Identification of rice plant diseases using lightweight attention networks
Identification of rice plant diseases using lightweight attention networks
复制标题
使用轻量级注意力网络识别水稻病害
DOI：
10.1016/j.eswa.2020.114514
复制
发表时间：
2021-01-05
影响因子：
8.5
通讯作者：
Nanehkaran, Yaser A.
中科院分区：
文献类型：
--
作者：
Chen, Junde;Zhang, Defu;Nanehkaran, Yaser A.
稻米是世界上最重要的农作物之一，大多数人将稻米作为主食，尤其是在亚洲国家。各种水稻病害对作物产量产生负面影响。如果不采取适当的检测，它们可能会传播并导致农业产量大幅下降。严重时甚至可能造成粮食绝收，对粮食安全造成毁灭性影响。基于深度学习的 CNN 方法已成为解决与图像识别和分类相关的大多数技术挑战的标准方法。在本研究中，为了增强微小病变特征的学习能力，我们选择在ImageNet上预训练的MobileNet-V2作为主干网络，并添加注意机制来学习通道间关系和空间点对于输入特征的重要性。同时，对损失函数进行优化，并进行两次迁移学习进行模型训练。与其他最先进的方法相比，所提出的程序具有优越的性能。它在公共数据集上的平均识别准确率达到99.67%。即使在复杂的背景条件下，水稻病害识别的平均准确率也达到98.48%。实验结果证明了该方法的有效性，并且有效地完成了水稻病害鉴定。
Rice is one of the most important crops in the world, and most people consume rice as a staple food, especially in Asian countries. Various rice plant diseases have a negative effect on crop yields. If proper detection is not taken, they can spread and lead to a significant decline in agricultural productions. In severe cases, they may even cause no grain harvest entirely, thus having a devastating impact on food security. The deep learning-based CNN methods have become the standard methods to address most of the technical challenges related to image identification and classification. In this study, to enhance the learning capability for minute lesion features, we chose the MobileNet-V2 pre-trained on ImageNet as the backbone network and added the attention mechanism to learn the importance of inter-channel relationship and spatial points for input features. In the meantime, the loss function was optimized and the transfer learning was performed twice for model training. The proposed procedure presents a superior performance relative to other state-of-the-art methods. It achieves an average identification accuracy of 99.67% on the public dataset. Even under complicated backdrop conditions, the average accuracy reaches 98.48% for identifying rice plant diseases. Experimental findings demonstrate the validity of the proposed procedure, and it is accomplished efficiently for rice disease identification.