fields. |
| |
| Keywords: | image recognition diseases grape leaf transfer learning convolutional neural network global average pooling mobile phone recognition system intelligent diagnosis |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《农业工程学报》浏览原始摘要信息 |
| 点击此处可从《农业工程学报》下载免费的PDF全文 |
|
