当前位置: X-MOL 学术Plant Pathol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Attention embedded lightweight network for maize disease recognition
Plant Pathology ( IF 2.3 ) Pub Date : 2020-11-23 , DOI: 10.1111/ppa.13322
Junde Chen 1 , Wenhua Wang 2 , Defu Zhang 1 , Adnan Zeb 1 , Yaser Ahangari Nanehkaran 1
Affiliation  

Crop disease has a negative impact on food security. If diverse crop diseases are not identified in time, they can spread and influence the quality, quantity, and production of grain. Severe crop diseases can even result in complete failure of the harvest. Recent developments in deep learning, particularly convolutional neural networks (CNNs), have exhibited impressive performance in both image recognition and classification. In this study, we propose a novel network architecture, namely Mobile‐DANet, to identify maize crop diseases. Based on DenseNet, we retained the structure of the transition layers and used the depthwise separable convolution in dense blocks instead of the traditional convolution layers, and then embedded the attention module to learn the importance of interchannel relationship and spatial points for input features. In addition, transfer learning was used in model training. By this means, we improved the accuracy of the model while saving more computational power than deep CNNs. This model achieved an average accuracy of 98.50% on the open maize data set, and even with complicated backdrop conditions, Mobile‐DANet realized an average accuracy of 95.86% for identifying maize crop diseases on a local data set. The experimental findings show the effectiveness and feasibility of the Mobile‐DANet. Our data set is available at https://github.com/xtu502/maize‐disease‐identification.

中文翻译:

注意嵌入式轻量级网络,用于玉米疾病识别

作物病害对粮食安全产生不利影响。如果不能及时发现多种农作物病害,它们会传播并影响谷物的质量,数量和产量。严重的农作物病害甚至可能导致收成完全丧失。深度学习的最新发展,尤其是卷积神经网络(CNN),在图像识别和分类方面均表现出令人印象深刻的性能。在这项研究中,我们提出了一种新颖的网络架构,即Mobile-DANet,以识别玉米作物病害。在DenseNet的基础上,我们保留了过渡层的结构,并在密集块中使用了深度可分离卷积,而不是传统的卷积层,然后嵌入了注意力模块,以了解通道间关系和空间点对于输入特征的重要性。此外,在模型训练中使用了转移学习。通过这种方式,我们提高了模型的准确性,同时比深层CNN节省了更多的计算能力。该模型在开放的玉米数据集上的平均准确度达到98.50%,即使在复杂的背景条件下,Mobile-DANet在本地数据集上识别玉米作物病害的平均准确度也达到95.86%。实验结果表明了Mobile-DANet的有效性和可行性。我们的数据集位于https://github.com/xtu502/maize-disease-identification。Mobile-DANet在本地数据集上识别玉米作物病害的平均准确度达到95.86%。实验结果表明了Mobile-DANet的有效性和可行性。我们的数据集位于https://github.com/xtu502/maize-disease-identification。Mobile-DANet在本地数据集上识别玉米作物病害的平均准确度达到95.86%。实验结果证明了Mobile-DANet的有效性和可行性。我们的数据集位于https://github.com/xtu502/maize-disease-identification。
更新日期:2020-11-23
down
wechat
bug