当前位置: X-MOL 学术Appl. Soft Comput. › 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.)
Identifying crop diseases using attention embedded MobileNet-V2 model
Applied Soft Computing ( IF 8.7 ) Pub Date : 2021-09-17 , DOI: 10.1016/j.asoc.2021.107901
Junde Chen 1 , Defu Zhang 1 , Md Suzauddola 1 , Adnan Zeb 1
Affiliation  

Various crop diseases are a major problem worldwide since their occurrence leads to a significant decrease in crop production. The image-based automatic identification of crop diseases that involves food security has attracted much attention recently. It is a challenging research topic due to the complexity of crop disease images, such as clutter field backdrops and irregular lighting strengths. A variety of deep learning networks, especially CNNs, are becoming the mainstream methods for addressing many challenges correlated with image recognition and classification. In this study, to improve the learning ability of minor lesion features, we introduced the Location-wise Soft Attention mechanism to the pre-trained MobileNet-V2, in which the general knowledge of images learned from ImageNet was migrated to our crop disease recognition mode, namely, CDRM. Further, a localization strategy was embedded in the proposed network, and the two-phase progressive strategy was executed for model training. The proposed method shows substantial efficacy in the experimental analyses. It reached a 99.71% average accuracy on the open-source dataset, and even under cluttered background conditions, the average accuracy attained 99.13% for the identification of crop diseases. Experimental findings deliver a competitive performance compared to other state-of-the-art methods and also indicate the efficacy and extension of the proposed method. Our code is available at https://github.com/xtu502/crop-disease-recognition-model.



中文翻译:

使用注意力嵌入 MobileNet-V2 模型识别作物病害

各种作物病害是世界范围内的主要问题,因为它们的发生导致作物产量显着下降。基于图像的粮食安全作物病害自动识别近年来备受关注。由于作物病害图像的复杂性,例如杂乱的田野背景和不规则的光照强度,这是一个具有挑战性的研究课题。各种深度学习网络,尤其是 CNN,正在成为解决与图像识别和分类相关的许多挑战的主流方法。在这项研究中,为了提高小病灶特征的学习能力,我们在预训练的 MobileNet-V2 中引入了 Location-wise Soft Attention 机制,其中从 ImageNet 学习的图像的一般知识迁移到我们的作物病害识别模式,即 CDRM。此外,在所提出的网络中嵌入了定位策略,并执行了两阶段渐进策略以进行模型训练。所提出的方法在实验分析中显示出显着的功效。在开源数据集上达到了99.71%的平均准确率,即使在杂乱的背景条件下,作物病害识别的平均准确率也达到了99.13%。与其他最先进的方法相比,实验结果提供了具有竞争力的性能,并且还表明了所提出方法的有效性和扩展性。我们的代码可在 https://github.com/xtu502/crop-disease-recognition-model 获得。所提出的方法在实验分析中显示出显着的功效。在开源数据集上达到了99.71%的平均准确率,即使在杂乱的背景条件下,作物病害识别的平均准确率也达到了99.13%。与其他最先进的方法相比,实验结果提供了具有竞争力的性能,并且还表明了所提出方法的有效性和扩展性。我们的代码可在 https://github.com/xtu502/crop-disease-recognition-model 获得。所提出的方法在实验分析中显示出显着的功效。在开源数据集上达到了99.71%的平均准确率,即使在杂乱的背景条件下,作物病害识别的平均准确率也达到了99.13%。与其他最先进的方法相比,实验结果提供了具有竞争力的性能,并且还表明了所提出方法的有效性和扩展性。我们的代码可在 https://github.com/xtu502/crop-disease-recognition-model 获得。与其他最先进的方法相比,实验结果提供了具有竞争力的性能,并且还表明了所提出方法的有效性和扩展性。我们的代码可在 https://github.com/xtu502/crop-disease-recognition-model 获得。与其他最先进的方法相比,实验结果提供了具有竞争力的性能,并且还表明了所提出方法的有效性和扩展性。我们的代码可在 https://github.com/xtu502/crop-disease-recognition-model 获得。

更新日期:2021-09-27
down
wechat
bug